Prediction of residue-residue contact matrix for protein-protein interaction with Fisher score features and deep learning.

PubMed

Du, Tianchuan; Liao, Li; Wu, Cathy H; Sun, Bilin

2016-11-01

Protein-protein interactions play essential roles in many biological processes. Acquiring knowledge of the residue-residue contact information of two interacting proteins is not only helpful in annotating functions for proteins, but also critical for structure-based drug design. The prediction of the protein residue-residue contact matrix of the interfacial regions is challenging. In this work, we introduced deep learning techniques (specifically, stacked autoencoders) to build deep neural network models to tackled the residue-residue contact prediction problem. In tandem with interaction profile Hidden Markov Models, which was used first to extract Fisher score features from protein sequences, stacked autoencoders were deployed to extract and learn hidden abstract features. The deep learning model showed significant improvement over the traditional machine learning model, Support Vector Machines (SVM), with the overall accuracy increased by 15% from 65.40% to 80.82%. We showed that the stacked autoencoders could extract novel features, which can be utilized by deep neural networks and other classifiers to enhance learning, out of the Fisher score features. It is further shown that deep neural networks have significant advantages over SVM in making use of the newly extracted features. Copyright © 2016. Published by Elsevier Inc.

SchNet - A deep learning architecture for molecules and materials

NASA Astrophysics Data System (ADS)

Schütt, K. T.; Sauceda, H. E.; Kindermans, P.-J.; Tkatchenko, A.; Müller, K.-R.

2018-06-01

Deep learning has led to a paradigm shift in artificial intelligence, including web, text, and image search, speech recognition, as well as bioinformatics, with growing impact in chemical physics. Machine learning, in general, and deep learning, in particular, are ideally suitable for representing quantum-mechanical interactions, enabling us to model nonlinear potential-energy surfaces or enhancing the exploration of chemical compound space. Here we present the deep learning architecture SchNet that is specifically designed to model atomistic systems by making use of continuous-filter convolutional layers. We demonstrate the capabilities of SchNet by accurately predicting a range of properties across chemical space for molecules and materials, where our model learns chemically plausible embeddings of atom types across the periodic table. Finally, we employ SchNet to predict potential-energy surfaces and energy-conserving force fields for molecular dynamics simulations of small molecules and perform an exemplary study on the quantum-mechanical properties of C20-fullerene that would have been infeasible with regular ab initio molecular dynamics.

Creating the learning situation to promote student deep learning: Data analysis and application case

NASA Astrophysics Data System (ADS)

Guo, Yuanyuan; Wu, Shaoyan

2017-05-01

How to lead students to deeper learning and cultivate engineering innovative talents need to be studied for higher engineering education. In this study, through the survey data analysis and theoretical research, we discuss the correlation of teaching methods, learning motivation, and learning methods. In this research, we find that students have different motivation orientation according to the perception of teaching methods in the process of engineering education, and this affects their choice of learning methods. As a result, creating situations is critical to lead students to deeper learning. Finally, we analyze the process of learning situational creation in the teaching process of «bidding and contract management workshops». In this creation process, teachers use the student-centered teaching to lead students to deeper study. Through the study of influence factors of deep learning process, and building the teaching situation for the purpose of promoting deep learning, this thesis provide a meaningful reference for enhancing students' learning quality, teachers' teaching quality and the quality of innovation talent.

BiRen: predicting enhancers with a deep-learning-based model using the DNA sequence alone.

PubMed

Yang, Bite; Liu, Feng; Ren, Chao; Ouyang, Zhangyi; Xie, Ziwei; Bo, Xiaochen; Shu, Wenjie

2017-07-01

Enhancer elements are noncoding stretches of DNA that play key roles in controlling gene expression programmes. Despite major efforts to develop accurate enhancer prediction methods, identifying enhancer sequences continues to be a challenge in the annotation of mammalian genomes. One of the major issues is the lack of large, sufficiently comprehensive and experimentally validated enhancers for humans or other species. Thus, the development of computational methods based on limited experimentally validated enhancers and deciphering the transcriptional regulatory code encoded in the enhancer sequences is urgent. We present a deep-learning-based hybrid architecture, BiRen, which predicts enhancers using the DNA sequence alone. Our results demonstrate that BiRen can learn common enhancer patterns directly from the DNA sequence and exhibits superior accuracy, robustness and generalizability in enhancer prediction relative to other state-of-the-art enhancer predictors based on sequence characteristics. Our BiRen will enable researchers to acquire a deeper understanding of the regulatory code of enhancer sequences. Our BiRen method can be freely accessed at https://github.com/wenjiegroup/BiRen . shuwj@bmi.ac.cn or boxc@bmi.ac.cn. Supplementary data are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Deep learning in mammography and breast histology, an overview and future trends.

PubMed

Hamidinekoo, Azam; Denton, Erika; Rampun, Andrik; Honnor, Kate; Zwiggelaar, Reyer

2018-07-01

Recent improvements in biomedical image analysis using deep learning based neural networks could be exploited to enhance the performance of Computer Aided Diagnosis (CAD) systems. Considering the importance of breast cancer worldwide and the promising results reported by deep learning based methods in breast imaging, an overview of the recent state-of-the-art deep learning based CAD systems developed for mammography and breast histopathology images is presented. In this study, the relationship between mammography and histopathology phenotypes is described, which takes biological aspects into account. We propose a computer based breast cancer modelling approach: the Mammography-Histology-Phenotype-Linking-Model, which develops a mapping of features/phenotypes between mammographic abnormalities and their histopathological representation. Challenges are discussed along with the potential contribution of such a system to clinical decision making and treatment management. Crown Copyright © 2018. Published by Elsevier B.V. All rights reserved.

The Power and Utility of Reflective Learning Portfolios in Honors

ERIC Educational Resources Information Center

Corley, Christopher R.; Zubizarreta, John

2012-01-01

The explosive growth of learning portfolios in higher education as a compelling tool for enhanced student learning, assessment, and career preparation is a sign of the increasing significance of reflective practice and mindful, systematic documentation in promoting deep, meaningful, transformative learning experiences. The advent of sophisticated…

Bothered by abstractness or engaged by cohesion? Experts' explanations enhance novices' deep-learning.

PubMed

Lachner, Andreas; Nückles, Matthias

2015-03-01

Experts' explanations have been shown to better enhance novices' transfer as compared with advanced students' explanations. Based on research on expertise and text comprehension, we investigated whether the abstractness or the cohesion of experts' and intermediates' explanations accounted for novices' learning. In Study 1, we showed that the superior cohesion of experts' explanations accounted for most of novices' transfer, whereas the degree of abstractness did not impact novices' transfer performance. In Study 2, we investigated novices' processing while learning with experts' and intermediates' explanations. We found that novices studying experts' explanations actively self-regulated their processing of the explanations, as they showed mainly deep-processing activities, whereas novices learning with intermediates' explanations were mainly engaged in shallow-processing activities by paraphrasing the explanations. Thus, we concluded that subject-matter expertise is a crucial prerequisite for instructors. Despite the abstract character of experts' explanations, their subject-matter expertise enables them to generate highly cohesive explanations that serve as a valuable scaffold for students' construction of flexible knowledge by engaging them in deep-level processing. PsycINFO Database Record (c) 2015 APA, all rights reserved.

Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI.

PubMed

Gong, Enhao; Pauly, John M; Wintermark, Max; Zaharchuk, Greg

2018-02-13

There are concerns over gadolinium deposition from gadolinium-based contrast agents (GBCA) administration. To reduce gadolinium dose in contrast-enhanced brain MRI using a deep learning method. Retrospective, crossover. Sixty patients receiving clinically indicated contrast-enhanced brain MRI. 3D T 1 -weighted inversion-recovery prepped fast-spoiled-gradient-echo (IR-FSPGR) imaging was acquired at both 1.5T and 3T. In 60 brain MRI exams, the IR-FSPGR sequence was obtained under three conditions: precontrast, postcontrast images with 10% low-dose (0.01mmol/kg) and 100% full-dose (0.1 mmol/kg) of gadobenate dimeglumine. We trained a deep learning model using the first 10 cases (with mixed indications) to approximate full-dose images from the precontrast and low-dose images. Synthesized full-dose images were created using the trained model in two test sets: 20 patients with mixed indications and 30 patients with glioma. For both test sets, low-dose, true full-dose, and the synthesized full-dose postcontrast image sets were compared quantitatively using peak-signal-to-noise-ratios (PSNR) and structural-similarity-index (SSIM). For the test set comprised of 20 patients with mixed indications, two neuroradiologists scored blindly and independently for the three postcontrast image sets, evaluating image quality, motion-artifact suppression, and contrast enhancement compared with precontrast images. Results were assessed using paired t-tests and noninferiority tests. The proposed deep learning method yielded significant (n = 50, P < 0.001) improvements over the low-dose images (>5 dB PSNR gains and >11.0% SSIM). Ratings on image quality (n = 20, P = 0.003) and contrast enhancement (n = 20, P < 0.001) were significantly increased. Compared to true full-dose images, the synthesized full-dose images have a slight but not significant reduction in image quality (n = 20, P = 0.083) and contrast enhancement (n = 20, P = 0.068). Slightly better (n = 20, P = 0.039) motion-artifact suppression was noted in the synthesized images. The noninferiority test rejects the inferiority of the synthesized to true full-dose images for image quality (95% CI: -14-9%), artifacts suppression (95% CI: -5-20%), and contrast enhancement (95% CI: -13-6%). With the proposed deep learning method, gadolinium dose can be reduced 10-fold while preserving contrast information and avoiding significant image quality degradation. 3 Technical Efficacy: Stage 5 J. Magn. Reson. Imaging 2018. © 2018 International Society for Magnetic Resonance in Medicine.

Multi-level gene/MiRNA feature selection using deep belief nets and active learning.

PubMed

Ibrahim, Rania; Yousri, Noha A; Ismail, Mohamed A; El-Makky, Nagwa M

2014-01-01

Selecting the most discriminative genes/miRNAs has been raised as an important task in bioinformatics to enhance disease classifiers and to mitigate the dimensionality curse problem. Original feature selection methods choose genes/miRNAs based on their individual features regardless of how they perform together. Considering group features instead of individual ones provides a better view for selecting the most informative genes/miRNAs. Recently, deep learning has proven its ability in representing the data in multiple levels of abstraction, allowing for better discrimination between different classes. However, the idea of using deep learning for feature selection is not widely used in the bioinformatics field yet. In this paper, a novel multi-level feature selection approach named MLFS is proposed for selecting genes/miRNAs based on expression profiles. The approach is based on both deep and active learning. Moreover, an extension to use the technique for miRNAs is presented by considering the biological relation between miRNAs and genes. Experimental results show that the approach was able to outperform classical feature selection methods in hepatocellular carcinoma (HCC) by 9%, lung cancer by 6% and breast cancer by around 10% in F1-measure. Results also show the enhancement in F1-measure of our approach over recently related work in [1] and [2].

Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopy.

PubMed

Terunuma, Toshiyuki; Tokui, Aoi; Sakae, Takeji

2018-03-01

Robustness to obstacles is the most important factor necessary to achieve accurate tumor tracking without fiducial markers. Some high-density structures, such as bone, are enhanced on X-ray fluoroscopic images, which cause tumor mistracking. Tumor tracking should be performed by controlling "importance recognition": the understanding that soft-tissue is an important tracking feature and bone structure is unimportant. We propose a new real-time tumor-contouring method that uses deep learning with importance recognition control. The novelty of the proposed method is the combination of the devised random overlay method and supervised deep learning to induce the recognition of structures in tumor contouring as important or unimportant. This method can be used for tumor contouring because it uses deep learning to perform image segmentation. Our results from a simulated fluoroscopy model showed accurate tracking of a low-visibility tumor with an error of approximately 1 mm, even if enhanced bone structure acted as an obstacle. A high similarity of approximately 0.95 on the Jaccard index was observed between the segmented and ground truth tumor regions. A short processing time of 25 ms was achieved. The results of this simulated fluoroscopy model support the feasibility of robust real-time tumor contouring with fluoroscopy. Further studies using clinical fluoroscopy are highly anticipated.

3D Deep Learning Angiography (3D-DLA) from C-arm Conebeam CT.

PubMed

Montoya, J C; Li, Y; Strother, C; Chen, G-H

2018-05-01

Deep learning is a branch of artificial intelligence that has demonstrated unprecedented performance in many medical imaging applications. Our purpose was to develop a deep learning angiography method to generate 3D cerebral angiograms from a single contrast-enhanced C-arm conebeam CT acquisition in order to reduce image artifacts and radiation dose. A set of 105 3D rotational angiography examinations were randomly selected from an internal data base. All were acquired using a clinical system in conjunction with a standard injection protocol. More than 150 million labeled voxels from 35 subjects were used for training. A deep convolutional neural network was trained to classify each image voxel into 3 tissue types (vasculature, bone, and soft tissue). The trained deep learning angiography model was then applied for tissue classification into a validation cohort of 8 subjects and a final testing cohort of the remaining 62 subjects. The final vasculature tissue class was used to generate the 3D deep learning angiography images. To quantify the generalization error of the trained model, we calculated the accuracy, sensitivity, precision, and Dice similarity coefficients for vasculature classification in relevant anatomy. The 3D deep learning angiography and clinical 3D rotational angiography images were subjected to a qualitative assessment for the presence of intersweep motion artifacts. Vasculature classification accuracy and 95% CI in the testing dataset were 98.7% (98.3%-99.1%). No residual signal from osseous structures was observed for any 3D deep learning angiography testing cases except for small regions in the otic capsule and nasal cavity compared with 37% (23/62) of the 3D rotational angiographies. Deep learning angiography accurately recreated the vascular anatomy of the 3D rotational angiography reconstructions without a mask. Deep learning angiography reduced misregistration artifacts induced by intersweep motion, and it reduced radiation exposure required to obtain clinically useful 3D rotational angiography. © 2018 by American Journal of Neuroradiology.

Context odor presentation during sleep enhances memory in honeybees.

PubMed

Zwaka, Hanna; Bartels, Ruth; Gora, Jacob; Franck, Vivien; Culo, Ana; Götsch, Moritz; Menzel, Randolf

2015-11-02

Sleep plays an important role in stabilizing new memory traces after learning [1-3]. Here we investigate whether sleep's role in memory processing is similar in evolutionarily distant species and demonstrate that a context trigger during deep-sleep phases improves memory in invertebrates, as it does in humans. We show that in honeybees (Apis mellifera), exposure to an odor during deep sleep that has been present during learning improves memory performance the following day. Presentation of the context odor during wake phases or novel odors during sleep does not enhance memory. In humans, memory consolidation can be triggered by presentation of a context odor during slow-wave sleep that had been present during learning [3-5]. Our results reveal that deep-sleep phases in honeybees have the potential to prompt memory consolidation, just as they do in humans. This study provides strong evidence for a conserved role of sleep-and how it affects memory processes-from insects to mammals. Copyright © 2015 Elsevier Ltd. All rights reserved.

Deep Learning in Gastrointestinal Endoscopy.

PubMed

Patel, Vivek; Armstrong, David; Ganguli, Malika; Roopra, Sandeep; Kantipudi, Neha; Albashir, Siwar; Kamath, Markad V

2016-01-01

Gastrointestinal (GI) endoscopy is used to inspect the lumen or interior of the GI tract for several purposes, including, (1) making a clinical diagnosis, in real time, based on the visual appearances; (2) taking targeted tissue samples for subsequent histopathological examination; and (3) in some cases, performing therapeutic interventions targeted at specific lesions. GI endoscopy is therefore predicated on the assumption that the operator-the endoscopist-is able to identify and characterize abnormalities or lesions accurately and reproducibly. However, as in other areas of clinical medicine, such as histopathology and radiology, many studies have documented marked interobserver and intraobserver variability in lesion recognition. Thus, there is a clear need and opportunity for techniques or methodologies that will enhance the quality of lesion recognition and diagnosis and improve the outcomes of GI endoscopy. Deep learning models provide a basis to make better clinical decisions in medical image analysis. Biomedical image segmentation, classification, and registration can be improved with deep learning. Recent evidence suggests that the application of deep learning methods to medical image analysis can contribute significantly to computer-aided diagnosis. Deep learning models are usually considered to be more flexible and provide reliable solutions for image analysis problems compared to conventional computer vision models. The use of fast computers offers the possibility of real-time support that is important for endoscopic diagnosis, which has to be made in real time. Advanced graphics processing units and cloud computing have also favored the use of machine learning, and more particularly, deep learning for patient care. This paper reviews the rapidly evolving literature on the feasibility of applying deep learning algorithms to endoscopic imaging.

Two Stage Data Augmentation for Low Resourced Speech Recognition (Author’s Manuscript)

DTIC Science & Technology

2016-09-12

speech recognition, deep neural networks, data augmentation 1. Introduction When training data is limited—whether it be audio or text—the obvious...Schwartz, and S. Tsakalidis, “Enhancing low resource keyword spotting with au- tomatically retrieved web documents,” in Interspeech, 2015, pp. 839–843. [2...and F. Seide, “Feature learning in deep neural networks - a study on speech recognition tasks,” in International Conference on Learning Representations

Community-Based Learning: Engaging Students for Success and Citizenship

ERIC Educational Resources Information Center

Melaville, Atelia; Berg, Amy C.; Blank, Martin J.

2006-01-01

Community schools foster a learning environment that extends far beyond the classroom walls. Students learn and problem solve in the context of their lives and communities. Community schools nurture this natural engagement. Because of the deep and purposeful connections between schools and communities, the curriculum is influenced and enhanced,…

A new method for enhancer prediction based on deep belief network.

PubMed

Bu, Hongda; Gan, Yanglan; Wang, Yang; Zhou, Shuigeng; Guan, Jihong

2017-10-16

Studies have shown that enhancers are significant regulatory elements to play crucial roles in gene expression regulation. Since enhancers are unrelated to the orientation and distance to their target genes, it is a challenging mission for scholars and researchers to accurately predicting distal enhancers. In the past years, with the high-throughout ChiP-seq technologies development, several computational techniques emerge to predict enhancers using epigenetic or genomic features. Nevertheless, the inconsistency of computational models across different cell-lines and the unsatisfactory prediction performance call for further research in this area. Here, we propose a new Deep Belief Network (DBN) based computational method for enhancer prediction, which is called EnhancerDBN. This method combines diverse features, composed of DNA sequence compositional features, DNA methylation and histone modifications. Our computational results indicate that 1) EnhancerDBN outperforms 13 existing methods in prediction, and 2) GC content and DNA methylation can serve as relevant features for enhancer prediction. Deep learning is effective in boosting the performance of enhancer prediction.

Summative Co-Assessment: A Deep Learning Approach To Enhancing Employability Skills and Attributes

ERIC Educational Resources Information Center

Deeley, Susan J.

2014-01-01

Service-learning is a pedagogy that combines academic study with service to the community. Voluntary work placements are integral to service-learning and offer students an ideal opportunity to develop their employability skills and attributes. In a service-learning course, it was considered good practice to raise students' awareness of the…

Toward a real-time system for temporal enhanced ultrasound-guided prostate biopsy.

PubMed

Azizi, Shekoofeh; Van Woudenberg, Nathan; Sojoudi, Samira; Li, Ming; Xu, Sheng; Abu Anas, Emran M; Yan, Pingkun; Tahmasebi, Amir; Kwak, Jin Tae; Turkbey, Baris; Choyke, Peter; Pinto, Peter; Wood, Bradford; Mousavi, Parvin; Abolmaesumi, Purang

2018-03-27

We have previously proposed temporal enhanced ultrasound (TeUS) as a new paradigm for tissue characterization. TeUS is based on analyzing a sequence of ultrasound data with deep learning and has been demonstrated to be successful for detection of cancer in ultrasound-guided prostate biopsy. Our aim is to enable the dissemination of this technology to the community for large-scale clinical validation. In this paper, we present a unified software framework demonstrating near-real-time analysis of ultrasound data stream using a deep learning solution. The system integrates ultrasound imaging hardware, visualization and a deep learning back-end to build an accessible, flexible and robust platform. A client-server approach is used in order to run computationally expensive algorithms in parallel. We demonstrate the efficacy of the framework using two applications as case studies. First, we show that prostate cancer detection using near-real-time analysis of RF and B-mode TeUS data and deep learning is feasible. Second, we present real-time segmentation of ultrasound prostate data using an integrated deep learning solution. The system is evaluated for cancer detection accuracy on ultrasound data obtained from a large clinical study with 255 biopsy cores from 157 subjects. It is further assessed with an independent dataset with 21 biopsy targets from six subjects. In the first study, we achieve area under the curve, sensitivity, specificity and accuracy of 0.94, 0.77, 0.94 and 0.92, respectively, for the detection of prostate cancer. In the second study, we achieve an AUC of 0.85. Our results suggest that TeUS-guided biopsy can be potentially effective for the detection of prostate cancer.

Deep Learning in Medical Imaging: General Overview

PubMed Central

Lee, June-Goo; Jun, Sanghoon; Cho, Young-Won; Lee, Hyunna; Kim, Guk Bae

2017-01-01

The artificial neural network (ANN)–a machine learning technique inspired by the human neuronal synapse system–was introduced in the 1950s. However, the ANN was previously limited in its ability to solve actual problems, due to the vanishing gradient and overfitting problems with training of deep architecture, lack of computing power, and primarily the absence of sufficient data to train the computer system. Interest in this concept has lately resurfaced, due to the availability of big data, enhanced computing power with the current graphics processing units, and novel algorithms to train the deep neural network. Recent studies on this technology suggest its potentially to perform better than humans in some visual and auditory recognition tasks, which may portend its applications in medicine and healthcare, especially in medical imaging, in the foreseeable future. This review article offers perspectives on the history, development, and applications of deep learning technology, particularly regarding its applications in medical imaging. PMID:28670152

Deep Learning in Medical Imaging: General Overview.

PubMed

Lee, June-Goo; Jun, Sanghoon; Cho, Young-Won; Lee, Hyunna; Kim, Guk Bae; Seo, Joon Beom; Kim, Namkug

2017-01-01

The artificial neural network (ANN)-a machine learning technique inspired by the human neuronal synapse system-was introduced in the 1950s. However, the ANN was previously limited in its ability to solve actual problems, due to the vanishing gradient and overfitting problems with training of deep architecture, lack of computing power, and primarily the absence of sufficient data to train the computer system. Interest in this concept has lately resurfaced, due to the availability of big data, enhanced computing power with the current graphics processing units, and novel algorithms to train the deep neural network. Recent studies on this technology suggest its potentially to perform better than humans in some visual and auditory recognition tasks, which may portend its applications in medicine and healthcare, especially in medical imaging, in the foreseeable future. This review article offers perspectives on the history, development, and applications of deep learning technology, particularly regarding its applications in medical imaging.

Enhanced Higgs boson to τ(+)τ(-) search with deep learning.

PubMed

Baldi, P; Sadowski, P; Whiteson, D

2015-03-20

The Higgs boson is thought to provide the interaction that imparts mass to the fundamental fermions, but while measurements at the Large Hadron Collider (LHC) are consistent with this hypothesis, current analysis techniques lack the statistical power to cross the traditional 5σ significance barrier without more data. Deep learning techniques have the potential to increase the statistical power of this analysis by automatically learning complex, high-level data representations. In this work, deep neural networks are used to detect the decay of the Higgs boson to a pair of tau leptons. A Bayesian optimization algorithm is used to tune the network architecture and training algorithm hyperparameters, resulting in a deep network of eight nonlinear processing layers that improves upon the performance of shallow classifiers even without the use of features specifically engineered by physicists for this application. The improvement in discovery significance is equivalent to an increase in the accumulated data set of 25%.

Written Identification of Errors to Learn Professional Procedures in VET

ERIC Educational Resources Information Center

Boldrini, Elena; Cattaneo, Alberto

2013-01-01

Research has demonstrated that the use of worked-out examples to present errors has great potential for procedural knowledge acquirement. Nevertheless, the identification of errors alone does not directly enhance a deep learning process if it is not adequately scaffolded by written self-explanations. We hypothesised that in learning a professional…

Influence of a veterinary curriculum on the approaches and study skills of veterinary medical students.

PubMed

Chigerwe, Munashe; Ilkiw, Jan E; Boudreaux, Karen A

2011-01-01

The objectives of the present study were to evaluate first-, second-, third-, and fourth-year veterinary medical students' approaches to studying and learning as well as the factors within the curriculum that may influence these approaches. A questionnaire consisting of the short version of the Approaches and Study Skills Inventory for Students (ASSIST) was completed by 405 students, and it included questions relating to conceptions about learning, approaches to studying, and preferences for different types of courses and teaching. Descriptive statistics, factor analysis, Cronbach's alpha analysis, and log-linear analysis were performed on the data. Deep, strategic, and surface learning approaches emerged. There were a few differences between our findings and those presented in previous studies in terms of the correlation of the subscale monitoring effectiveness, which showed loading with both the deep and strategic learning approaches. In addition, the subscale alertness to assessment demands showed correlation with the surface learning approach. The perception of high workloads, the use of previous test files as a method for studying, and examinations that are based only on material provided in lecture notes were positively associated with the surface learning approach. Focusing on improving specific teaching and assessment methods that enhance deep learning is anticipated to enhance students' positive learning experience. These teaching methods include instructors who encourage students to be critical thinkers, the integration of course material in other disciplines, courses that encourage thinking and reading about the learning material, and books and articles that challenge students while providing explanations beyond lecture material.

Rolling bearing fault feature learning using improved convolutional deep belief network with compressed sensing

NASA Astrophysics Data System (ADS)

Shao, Haidong; Jiang, Hongkai; Zhang, Haizhou; Duan, Wenjing; Liang, Tianchen; Wu, Shuaipeng

2018-02-01

The vibration signals collected from rolling bearing are usually complex and non-stationary with heavy background noise. Therefore, it is a great challenge to efficiently learn the representative fault features of the collected vibration signals. In this paper, a novel method called improved convolutional deep belief network (CDBN) with compressed sensing (CS) is developed for feature learning and fault diagnosis of rolling bearing. Firstly, CS is adopted for reducing the vibration data amount to improve analysis efficiency. Secondly, a new CDBN model is constructed with Gaussian visible units to enhance the feature learning ability for the compressed data. Finally, exponential moving average (EMA) technique is employed to improve the generalization performance of the constructed deep model. The developed method is applied to analyze the experimental rolling bearing vibration signals. The results confirm that the developed method is more effective than the traditional methods.

DeepARG: a deep learning approach for predicting antibiotic resistance genes from metagenomic data.

PubMed

Arango-Argoty, Gustavo; Garner, Emily; Pruden, Amy; Heath, Lenwood S; Vikesland, Peter; Zhang, Liqing

2018-02-01

Growing concerns about increasing rates of antibiotic resistance call for expanded and comprehensive global monitoring. Advancing methods for monitoring of environmental media (e.g., wastewater, agricultural waste, food, and water) is especially needed for identifying potential resources of novel antibiotic resistance genes (ARGs), hot spots for gene exchange, and as pathways for the spread of ARGs and human exposure. Next-generation sequencing now enables direct access and profiling of the total metagenomic DNA pool, where ARGs are typically identified or predicted based on the "best hits" of sequence searches against existing databases. Unfortunately, this approach produces a high rate of false negatives. To address such limitations, we propose here a deep learning approach, taking into account a dissimilarity matrix created using all known categories of ARGs. Two deep learning models, DeepARG-SS and DeepARG-LS, were constructed for short read sequences and full gene length sequences, respectively. Evaluation of the deep learning models over 30 antibiotic resistance categories demonstrates that the DeepARG models can predict ARGs with both high precision (> 0.97) and recall (> 0.90). The models displayed an advantage over the typical best hit approach, yielding consistently lower false negative rates and thus higher overall recall (> 0.9). As more data become available for under-represented ARG categories, the DeepARG models' performance can be expected to be further enhanced due to the nature of the underlying neural networks. Our newly developed ARG database, DeepARG-DB, encompasses ARGs predicted with a high degree of confidence and extensive manual inspection, greatly expanding current ARG repositories. The deep learning models developed here offer more accurate antimicrobial resistance annotation relative to current bioinformatics practice. DeepARG does not require strict cutoffs, which enables identification of a much broader diversity of ARGs. The DeepARG models and database are available as a command line version and as a Web service at http://bench.cs.vt.edu/deeparg .

Connecting Reflective Practice, Dialogic Protocols, and Professional Learning

ERIC Educational Resources Information Center

Nehring, James; Laboy, Wilfredo T.; Catarius, Lynn

2010-01-01

In recent years, elements of reflective practice have been popularized in state school professional development. As reflective practice has moved into the mainstream, dialogic protocols have been developed by numerous organizations to structure discourse for deep understanding, enhance professional practice and advance organizational learning.…

Approaches and Study Skills Inventory for Students (ASSIST) in an Introductory Course in Chemistry

ERIC Educational Resources Information Center

Brown, Stephen; White, Sue; Wakeling, Lara; Naiker, Mani

2015-01-01

Approaches to study and learning may enhance or undermine educational outcomes, and thus it is important for educators to be knowledgeable about their students' approaches to study and learning. The Approaches and Study Skills Inventory for Students (ASSIST)--a 52 item inventory which identifies three learning styles (Deep, Strategic, and…

Using Blogs as a Means of Enhancing Reflective Teaching Practice in Open Distance Learning Ecologies

ERIC Educational Resources Information Center

van Wyk, Micheal M.

2013-01-01

Reflection is an important concept or principle that is fundamental in the interpretation of new information, and is also required if learning is to advance from surface to deep learning. The purpose of this article is to explore the use of blogs as an e-learning journal writing tool for reflection and peer-feedback during Teaching Practice…

EP-DNN: A Deep Neural Network-Based Global Enhancer Prediction Algorithm.

PubMed

Kim, Seong Gon; Harwani, Mrudul; Grama, Ananth; Chaterji, Somali

2016-12-08

We present EP-DNN, a protocol for predicting enhancers based on chromatin features, in different cell types. Specifically, we use a deep neural network (DNN)-based architecture to extract enhancer signatures in a representative human embryonic stem cell type (H1) and a differentiated lung cell type (IMR90). We train EP-DNN using p300 binding sites, as enhancers, and TSS and random non-DHS sites, as non-enhancers. We perform same-cell and cross-cell predictions to quantify the validation rate and compare against two state-of-the-art methods, DEEP-ENCODE and RFECS. We find that EP-DNN has superior accuracy with a validation rate of 91.6%, relative to 85.3% for DEEP-ENCODE and 85.5% for RFECS, for a given number of enhancer predictions and also scales better for a larger number of enhancer predictions. Moreover, our H1 → IMR90 predictions turn out to be more accurate than IMR90 → IMR90, potentially because H1 exhibits a richer signature set and our EP-DNN model is expressive enough to extract these subtleties. Our work shows how to leverage the full expressivity of deep learning models, using multiple hidden layers, while avoiding overfitting on the training data. We also lay the foundation for exploration of cross-cell enhancer predictions, potentially reducing the need for expensive experimentation.

EP-DNN: A Deep Neural Network-Based Global Enhancer Prediction Algorithm

NASA Astrophysics Data System (ADS)

Kim, Seong Gon; Harwani, Mrudul; Grama, Ananth; Chaterji, Somali

2016-12-01

We present EP-DNN, a protocol for predicting enhancers based on chromatin features, in different cell types. Specifically, we use a deep neural network (DNN)-based architecture to extract enhancer signatures in a representative human embryonic stem cell type (H1) and a differentiated lung cell type (IMR90). We train EP-DNN using p300 binding sites, as enhancers, and TSS and random non-DHS sites, as non-enhancers. We perform same-cell and cross-cell predictions to quantify the validation rate and compare against two state-of-the-art methods, DEEP-ENCODE and RFECS. We find that EP-DNN has superior accuracy with a validation rate of 91.6%, relative to 85.3% for DEEP-ENCODE and 85.5% for RFECS, for a given number of enhancer predictions and also scales better for a larger number of enhancer predictions. Moreover, our H1 → IMR90 predictions turn out to be more accurate than IMR90 → IMR90, potentially because H1 exhibits a richer signature set and our EP-DNN model is expressive enough to extract these subtleties. Our work shows how to leverage the full expressivity of deep learning models, using multiple hidden layers, while avoiding overfitting on the training data. We also lay the foundation for exploration of cross-cell enhancer predictions, potentially reducing the need for expensive experimentation.

Deep learning for brain tumor classification

NASA Astrophysics Data System (ADS)

Paul, Justin S.; Plassard, Andrew J.; Landman, Bennett A.; Fabbri, Daniel

2017-03-01

Recent research has shown that deep learning methods have performed well on supervised machine learning, image classification tasks. The purpose of this study is to apply deep learning methods to classify brain images with different tumor types: meningioma, glioma, and pituitary. A dataset was publicly released containing 3,064 T1-weighted contrast enhanced MRI (CE-MRI) brain images from 233 patients with either meningioma, glioma, or pituitary tumors split across axial, coronal, or sagittal planes. This research focuses on the 989 axial images from 191 patients in order to avoid confusing the neural networks with three different planes containing the same diagnosis. Two types of neural networks were used in classification: fully connected and convolutional neural networks. Within these two categories, further tests were computed via the augmentation of the original 512×512 axial images. Training neural networks over the axial data has proven to be accurate in its classifications with an average five-fold cross validation of 91.43% on the best trained neural network. This result demonstrates that a more general method (i.e. deep learning) can outperform specialized methods that require image dilation and ring-forming subregions on tumors.

Peer Learning and Support of Technology in an Undergraduate Biology Course to Enhance Deep Learning

PubMed Central

Tsaushu, Masha; Tal, Tali; Sagy, Ornit; Kali, Yael; Gepstein, Shimon; Zilberstein, Dan

2012-01-01

This study offers an innovative and sustainable instructional model for an introductory undergraduate course. The model was gradually implemented during 3 yr in a research university in a large-lecture biology course that enrolled biology majors and nonmajors. It gives priority to sources not used enough to enhance active learning in higher education: technology and the students themselves. Most of the lectures were replaced with continuous individual learning and 1-mo group learning of one topic, both supported by an interactive online tutorial. Assessment included open-ended complex questions requiring higher-order thinking skills that were added to the traditional multiple-choice (MC) exam. Analysis of students’ outcomes indicates no significant difference among the three intervention versions in the MC questions of the exam, while students who took part in active-learning groups at the advanced version of the model had significantly higher scores in the more demanding open-ended questions compared with their counterparts. We believe that social-constructivist learning of one topic during 1 mo has significantly contributed to student deep learning across topics. It developed a biological discourse, which is more typical to advanced stages of learning biology, and changed the image of instructors from “knowledge transmitters” to “role model scientists.” PMID:23222836

Peer learning and support of technology in an undergraduate biology course to enhance deep learning.

PubMed

Tsaushu, Masha; Tal, Tali; Sagy, Ornit; Kali, Yael; Gepstein, Shimon; Zilberstein, Dan

2012-01-01

This study offers an innovative and sustainable instructional model for an introductory undergraduate course. The model was gradually implemented during 3 yr in a research university in a large-lecture biology course that enrolled biology majors and nonmajors. It gives priority to sources not used enough to enhance active learning in higher education: technology and the students themselves. Most of the lectures were replaced with continuous individual learning and 1-mo group learning of one topic, both supported by an interactive online tutorial. Assessment included open-ended complex questions requiring higher-order thinking skills that were added to the traditional multiple-choice (MC) exam. Analysis of students' outcomes indicates no significant difference among the three intervention versions in the MC questions of the exam, while students who took part in active-learning groups at the advanced version of the model had significantly higher scores in the more demanding open-ended questions compared with their counterparts. We believe that social-constructivist learning of one topic during 1 mo has significantly contributed to student deep learning across topics. It developed a biological discourse, which is more typical to advanced stages of learning biology, and changed the image of instructors from "knowledge transmitters" to "role model scientists."

[Efficacy of the program "Testas's (mis)adventures" to promote the deep approach to learning].

PubMed

Rosário, Pedro; González-Pienda, Julio Antonio; Cerezo, Rebeca; Pinto, Ricardo; Ferreira, Pedro; Abilio, Lourenço; Paiva, Olimpia

2010-11-01

This paper provides information about the efficacy of a tutorial training program intended to enhance elementary fifth graders' study processes and foster their deep approaches to learning. The program "Testas's (mis)adventures" consists of a set of books in which Testas, a typical student, reveals and reflects upon his life experiences during school years. These life stories are nothing but an opportunity to present and train a wide range of learning strategies and self-regulatory processes, designed to insure students' deeper preparation for present and future learning challenges. The program has been developed along a school year, in a one hour weekly tutorial sessions. The training program had a semi-experimental design, included an experimental group (n=50) and a control one (n=50), and used pre- and posttest measures (learning strategies' declarative knowledge, learning approaches and academic achievement). Data suggest that the students enrolled in the training program, comparing with students in the control group, showed a significant improvement in their declarative knowledge of learning strategies and in their deep approach to learning, consequently lowering their use of a surface approach. In spite of this, in what concerns to academic achievement, no statistically significant differences have been found.

Students Approach to Learning and Their Use of Lecture Capture

ERIC Educational Resources Information Center

Vajoczki, Susan; Watt, Susan; Marquis, Nick; Liao, Rose; Vine, Michelle

2011-01-01

This study examined lecture capture as a way of enhancing university education, and explored how students with different learning approaches used lecture capturing (i.e., podcasts and vodcasts). Results indicate that both deep and surface learners report increased course satisfaction and better retention of knowledge in courses with traditional…

Does the Use of Case-Based Learning Impact the Retention of Key Concepts in Undergraduate Biochemistry?

ERIC Educational Resources Information Center

Kulak, Verena; Newton, Genevieve; Sharma, Rahul

2017-01-01

Objective: Enhanced knowledge retention and a preference towards a deep learning approach are desirable pedagogical outcomes of case-based learning (CBL). The CBL literature is sparse with respect to these outcomes, and this is especially so in the area of biochemistry. The present study determined the effect of CBL vs. non CBL on knowledge…

Effects of a Metacognitive Intervention on Students' Approaches to Learning and Self-Efficacy in a First Year Medical Course

ERIC Educational Resources Information Center

Papinczak, Tracey; Young, Louise; Groves, Michele; Haynes, Michele

2008-01-01

Aim: To determine the influence of metacognitive activities within the PBL tutorial environment on the development of deep learning approach, reduction in surface approach, and enhancement of individual learning self-efficacy. Method: Participants were first-year medical students (N = 213). A pre-test, post-test design was implemented with…

Deep neural networks to enable real-time multimessenger astrophysics

NASA Astrophysics Data System (ADS)

George, Daniel; Huerta, E. A.

2018-02-01

Gravitational wave astronomy has set in motion a scientific revolution. To further enhance the science reach of this emergent field of research, there is a pressing need to increase the depth and speed of the algorithms used to enable these ground-breaking discoveries. We introduce Deep Filtering—a new scalable machine learning method for end-to-end time-series signal processing. Deep Filtering is based on deep learning with two deep convolutional neural networks, which are designed for classification and regression, to detect gravitational wave signals in highly noisy time-series data streams and also estimate the parameters of their sources in real time. Acknowledging that some of the most sensitive algorithms for the detection of gravitational waves are based on implementations of matched filtering, and that a matched filter is the optimal linear filter in Gaussian noise, the application of Deep Filtering using whitened signals in Gaussian noise is investigated in this foundational article. The results indicate that Deep Filtering outperforms conventional machine learning techniques, achieves similar performance compared to matched filtering, while being several orders of magnitude faster, allowing real-time signal processing with minimal resources. Furthermore, we demonstrate that Deep Filtering can detect and characterize waveform signals emitted from new classes of eccentric or spin-precessing binary black holes, even when trained with data sets of only quasicircular binary black hole waveforms. The results presented in this article, and the recent use of deep neural networks for the identification of optical transients in telescope data, suggests that deep learning can facilitate real-time searches of gravitational wave sources and their electromagnetic and astroparticle counterparts. In the subsequent article, the framework introduced herein is directly applied to identify and characterize gravitational wave events in real LIGO data.

Genome-wide prediction of cis-regulatory regions using supervised deep learning methods.

PubMed

Li, Yifeng; Shi, Wenqiang; Wasserman, Wyeth W

2018-05-31

In the human genome, 98% of DNA sequences are non-protein-coding regions that were previously disregarded as junk DNA. In fact, non-coding regions host a variety of cis-regulatory regions which precisely control the expression of genes. Thus, Identifying active cis-regulatory regions in the human genome is critical for understanding gene regulation and assessing the impact of genetic variation on phenotype. The developments of high-throughput sequencing and machine learning technologies make it possible to predict cis-regulatory regions genome wide. Based on rich data resources such as the Encyclopedia of DNA Elements (ENCODE) and the Functional Annotation of the Mammalian Genome (FANTOM) projects, we introduce DECRES based on supervised deep learning approaches for the identification of enhancer and promoter regions in the human genome. Due to their ability to discover patterns in large and complex data, the introduction of deep learning methods enables a significant advance in our knowledge of the genomic locations of cis-regulatory regions. Using models for well-characterized cell lines, we identify key experimental features that contribute to the predictive performance. Applying DECRES, we delineate locations of 300,000 candidate enhancers genome wide (6.8% of the genome, of which 40,000 are supported by bidirectional transcription data), and 26,000 candidate promoters (0.6% of the genome). The predicted annotations of cis-regulatory regions will provide broad utility for genome interpretation from functional genomics to clinical applications. The DECRES model demonstrates potentials of deep learning technologies when combined with high-throughput sequencing data, and inspires the development of other advanced neural network models for further improvement of genome annotations.

Transforming Information Literacy Conversations to Enhance Student Learning: New Curriculum Dialogues

ERIC Educational Resources Information Center

Salisbury, Fiona A.; Karasmanis, Sharon; Robertson, Tracy; Corbin, Jenny; Hulett, Heather; Peseta, Tai L.

2012-01-01

Information literacy is an essential component of the La Trobe University inquiry/research graduate capability and it provides the skill set needed for students to take their first steps on the path to engaging with academic information and scholarly communication processes. A deep learning approach to information literacy can be achieved if…

Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database.

PubMed

Choi, Joon Yul; Yoo, Tae Keun; Seo, Jeong Gi; Kwak, Jiyong; Um, Terry Taewoong; Rim, Tyler Hyungtaek

2017-01-01

Deep learning emerges as a powerful tool for analyzing medical images. Retinal disease detection by using computer-aided diagnosis from fundus image has emerged as a new method. We applied deep learning convolutional neural network by using MatConvNet for an automated detection of multiple retinal diseases with fundus photographs involved in STructured Analysis of the REtina (STARE) database. Dataset was built by expanding data on 10 categories, including normal retina and nine retinal diseases. The optimal outcomes were acquired by using a random forest transfer learning based on VGG-19 architecture. The classification results depended greatly on the number of categories. As the number of categories increased, the performance of deep learning models was diminished. When all 10 categories were included, we obtained results with an accuracy of 30.5%, relative classifier information (RCI) of 0.052, and Cohen's kappa of 0.224. Considering three integrated normal, background diabetic retinopathy, and dry age-related macular degeneration, the multi-categorical classifier showed accuracy of 72.8%, 0.283 RCI, and 0.577 kappa. In addition, several ensemble classifiers enhanced the multi-categorical classification performance. The transfer learning incorporated with ensemble classifier of clustering and voting approach presented the best performance with accuracy of 36.7%, 0.053 RCI, and 0.225 kappa in the 10 retinal diseases classification problem. First, due to the small size of datasets, the deep learning techniques in this study were ineffective to be applied in clinics where numerous patients suffering from various types of retinal disorders visit for diagnosis and treatment. Second, we found that the transfer learning incorporated with ensemble classifiers can improve the classification performance in order to detect multi-categorical retinal diseases. Further studies should confirm the effectiveness of algorithms with large datasets obtained from hospitals.

An instructional intervention to encourage effective deep collaborative learning in undergraduate veterinary students.

PubMed

Khosa, Deep K; Volet, Simone E; Bolton, John R

2010-01-01

In recent years, veterinary education has received an increased amount of attention directed at the value and application of collaborative case-based learning. The benefit of instilling deep learning practices in undergraduate veterinary students has also emerged as a powerful tool in encouraging continued professional education. However, research into the design and application of instructional strategies to encourage deep, collaborative case-based learning in veterinary undergraduates has been limited. This study focused on delivering an instructional intervention (via a 20-minute presentation and student handout) to foster productive, collaborative case-based learning in veterinary education. The aim was to instigate and encourage deep learning practices in a collaborative case-based assignment and to assess the impact of the intervention on students' group learning. Two cohorts of veterinary students were involved in the study. One cohort was exposed to an instructional intervention, and the other provided the control for the study. The instructional strategy was grounded in the collaborative learning literature and prior empirical studies with veterinary students. Results showed that the intervention cohort spent proportionally more time on understanding case content material than did the control cohort and rated their face-to-face discussions as more useful in achieving their learning outcomes than did their control counterparts. In addition, the perceived difficulty of the assignment evolved differently for the control and intervention students from start to end of the assignment. This study provides encouraging evidence that veterinary students can change and enhance the way they interact in a group setting to effectively engage in collaborative learning practices.

Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

PubMed

Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

2017-03-01

Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

Deep Reading, Cost/Benefit, and the Construction of Meaning: Enhancing Reading Comprehension and Deep Learning in Sociology Courses

ERIC Educational Resources Information Center

Roberts, Judith C.; Roberts, Keith A.

2008-01-01

Reading comprehension skill is often assumed by sociology instructors, yet many college students seem to have marginal reading comprehension skills, which may explain why fewer than half of them are actually doing the reading. Sanctions that force students to either read or to pay a price are based on a rational choice model of behavior--a…

Enhancing the Agency of the Listener: Introducing Reception Theory in a Lecture

ERIC Educational Resources Information Center

Smyth, Karen Elaine

2009-01-01

This article explores a teaching approach that aims to engage learners more fully in the deep learning process that is characterised by the development of critical thinking skills. The concept of critical thinking skills is reconsidered in the context of the need to shift focus away from teaching teachers about learning to teaching students about…

"The Strawberry Caper": Using Scenario-Based Problem Solving to Integrate Middle School Science Topics

ERIC Educational Resources Information Center

Gonda, Rebecca L.; DeHart, Kyle; Ashman, Tia-Lynn; Legg, Alison Slinskey

2015-01-01

Achieving a deep understanding of the many topics covered in middle school biology classes is difficult for many students. One way to help students learn these topics is through scenario-based learning, which enhances students' performance. The scenario-based problem-solving module presented here, "The Strawberry Caper," not only…

Face-name association learning and brain structural substrates in alcoholism.

PubMed

Pitel, Anne-Lise; Chanraud, Sandra; Rohlfing, Torsten; Pfefferbaum, Adolf; Sullivan, Edith V

2012-07-01

Associative learning is required for face-name association and is impaired in alcoholism, but the cognitive processes and brain structural components underlying this deficit remain unclear. It is also unknown whether prompting alcoholics to implement a deep level of processing during face-name encoding would enhance performance. Abstinent alcoholics and controls performed a levels-of-processing face-name learning task. Participants indicated whether the face was that of an honest person (deep encoding) or that of a man (shallow encoding). Retrieval was examined using an associative (face-name) recognition task and a single-item (face or name only) recognition task. Participants also underwent 3T structural MRI. Compared with controls, alcoholics had poorer associative and single-item learning and performed at similar levels. Level of processing at encoding had little effect on recognition performance but affected reaction time (RT). Correlations with brain volumes were generally modest and based primarily on RT in alcoholics, where the deeper the processing at encoding, the more restricted the correlations with brain volumes. In alcoholics, longer control task RTs correlated modestly with smaller tissue volumes across several anterior to posterior brain regions; shallow encoding correlated with calcarine and striatal volumes; deep encoding correlated with precuneus and parietal volumes; and associative recognition RT correlated with cerebellar volumes. In controls, poorer associative recognition with deep encoding correlated significantly with smaller volumes of frontal and striatal structures. Despite prompting, alcoholics did not take advantage of encoding memoranda at a deep level to enhance face-name recognition accuracy. Nonetheless, conditions of deeper encoding resulted in faster RTs and more specific relations with regional brain volumes than did shallow encoding. The normal relation between associative recognition and corticostriatal volumes was not present in alcoholics. Rather, their speeded RTs occurred at the expense of accuracy and were related most robustly to cerebellar volumes. Copyright © 2012 by the Research Society on Alcoholism.

Superficial and deep learning approaches among medical students in an interdisciplinary integrated curriculum.

PubMed

Mirghani, Hisham M; Ezimokhai, Mutairu; Shaban, Sami; van Berkel, Henk J M

2014-01-01

Students' learning approaches have a significant impact on the success of the educational experience, and a mismatch between instructional methods and the learning approach is very likely to create an obstacle to learning. Educational institutes' understanding of students' learning approaches allows those institutes to introduce changes in their curriculum content, instructional format, and assessment methods that will allow students to adopt deep learning techniques and critical thinking. The objective of this study was to determine and compare learning approaches among medical students following an interdisciplinary integrated curriculum. This was a cross-sectional study in which an electronic questionnaire using the Biggs two-factor Study Process Questionnaire (SPQ) with 20 questions was administered. Of a total of 402 students at the medical school, 214 (53.2%) completed the questionnaire. There was a significant difference in the mean score of superficial approach, motive and strategy between students in the six medical school years. However, no significant difference was observed in the mean score of deep approach, motive and strategy. The mean score for years 1 and 2 showed a significantly higher surface approach, surface motive and surface strategy when compared with students in years 4-6 in medical school. The superficial approach to learning was mostly preferred among first and second year medical students, and the least preferred among students in the final clinical years. These results may be useful in creating future teaching, learning and assessment strategies aiming to enhance a deep learning approach among medical students. Future studies are needed to investigate the reason for the preferred superficial approach among medical students in their early years of study.

Wavelet-enhanced convolutional neural network: a new idea in a deep learning paradigm.

PubMed

Savareh, Behrouz Alizadeh; Emami, Hassan; Hajiabadi, Mohamadreza; Azimi, Seyed Majid; Ghafoori, Mahyar

2018-05-29

Manual brain tumor segmentation is a challenging task that requires the use of machine learning techniques. One of the machine learning techniques that has been given much attention is the convolutional neural network (CNN). The performance of the CNN can be enhanced by combining other data analysis tools such as wavelet transform. In this study, one of the famous implementations of CNN, a fully convolutional network (FCN), was used in brain tumor segmentation and its architecture was enhanced by wavelet transform. In this combination, a wavelet transform was used as a complementary and enhancing tool for CNN in brain tumor segmentation. Comparing the performance of basic FCN architecture against the wavelet-enhanced form revealed a remarkable superiority of enhanced architecture in brain tumor segmentation tasks. Using mathematical functions and enhancing tools such as wavelet transform and other mathematical functions can improve the performance of CNN in any image processing task such as segmentation and classification.

Deep Learning in Label-free Cell Classification

PubMed Central

Chen, Claire Lifan; Mahjoubfar, Ata; Tai, Li-Chia; Blaby, Ian K.; Huang, Allen; Niazi, Kayvan Reza; Jalali, Bahram

2016-01-01

Label-free cell analysis is essential to personalized genomics, cancer diagnostics, and drug development as it avoids adverse effects of staining reagents on cellular viability and cell signaling. However, currently available label-free cell assays mostly rely only on a single feature and lack sufficient differentiation. Also, the sample size analyzed by these assays is limited due to their low throughput. Here, we integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms including artificial neural network, support vector machine, logistic regression, and a novel deep learning pipeline, which adopts global optimization of receiver operating characteristics. As a validation of the enhanced sensitivity and specificity of our system, we show classification of white blood T-cells against colon cancer cells, as well as lipid accumulating algal strains for biofuel production. This system opens up a new path to data-driven phenotypic diagnosis and better understanding of the heterogeneous gene expressions in cells. PMID:26975219

Deep Learning in Label-free Cell Classification

NASA Astrophysics Data System (ADS)

Chen, Claire Lifan; Mahjoubfar, Ata; Tai, Li-Chia; Blaby, Ian K.; Huang, Allen; Niazi, Kayvan Reza; Jalali, Bahram

2016-03-01

Label-free cell analysis is essential to personalized genomics, cancer diagnostics, and drug development as it avoids adverse effects of staining reagents on cellular viability and cell signaling. However, currently available label-free cell assays mostly rely only on a single feature and lack sufficient differentiation. Also, the sample size analyzed by these assays is limited due to their low throughput. Here, we integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individual cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms including artificial neural network, support vector machine, logistic regression, and a novel deep learning pipeline, which adopts global optimization of receiver operating characteristics. As a validation of the enhanced sensitivity and specificity of our system, we show classification of white blood T-cells against colon cancer cells, as well as lipid accumulating algal strains for biofuel production. This system opens up a new path to data-driven phenotypic diagnosis and better understanding of the heterogeneous gene expressions in cells.

Uniting Active and Deep Learning to Teach Problem-Solving Skills: Strategic Tools and the Learning Spiral

ERIC Educational Resources Information Center

Diamond, Nina; Koernig, Stephen K.; Iqbal, Zafar

2008-01-01

This article describes an innovative strategic tools course designed to enhance the problem-solving skills of marketing majors. The course serves as a means of preparing students to capitalize on opportunities afforded by a case-based capstone course and to better meet the needs and expectations of prospective employers. The course format utilizes…

Multi-categorical deep learning neural network to classify retinal images: A pilot study employing small database

PubMed Central

Seo, Jeong Gi; Kwak, Jiyong; Um, Terry Taewoong; Rim, Tyler Hyungtaek

2017-01-01

Deep learning emerges as a powerful tool for analyzing medical images. Retinal disease detection by using computer-aided diagnosis from fundus image has emerged as a new method. We applied deep learning convolutional neural network by using MatConvNet for an automated detection of multiple retinal diseases with fundus photographs involved in STructured Analysis of the REtina (STARE) database. Dataset was built by expanding data on 10 categories, including normal retina and nine retinal diseases. The optimal outcomes were acquired by using a random forest transfer learning based on VGG-19 architecture. The classification results depended greatly on the number of categories. As the number of categories increased, the performance of deep learning models was diminished. When all 10 categories were included, we obtained results with an accuracy of 30.5%, relative classifier information (RCI) of 0.052, and Cohen’s kappa of 0.224. Considering three integrated normal, background diabetic retinopathy, and dry age-related macular degeneration, the multi-categorical classifier showed accuracy of 72.8%, 0.283 RCI, and 0.577 kappa. In addition, several ensemble classifiers enhanced the multi-categorical classification performance. The transfer learning incorporated with ensemble classifier of clustering and voting approach presented the best performance with accuracy of 36.7%, 0.053 RCI, and 0.225 kappa in the 10 retinal diseases classification problem. First, due to the small size of datasets, the deep learning techniques in this study were ineffective to be applied in clinics where numerous patients suffering from various types of retinal disorders visit for diagnosis and treatment. Second, we found that the transfer learning incorporated with ensemble classifiers can improve the classification performance in order to detect multi-categorical retinal diseases. Further studies should confirm the effectiveness of algorithms with large datasets obtained from hospitals. PMID:29095872

Making Data Mobile: The Hubble Deep Field Academy iPad app

NASA Astrophysics Data System (ADS)

Eisenhamer, Bonnie; Cordes, K.; Davis, S.; Eisenhamer, J.

2013-01-01

Many school districts are purchasing iPads for educators and students to use as learning tools in the classroom. Educators often prefer these devices to desktop and laptop computers because they offer portability and an intuitive design, while having a larger screen size when compared to smart phones. As a result, we began investigating the potential of adapting online activities for use on Apple’s iPad to enhance the dissemination and usage of these activities in instructional settings while continuing to meet educators’ needs. As a pilot effort, we are developing an iPad app for the “Hubble Deep Field Academy” - an activity that is currently available online and commonly used by middle school educators. The Hubble Deep Field Academy app features the HDF-North image while centering on the theme of how scientists use light to explore and study the universe. It also includes features such as embedded links to vocabulary, images and videos, teacher background materials, and readings about Hubble’s other deep field surveys. It is our goal is to impact students’ engagement in STEM-related activities, while enhancing educators’ usage of NASA data via new and innovative mediums. We also hope to develop and share lessons learned with the E/PO community that can be used to support similar projects. We plan to test the Hubble Deep Field Academy app during the school year to determine if this new activity format is beneficial to the education community.

DeepDeath: Learning to predict the underlying cause of death with Big Data.

PubMed

Hassanzadeh, Hamid Reza; Ying Sha; Wang, May D

2017-07-01

Multiple cause-of-death data provides a valuable source of information that can be used to enhance health standards by predicting health related trajectories in societies with large populations. These data are often available in large quantities across U.S. states and require Big Data techniques to uncover complex hidden patterns. We design two different classes of models suitable for large-scale analysis of mortality data, a Hadoop-based ensemble of random forests trained over N-grams, and the DeepDeath, a deep classifier based on the recurrent neural network (RNN). We apply both classes to the mortality data provided by the National Center for Health Statistics and show that while both perform significantly better than the random classifier, the deep model that utilizes long short-term memory networks (LSTMs), surpasses the N-gram based models and is capable of learning the temporal aspect of the data without a need for building ad-hoc, expert-driven features.

Deep learning for staging liver fibrosis on CT: a pilot study.

PubMed

Yasaka, Koichiro; Akai, Hiroyuki; Kunimatsu, Akira; Abe, Osamu; Kiryu, Shigeru

2018-05-14

To investigate whether liver fibrosis can be staged by deep learning techniques based on CT images. This clinical retrospective study, approved by our institutional review board, included 496 CT examinations of 286 patients who underwent dynamic contrast-enhanced CT for evaluations of the liver and for whom histopathological information regarding liver fibrosis stage was available. The 396 portal phase images with age and sex data of patients (F0/F1/F2/F3/F4 = 113/36/56/66/125) were used for training a deep convolutional neural network (DCNN); the data for the other 100 (F0/F1/F2/F3/F4 = 29/9/14/16/32) were utilised for testing the trained network, with the histopathological fibrosis stage used as reference. To improve robustness, additional images for training data were generated by rotating or parallel shifting the images, or adding Gaussian noise. Supervised training was used to minimise the difference between the liver fibrosis stage and the fibrosis score obtained from deep learning based on CT images (F DLCT score) output by the model. Testing data were input into the trained DCNNs to evaluate their performance. The F DLCT scores showed a significant correlation with liver fibrosis stage (Spearman's correlation coefficient = 0.48, p < 0.001). The areas under the receiver operating characteristic curves (with 95% confidence intervals) for diagnosing significant fibrosis (≥ F2), advanced fibrosis (≥ F3) and cirrhosis (F4) by using F DLCT scores were 0.74 (0.64-0.85), 0.76 (0.66-0.85) and 0.73 (0.62-0.84), respectively. Liver fibrosis can be staged by using a deep learning model based on CT images, with moderate performance. • Liver fibrosis can be staged by a deep learning model based on magnified CT images including the liver surface, with moderate performance. • Scores from a trained deep learning model showed moderate correlation with histopathological liver fibrosis staging. • Further improvement are necessary before utilisation in clinical settings.

Deep Learning in Label-free Cell Classification

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chen, Claire Lifan; Mahjoubfar, Ata; Tai, Li-Chia

Label-free cell analysis is essential to personalized genomics, cancer diagnostics, and drug development as it avoids adverse effects of staining reagents on cellular viability and cell signaling. However, currently available label-free cell assays mostly rely only on a single feature and lack sufficient differentiation. Also, the sample size analyzed by these assays is limited due to their low throughput. Here, we integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individualmore » cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms including artificial neural network, support vector machine, logistic regression, and a novel deep learning pipeline, which adopts global optimization of receiver operating characteristics. As a validation of the enhanced sensitivity and specificity of our system, we show classification of white blood T-cells against colon cancer cells, as well as lipid accumulating algal strains for biofuel production. In conclusion, this system opens up a new path to data-driven phenotypic diagnosis and better understanding of the heterogeneous gene expressions in cells.« less

Deep Learning in Label-free Cell Classification

DOE PAGES

Chen, Claire Lifan; Mahjoubfar, Ata; Tai, Li-Chia; ...

2016-03-15

Label-free cell analysis is essential to personalized genomics, cancer diagnostics, and drug development as it avoids adverse effects of staining reagents on cellular viability and cell signaling. However, currently available label-free cell assays mostly rely only on a single feature and lack sufficient differentiation. Also, the sample size analyzed by these assays is limited due to their low throughput. Here, we integrate feature extraction and deep learning with high-throughput quantitative imaging enabled by photonic time stretch, achieving record high accuracy in label-free cell classification. Our system captures quantitative optical phase and intensity images and extracts multiple biophysical features of individualmore » cells. These biophysical measurements form a hyperdimensional feature space in which supervised learning is performed for cell classification. We compare various learning algorithms including artificial neural network, support vector machine, logistic regression, and a novel deep learning pipeline, which adopts global optimization of receiver operating characteristics. As a validation of the enhanced sensitivity and specificity of our system, we show classification of white blood T-cells against colon cancer cells, as well as lipid accumulating algal strains for biofuel production. In conclusion, this system opens up a new path to data-driven phenotypic diagnosis and better understanding of the heterogeneous gene expressions in cells.« less

Classification of breast MRI lesions using small-size training sets: comparison of deep learning approaches

NASA Astrophysics Data System (ADS)

Amit, Guy; Ben-Ari, Rami; Hadad, Omer; Monovich, Einat; Granot, Noa; Hashoul, Sharbell

2017-03-01

Diagnostic interpretation of breast MRI studies requires meticulous work and a high level of expertise. Computerized algorithms can assist radiologists by automatically characterizing the detected lesions. Deep learning approaches have shown promising results in natural image classification, but their applicability to medical imaging is limited by the shortage of large annotated training sets. In this work, we address automatic classification of breast MRI lesions using two different deep learning approaches. We propose a novel image representation for dynamic contrast enhanced (DCE) breast MRI lesions, which combines the morphological and kinetics information in a single multi-channel image. We compare two classification approaches for discriminating between benign and malignant lesions: training a designated convolutional neural network and using a pre-trained deep network to extract features for a shallow classifier. The domain-specific trained network provided higher classification accuracy, compared to the pre-trained model, with an area under the ROC curve of 0.91 versus 0.81, and an accuracy of 0.83 versus 0.71. Similar accuracy was achieved in classifying benign lesions, malignant lesions, and normal tissue images. The trained network was able to improve accuracy by using the multi-channel image representation, and was more robust to reductions in the size of the training set. A small-size convolutional neural network can learn to accurately classify findings in medical images using only a few hundred images from a few dozen patients. With sufficient data augmentation, such a network can be trained to outperform a pre-trained out-of-domain classifier. Developing domain-specific deep-learning models for medical imaging can facilitate technological advancements in computer-aided diagnosis.

Predicting human protein function with multi-task deep neural networks.

PubMed

Fa, Rui; Cozzetto, Domenico; Wan, Cen; Jones, David T

2018-01-01

Machine learning methods for protein function prediction are urgently needed, especially now that a substantial fraction of known sequences remains unannotated despite the extensive use of functional assignments based on sequence similarity. One major bottleneck supervised learning faces in protein function prediction is the structured, multi-label nature of the problem, because biological roles are represented by lists of terms from hierarchically organised controlled vocabularies such as the Gene Ontology. In this work, we build on recent developments in the area of deep learning and investigate the usefulness of multi-task deep neural networks (MTDNN), which consist of upstream shared layers upon which are stacked in parallel as many independent modules (additional hidden layers with their own output units) as the number of output GO terms (the tasks). MTDNN learns individual tasks partially using shared representations and partially from task-specific characteristics. When no close homologues with experimentally validated functions can be identified, MTDNN gives more accurate predictions than baseline methods based on annotation frequencies in public databases or homology transfers. More importantly, the results show that MTDNN binary classification accuracy is higher than alternative machine learning-based methods that do not exploit commonalities and differences among prediction tasks. Interestingly, compared with a single-task predictor, the performance improvement is not linearly correlated with the number of tasks in MTDNN, but medium size models provide more improvement in our case. One of advantages of MTDNN is that given a set of features, there is no requirement for MTDNN to have a bootstrap feature selection procedure as what traditional machine learning algorithms do. Overall, the results indicate that the proposed MTDNN algorithm improves the performance of protein function prediction. On the other hand, there is still large room for deep learning techniques to further enhance prediction ability.

Deep Learning for real-time gravitational wave detection and parameter estimation: Results with Advanced LIGO data

NASA Astrophysics Data System (ADS)

George, Daniel; Huerta, E. A.

2018-03-01

The recent Nobel-prize-winning detections of gravitational waves from merging black holes and the subsequent detection of the collision of two neutron stars in coincidence with electromagnetic observations have inaugurated a new era of multimessenger astrophysics. To enhance the scope of this emergent field of science, we pioneered the use of deep learning with convolutional neural networks, that take time-series inputs, for rapid detection and characterization of gravitational wave signals. This approach, Deep Filtering, was initially demonstrated using simulated LIGO noise. In this article, we present the extension of Deep Filtering using real data from LIGO, for both detection and parameter estimation of gravitational waves from binary black hole mergers using continuous data streams from multiple LIGO detectors. We demonstrate for the first time that machine learning can detect and estimate the true parameters of real events observed by LIGO. Our results show that Deep Filtering achieves similar sensitivities and lower errors compared to matched-filtering while being far more computationally efficient and more resilient to glitches, allowing real-time processing of weak time-series signals in non-stationary non-Gaussian noise with minimal resources, and also enables the detection of new classes of gravitational wave sources that may go unnoticed with existing detection algorithms. This unified framework for data analysis is ideally suited to enable coincident detection campaigns of gravitational waves and their multimessenger counterparts in real-time.

The Combined Effects of Classroom Teaching and Learning Strategy Use on Students' Chemistry Self-Efficacy

NASA Astrophysics Data System (ADS)

Cheung, Derek

2015-02-01

For students to be successful in school chemistry, a strong sense of self-efficacy is essential. Chemistry self-efficacy can be defined as students' beliefs about the extent to which they are capable of performing specific chemistry tasks. According to Bandura (Psychol. Rev. 84:191-215, 1977), students acquire information about their level of self-efficacy from four sources: performance accomplishments, vicarious experiences, verbal persuasion, and physiological states. No published studies have investigated how instructional strategies in chemistry lessons can provide students with positive experiences with these four sources of self-efficacy information and how the instructional strategies promote students' chemistry self-efficacy. In this study, questionnaire items were constructed to measure student perceptions about instructional strategies, termed efficacy-enhancing teaching, which can provide positive experiences with the four sources of self-efficacy information. Structural equation modeling was then applied to test a hypothesized mediation model, positing that efficacy-enhancing teaching positively affects students' chemistry self-efficacy through their use of deep learning strategies such as metacognitive control strategies. A total of 590 chemistry students at nine secondary schools in Hong Kong participated in the survey. The mediation model provided a good fit to the student data. Efficacy-enhancing teaching had a direct effect on students' chemistry self-efficacy. Efficacy-enhancing teaching also directly affected students' use of deep learning strategies, which in turn affected students' chemistry self-efficacy. The implications of these findings for developing secondary school students' chemistry self-efficacy are discussed.

Face-Name Association Learning and Brain Structural Substrates in Alcoholism

PubMed Central

Pitel, Anne-Lise; Chanraud, Sandra; Rohlfing, Torsten; Pfefferbaum, Adolf; Sullivan, Edith V.

2011-01-01

Background Associative learning is required for face-name association and is impaired in alcoholism, but the cognitive processes and brain structural components underlying this deficit remain unclear. It is also unknown whether prompting alcoholics to implement a deep level of processing during face-name encoding would enhance performance. Methods Abstinent alcoholics and controls performed a levels-of-processing face-name learning task. Participants indicated whether the face was that of an honest person (deep encoding) or that of a man (shallow encoding). Retrieval was examined using an associative (face-name) recognition task and a single-item (face or name only) recognition task. Participants also underwent a 3T structural MRI. Results Compared with controls, alcoholics had poorer associative and single-item recognition, each impaired to the same extent. Level of processing at encoding had little effect on recognition performance but affected reaction time. Correlations with brain volumes were generally modest and based primarily on reaction time in alcoholics, where the deeper the processing at encoding, the more restricted the correlations with brain volumes. In alcoholics, longer control task reaction times correlated modestly with volumes across several anterior to posterior brain regions; shallow encoding correlated with calcarine and striatal volumes; deep encoding correlated with precuneus and parietal volumes; associative recognition RT correlated with cerebellar volumes. In controls, poorer associative recognition with deep encoding correlated significantly with smaller volumes of frontal and striatal structures. Conclusions Despite prompting, alcoholics did not take advantage of encoding memoranda at a deep level to enhance face-name recognition accuracy. Nonetheless, conditions of deeper encoding resulted in faster reaction times and more specific relations with regional brain volumes than did shallow encoding. The normal relation between associative recognition and corticostriatal volumes was not present in alcoholics. Rather, their speeded reaction time occurred at the expense of accuracy and was related most robustly to cerebellar volumes. PMID:22509954

Automated Critical Test Findings Identification and Online Notification System Using Artificial Intelligence in Imaging.

PubMed

Prevedello, Luciano M; Erdal, Barbaros S; Ryu, John L; Little, Kevin J; Demirer, Mutlu; Qian, Songyue; White, Richard D

2017-12-01

Purpose To evaluate the performance of an artificial intelligence (AI) tool using a deep learning algorithm for detecting hemorrhage, mass effect, or hydrocephalus (HMH) at non-contrast material-enhanced head computed tomographic (CT) examinations and to determine algorithm performance for detection of suspected acute infarct (SAI). Materials and Methods This HIPAA-compliant retrospective study was completed after institutional review board approval. A training and validation dataset of noncontrast-enhanced head CT examinations that comprised 100 examinations of HMH, 22 of SAI, and 124 of noncritical findings was obtained resulting in 2583 representative images. Examinations were processed by using a convolutional neural network (deep learning) using two different window and level configurations (brain window and stroke window). AI algorithm performance was tested on a separate dataset containing 50 examinations with HMH findings, 15 with SAI findings, and 35 with noncritical findings. Results Final algorithm performance for HMH showed 90% (45 of 50) sensitivity (95% confidence interval [CI]: 78%, 97%) and 85% (68 of 80) specificity (95% CI: 76%, 92%), with area under the receiver operating characteristic curve (AUC) of 0.91 with the brain window. For SAI, the best performance was achieved with the stroke window showing 62% (13 of 21) sensitivity (95% CI: 38%, 82%) and 96% (27 of 28) specificity (95% CI: 82%, 100%), with AUC of 0.81. Conclusion AI using deep learning demonstrates promise for detecting critical findings at noncontrast-enhanced head CT. A dedicated algorithm was required to detect SAI. Detection of SAI showed lower sensitivity in comparison to detection of HMH, but showed reasonable performance. Findings support further investigation of the algorithm in a controlled and prospective clinical setting to determine whether it can independently screen noncontrast-enhanced head CT examinations and notify the interpreting radiologist of critical findings. © RSNA, 2017 Online supplemental material is available for this article.

Discriminating between benign and malignant breast tumors using 3D convolutional neural network in dynamic contrast enhanced-MR images

NASA Astrophysics Data System (ADS)

Li, Jing; Fan, Ming; Zhang, Juan; Li, Lihua

2017-03-01

Convolutional neural networks (CNNs) are the state-of-the-art deep learning network architectures that can be used in a range of applications, including computer vision and medical image analysis. It exhibits a powerful representation learning mechanism with an automated design to learn features directly from the data. However, the common 2D CNNs only use the two dimension spatial information without evaluating the correlation between the adjoin slices. In this study, we established a method of 3D CNNs to discriminate between malignant and benign breast tumors. To this end, 143 patients were enrolled which include 66 benign and 77 malignant instances. The MRI images were pre-processed for noise reduction and breast tumor region segmentation. Data augmentation by spatial translating, rotating and vertical and horizontal flipping is applied to the cases to reduce possible over-fitting. A region-of-interest (ROI) and a volume-of-interest (VOI) were segmented in 2D and 3D DCE-MRI, respectively. The enhancement ratio for each MR series was calculated for the 2D and 3D images. The results for the enhancement ratio images in the two series are integrated for classification. The results of the area under the ROC curve(AUC) values are 0.739 and 0.801 for 2D and 3D methods, respectively. The results for 3D CNN which combined 5 slices for each enhancement ratio images achieved a high accuracy(Acc), sensitivity(Sens) and specificity(Spec) of 0.781, 0.744 and 0.823, respectively. This study indicates that 3D CNN deep learning methods can be a promising technology for breast tumor classification without manual feature extraction.

Representations in learning new faces: evidence from prosopagnosia.

PubMed

Polster, M R; Rapcsak, S Z

1996-05-01

We report the performance of a prosopagnosic patient on face learning tasks under different encoding instructions (i.e., levels of processing manipulations). R.J. performs at chance when given no encoding instructions or when given "shallow" encoding instruction to focus on facial features. By contrast, he performs relatively well with "deep" encoding instructions to rate faces in terms of personality traits or when provided with semantic and name information during the study phase. We propose that the improvement associated with deep encoding instructions may be related to the establishment of distinct visually derived and identity-specific semantic codes. The benefit associated with deep encoding in R.J., however, was found to be restricted to the specific view of the face presented at study and did not generalize to other views of the same face. These observations suggest that deep encoding instructions may enhance memory for concrete or pictorial representations of faces in patients with prosopagnosia, but that these patients cannot compensate for the inability to construct abstract structural codes that normally allow faces to be recognized from different orientations. We postulate further that R.J.'s poor performance on face learning tasks may be attributable to excessive reliance on a feature-based left hemisphere face processing system that operates primarily on view-specific representations.

Performance comparison of deep learning and segmentation-based radiomic methods in the task of distinguishing benign and malignant breast lesions on DCE-MRI

NASA Astrophysics Data System (ADS)

Antropova, Natasha; Huynh, Benjamin; Giger, Maryellen

2017-03-01

Intuitive segmentation-based CADx/radiomic features, calculated from the lesion segmentations of dynamic contrast-enhanced magnetic resonance images (DCE-MRIs) have been utilized in the task of distinguishing between malignant and benign lesions. Additionally, transfer learning with pre-trained deep convolutional neural networks (CNNs) allows for an alternative method of radiomics extraction, where the features are derived directly from the image data. However, the comparison of computer-extracted segmentation-based and CNN features in MRI breast lesion characterization has not yet been conducted. In our study, we used a DCE-MRI database of 640 breast cases - 191 benign and 449 malignant. Thirty-eight segmentation-based features were extracted automatically using our quantitative radiomics workstation. Also, 2D ROIs were selected around each lesion on the DCE-MRIs and directly input into a pre-trained CNN AlexNet, yielding CNN features. Each method was investigated separately and in combination in terms of performance in the task of distinguishing between benign and malignant lesions. Area under the ROC curve (AUC) served as the figure of merit. Both methods yielded promising classification performance with round-robin cross-validated AUC values of 0.88 (se =0.01) and 0.76 (se=0.02) for segmentationbased and deep learning methods, respectively. Combination of the two methods enhanced the performance in malignancy assessment resulting in an AUC value of 0.91 (se=0.01), a statistically significant improvement over the performance of the CNN method alone.

Compact Deep-Space Optical Communications Transceiver

NASA Technical Reports Server (NTRS)

Roberts, W. Thomas; Charles, Jeffrey R.

2009-01-01

Deep space optical communication transceivers must be very efficient receivers and transmitters of optical communication signals. For deep space missions, communication systems require high performance well beyond the scope of mere power efficiency, demanding maximum performance in relation to the precious and limited mass, volume, and power allocated. This paper describes the opto-mechanical design of a compact, efficient, functional brassboard deep space transceiver that is capable of achieving megabyte-per-second rates at Mars ranges. The special features embodied to enhance the system operability and functionality, and to reduce the mass and volume of the system are detailed. System tests and performance characteristics are described in detail. Finally, lessons learned in the implementation of the brassboard design and suggestions for improvements appropriate for a flight prototype are covered.

Searching for prostate cancer by fully automated magnetic resonance imaging classification: deep learning versus non-deep learning.

PubMed

Wang, Xinggang; Yang, Wei; Weinreb, Jeffrey; Han, Juan; Li, Qiubai; Kong, Xiangchuang; Yan, Yongluan; Ke, Zan; Luo, Bo; Liu, Tao; Wang, Liang

2017-11-13

Prostate cancer (PCa) is a major cause of death since ancient time documented in Egyptian Ptolemaic mummy imaging. PCa detection is critical to personalized medicine and varies considerably under an MRI scan. 172 patients with 2,602 morphologic images (axial 2D T2-weighted imaging) of the prostate were obtained. A deep learning with deep convolutional neural network (DCNN) and a non-deep learning with SIFT image feature and bag-of-word (BoW), a representative method for image recognition and analysis, were used to distinguish pathologically confirmed PCa patients from prostate benign conditions (BCs) patients with prostatitis or prostate benign hyperplasia (BPH). In fully automated detection of PCa patients, deep learning had a statistically higher area under the receiver operating characteristics curve (AUC) than non-deep learning (P = 0.0007 < 0.001). The AUCs were 0.84 (95% CI 0.78-0.89) for deep learning method and 0.70 (95% CI 0.63-0.77) for non-deep learning method, respectively. Our results suggest that deep learning with DCNN is superior to non-deep learning with SIFT image feature and BoW model for fully automated PCa patients differentiation from prostate BCs patients. Our deep learning method is extensible to image modalities such as MR imaging, CT and PET of other organs.

Deep Learning and Its Applications in Biomedicine.

PubMed

Cao, Chensi; Liu, Feng; Tan, Hai; Song, Deshou; Shu, Wenjie; Li, Weizhong; Zhou, Yiming; Bo, Xiaochen; Xie, Zhi

2018-02-01

Advances in biological and medical technologies have been providing us explosive volumes of biological and physiological data, such as medical images, electroencephalography, genomic and protein sequences. Learning from these data facilitates the understanding of human health and disease. Developed from artificial neural networks, deep learning-based algorithms show great promise in extracting features and learning patterns from complex data. The aim of this paper is to provide an overview of deep learning techniques and some of the state-of-the-art applications in the biomedical field. We first introduce the development of artificial neural network and deep learning. We then describe two main components of deep learning, i.e., deep learning architectures and model optimization. Subsequently, some examples are demonstrated for deep learning applications, including medical image classification, genomic sequence analysis, as well as protein structure classification and prediction. Finally, we offer our perspectives for the future directions in the field of deep learning. Copyright © 2018. Production and hosting by Elsevier B.V.

Text feature extraction based on deep learning: a review.

PubMed

Liang, Hong; Sun, Xiao; Sun, Yunlei; Gao, Yuan

2017-01-01

Selection of text feature item is a basic and important matter for text mining and information retrieval. Traditional methods of feature extraction require handcrafted features. To hand-design, an effective feature is a lengthy process, but aiming at new applications, deep learning enables to acquire new effective feature representation from training data. As a new feature extraction method, deep learning has made achievements in text mining. The major difference between deep learning and conventional methods is that deep learning automatically learns features from big data, instead of adopting handcrafted features, which mainly depends on priori knowledge of designers and is highly impossible to take the advantage of big data. Deep learning can automatically learn feature representation from big data, including millions of parameters. This thesis outlines the common methods used in text feature extraction first, and then expands frequently used deep learning methods in text feature extraction and its applications, and forecasts the application of deep learning in feature extraction.

Overview of deep learning in medical imaging.

PubMed

Suzuki, Kenji

2017-09-01

The use of machine learning (ML) has been increasing rapidly in the medical imaging field, including computer-aided diagnosis (CAD), radiomics, and medical image analysis. Recently, an ML area called deep learning emerged in the computer vision field and became very popular in many fields. It started from an event in late 2012, when a deep-learning approach based on a convolutional neural network (CNN) won an overwhelming victory in the best-known worldwide computer vision competition, ImageNet Classification. Since then, researchers in virtually all fields, including medical imaging, have started actively participating in the explosively growing field of deep learning. In this paper, the area of deep learning in medical imaging is overviewed, including (1) what was changed in machine learning before and after the introduction of deep learning, (2) what is the source of the power of deep learning, (3) two major deep-learning models: a massive-training artificial neural network (MTANN) and a convolutional neural network (CNN), (4) similarities and differences between the two models, and (5) their applications to medical imaging. This review shows that ML with feature input (or feature-based ML) was dominant before the introduction of deep learning, and that the major and essential difference between ML before and after deep learning is the learning of image data directly without object segmentation or feature extraction; thus, it is the source of the power of deep learning, although the depth of the model is an important attribute. The class of ML with image input (or image-based ML) including deep learning has a long history, but recently gained popularity due to the use of the new terminology, deep learning. There are two major models in this class of ML in medical imaging, MTANN and CNN, which have similarities as well as several differences. In our experience, MTANNs were substantially more efficient in their development, had a higher performance, and required a lesser number of training cases than did CNNs. "Deep learning", or ML with image input, in medical imaging is an explosively growing, promising field. It is expected that ML with image input will be the mainstream area in the field of medical imaging in the next few decades.

Deep Learning in Nuclear Medicine and Molecular Imaging: Current Perspectives and Future Directions.

PubMed

Choi, Hongyoon

2018-04-01

Recent advances in deep learning have impacted various scientific and industrial fields. Due to the rapid application of deep learning in biomedical data, molecular imaging has also started to adopt this technique. In this regard, it is expected that deep learning will potentially affect the roles of molecular imaging experts as well as clinical decision making. This review firstly offers a basic overview of deep learning particularly for image data analysis to give knowledge to nuclear medicine physicians and researchers. Because of the unique characteristics and distinctive aims of various types of molecular imaging, deep learning applications can be different from other fields. In this context, the review deals with current perspectives of deep learning in molecular imaging particularly in terms of development of biomarkers. Finally, future challenges of deep learning application for molecular imaging and future roles of experts in molecular imaging will be discussed.

Recurrent neural networks for breast lesion classification based on DCE-MRIs

NASA Astrophysics Data System (ADS)

Antropova, Natasha; Huynh, Benjamin; Giger, Maryellen

2018-02-01

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a significant role in breast cancer screening, cancer staging, and monitoring response to therapy. Recently, deep learning methods are being rapidly incorporated in image-based breast cancer diagnosis and prognosis. However, most of the current deep learning methods make clinical decisions based on 2-dimentional (2D) or 3D images and are not well suited for temporal image data. In this study, we develop a deep learning methodology that enables integration of clinically valuable temporal components of DCE-MRIs into deep learning-based lesion classification. Our work is performed on a database of 703 DCE-MRI cases for the task of distinguishing benign and malignant lesions, and uses the area under the ROC curve (AUC) as the performance metric in conducting that task. We train a recurrent neural network, specifically a long short-term memory network (LSTM), on sequences of image features extracted from the dynamic MRI sequences. These features are extracted with VGGNet, a convolutional neural network pre-trained on a large dataset of natural images ImageNet. The features are obtained from various levels of the network, to capture low-, mid-, and high-level information about the lesion. Compared to a classification method that takes as input only images at a single time-point (yielding an AUC = 0.81 (se = 0.04)), our LSTM method improves lesion classification with an AUC of 0.85 (se = 0.03).

Deep feature classification of angiomyolipoma without visible fat and renal cell carcinoma in abdominal contrast-enhanced CT images with texture image patches and hand-crafted feature concatenation.

PubMed

Lee, Hansang; Hong, Helen; Kim, Junmo; Jung, Dae Chul

2018-04-01

To develop an automatic deep feature classification (DFC) method for distinguishing benign angiomyolipoma without visible fat (AMLwvf) from malignant clear cell renal cell carcinoma (ccRCC) from abdominal contrast-enhanced computer tomography (CE CT) images. A dataset including 80 abdominal CT images of 39 AMLwvf and 41 ccRCC patients was used. We proposed a DFC method for differentiating the small renal masses (SRM) into AMLwvf and ccRCC using the combination of hand-crafted and deep features, and machine learning classifiers. First, 71-dimensional hand-crafted features (HCF) of texture and shape were extracted from the SRM contours. Second, 1000-4000-dimensional deep features (DF) were extracted from the ImageNet pretrained deep learning model with the SRM image patches. In DF extraction, we proposed the texture image patches (TIP) to emphasize the texture information inside the mass in DFs and reduce the mass size variability. Finally, the two features were concatenated and the random forest (RF) classifier was trained on these concatenated features to classify the types of SRMs. The proposed method was tested on our dataset using leave-one-out cross-validation and evaluated using accuracy, sensitivity, specificity, positive predictive values (PPV), negative predictive values (NPV), and area under receiver operating characteristics curve (AUC). In experiments, the combinations of four deep learning models, AlexNet, VGGNet, GoogleNet, and ResNet, and four input image patches, including original, masked, mass-size, and texture image patches, were compared and analyzed. In qualitative evaluation, we observed the change in feature distributions between the proposed and comparative methods using tSNE method. In quantitative evaluation, we evaluated and compared the classification results, and observed that (a) the proposed HCF + DF outperformed HCF-only and DF-only, (b) AlexNet showed generally the best performances among the CNN models, and (c) the proposed TIPs not only achieved the competitive performances among the input patches, but also steady performance regardless of CNN models. As a result, the proposed method achieved the accuracy of 76.6 ± 1.4% for the proposed HCF + DF with AlexNet and TIPs, which improved the accuracy by 6.6%p and 8.3%p compared to HCF-only and DF-only, respectively. The proposed shape features and TIPs improved the HCFs and DFs, respectively, and the feature concatenation further enhanced the quality of features for differentiating AMLwvf from ccRCC in abdominal CE CT images. © 2018 American Association of Physicists in Medicine.

The Intelligent Technologies of Electronic Information System

NASA Astrophysics Data System (ADS)

Li, Xianyu

2017-08-01

Based upon the synopsis of system intelligence and information services, this paper puts forward the attributes and the logic structure of information service, sets forth intelligent technology framework of electronic information system, and presents a series of measures, such as optimizing business information flow, advancing data decision capability, improving information fusion precision, strengthening deep learning application and enhancing prognostic and health management, and demonstrates system operation effectiveness. This will benefit the enhancement of system intelligence.

DCL System Using Deep Learning Approaches for Land-Based or Ship-Based Real-Time Recognition and Localization of Marine Mammals

DTIC Science & Technology

2013-09-30

method has been successfully implemented to automatically detect and recognize pulse trains from minke whales ( songs ) and sperm whales (Physeter...workshops, conferences and data challenges 2. Enhancements of the ASR algorithm for frequency-modulated sounds: Right Whale Study 3...Enhancements of the ASR algorithm for pulse trains: Minke Whale Study 4. Mining Big Data Sound Archives using High Performance Computing software and hardware

Basic steps in establishing effective small group teaching sessions in medical schools.

PubMed

Meo, Sultan Ayoub

2013-07-01

Small-group teaching and learning has achieved an admirable position in medical education and has become more popular as a means of encouraging the students in their studies and enhance the process of deep learning. The main characteristics of small group teaching are active involvement of the learners in entire learning cycle and well defined task orientation with achievable specific aims and objectives in a given time period. The essential components in the development of an ideal small group teaching and learning sessions are preliminary considerations at departmental and institutional level including educational strategies, group composition, physical environment, existing resources, diagnosis of the needs, formulation of the objectives and suitable teaching outline. Small group teaching increases the student interest, teamwork ability, retention of knowledge and skills, enhance transfer of concepts to innovative issues, and improve the self-directed learning. It develops self-motivation, investigating the issues, allows the student to test their thinking and higher-order activities. It also facilitates an adult style of learning, acceptance of personal responsibility for own progress. Moreover, it enhances student-faculty and peer-peer interaction, improves communication skills and provides opportunity to share the responsibility and clarify the points of bafflement.

Large-scale Labeled Datasets to Fuel Earth Science Deep Learning Applications

NASA Astrophysics Data System (ADS)

Maskey, M.; Ramachandran, R.; Miller, J.

2017-12-01

Deep learning has revolutionized computer vision and natural language processing with various algorithms scaled using high-performance computing. However, generic large-scale labeled datasets such as the ImageNet are the fuel that drives the impressive accuracy of deep learning results. Large-scale labeled datasets already exist in domains such as medical science, but creating them in the Earth science domain is a challenge. While there are ways to apply deep learning using limited labeled datasets, there is a need in the Earth sciences for creating large-scale labeled datasets for benchmarking and scaling deep learning applications. At the NASA Marshall Space Flight Center, we are using deep learning for a variety of Earth science applications where we have encountered the need for large-scale labeled datasets. We will discuss our approaches for creating such datasets and why these datasets are just as valuable as deep learning algorithms. We will also describe successful usage of these large-scale labeled datasets with our deep learning based applications.

Document Analyses of Student Use of a Blogging-Mapping Tool to Explore Evidence of Deep and Reflective Learning

ERIC Educational Resources Information Center

Xie, Ying

2008-01-01

Theories about reflective thinking and deep-surface learning abound. In order to arrive at the definition for "reflective thinking toward deep learning," this study establishes that reflective thinking toward deep learning refers to a learner's purposeful and conscious activity of manipulating ideas toward meaningful learning and knowledge…

Automatic tissue image segmentation based on image processing and deep learning

NASA Astrophysics Data System (ADS)

Kong, Zhenglun; Luo, Junyi; Xu, Shengpu; Li, Ting

2018-02-01

Image segmentation plays an important role in multimodality imaging, especially in fusion structural images offered by CT, MRI with functional images collected by optical technologies or other novel imaging technologies. Plus, image segmentation also provides detailed structure description for quantitative visualization of treating light distribution in the human body when incorporated with 3D light transport simulation method. Here we used image enhancement, operators, and morphometry methods to extract the accurate contours of different tissues such as skull, cerebrospinal fluid (CSF), grey matter (GM) and white matter (WM) on 5 fMRI head image datasets. Then we utilized convolutional neural network to realize automatic segmentation of images in a deep learning way. We also introduced parallel computing. Such approaches greatly reduced the processing time compared to manual and semi-automatic segmentation and is of great importance in improving speed and accuracy as more and more samples being learned. Our results can be used as a criteria when diagnosing diseases such as cerebral atrophy, which is caused by pathological changes in gray matter or white matter. We demonstrated the great potential of such image processing and deep leaning combined automatic tissue image segmentation in personalized medicine, especially in monitoring, and treatments.

Opinion mining on book review using CNN-L2-SVM algorithm

NASA Astrophysics Data System (ADS)

Rozi, M. F.; Mukhlash, I.; Soetrisno; Kimura, M.

2018-03-01

Review of a product can represent quality of a product itself. An extraction to that review can be used to know sentiment of that opinion. Process to extract useful information of user review is called Opinion Mining. Review extraction model that is enhancing nowadays is Deep Learning model. This Model has been used by many researchers to obtain excellent performance on Natural Language Processing. In this research, one of deep learning model, Convolutional Neural Network (CNN) is used for feature extraction and L2 Support Vector Machine (SVM) as classifier. These methods are implemented to know the sentiment of book review data. The result of this method shows state-of-the art performance in 83.23% for training phase and 64.6% for testing phase.

Adaptive Correlation Model for Visual Tracking Using Keypoints Matching and Deep Convolutional Feature.

PubMed

Li, Yuankun; Xu, Tingfa; Deng, Honggao; Shi, Guokai; Guo, Jie

2018-02-23

Although correlation filter (CF)-based visual tracking algorithms have achieved appealing results, there are still some problems to be solved. When the target object goes through long-term occlusions or scale variation, the correlation model used in existing CF-based algorithms will inevitably learn some non-target information or partial-target information. In order to avoid model contamination and enhance the adaptability of model updating, we introduce the keypoints matching strategy and adjust the model learning rate dynamically according to the matching score. Moreover, the proposed approach extracts convolutional features from a deep convolutional neural network (DCNN) to accurately estimate the position and scale of the target. Experimental results demonstrate that the proposed tracker has achieved satisfactory performance in a wide range of challenging tracking scenarios.

Systematic assessment of cervical cancer initiation and progression uncovers genetic panels for deep learning-based early diagnosis and proposes novel diagnostic and prognostic biomarkers.

PubMed

Long, Nguyen Phuoc; Jung, Kyung Hee; Yoon, Sang Jun; Anh, Nguyen Hoang; Nghi, Tran Diem; Kang, Yun Pyo; Yan, Hong Hua; Min, Jung Eun; Hong, Soon-Sun; Kwon, Sung Won

2017-12-12

Although many outstanding achievements in the management of cervical cancer (CxCa) have obtained, it still imposes a major burden which has prompted scientists to discover and validate new CxCa biomarkers to improve the diagnostic and prognostic assessment of CxCa. In this study, eight different gene expression data sets containing 202 cancer, 115 cervical intraepithelial neoplasia (CIN), and 105 normal samples were utilized for an integrative systems biology assessment in a multi-stage carcinogenesis manner. Deep learning-based diagnostic models were established based on the genetic panels of intrinsic genes of cervical carcinogenesis as well as on the unbiased variable selection approach. Survival analysis was also conducted to explore the potential biomarker candidates for prognostic assessment. Our results showed that cell cycle, RNA transport, mRNA surveillance, and one carbon pool by folate were the key regulatory mechanisms involved in the initiation, progression, and metastasis of CxCa. Various genetic panels combined with machine learning algorithms successfully differentiated CxCa from CIN and normalcy in cross-study normalized data sets. In particular, the 168-gene deep learning model for the differentiation of cancer from normalcy achieved an externally validated accuracy of 97.96% (99.01% sensitivity and 95.65% specificity). Survival analysis revealed that ZNF281 and EPHB6 were the two most promising prognostic genetic markers for CxCa among others. Our findings open new opportunities to enhance current understanding of the characteristics of CxCa pathobiology. In addition, the combination of transcriptomics-based signatures and deep learning classification may become an important approach to improve CxCa diagnosis and management in clinical practice.

Systematic assessment of cervical cancer initiation and progression uncovers genetic panels for deep learning-based early diagnosis and proposes novel diagnostic and prognostic biomarkers

PubMed Central

Long, Nguyen Phuoc; Jung, Kyung Hee; Yoon, Sang Jun; Anh, Nguyen Hoang; Nghi, Tran Diem; Kang, Yun Pyo; Yan, Hong Hua; Min, Jung Eun; Hong, Soon-Sun; Kwon, Sung Won

2017-01-01

Although many outstanding achievements in the management of cervical cancer (CxCa) have obtained, it still imposes a major burden which has prompted scientists to discover and validate new CxCa biomarkers to improve the diagnostic and prognostic assessment of CxCa. In this study, eight different gene expression data sets containing 202 cancer, 115 cervical intraepithelial neoplasia (CIN), and 105 normal samples were utilized for an integrative systems biology assessment in a multi-stage carcinogenesis manner. Deep learning-based diagnostic models were established based on the genetic panels of intrinsic genes of cervical carcinogenesis as well as on the unbiased variable selection approach. Survival analysis was also conducted to explore the potential biomarker candidates for prognostic assessment. Our results showed that cell cycle, RNA transport, mRNA surveillance, and one carbon pool by folate were the key regulatory mechanisms involved in the initiation, progression, and metastasis of CxCa. Various genetic panels combined with machine learning algorithms successfully differentiated CxCa from CIN and normalcy in cross-study normalized data sets. In particular, the 168-gene deep learning model for the differentiation of cancer from normalcy achieved an externally validated accuracy of 97.96% (99.01% sensitivity and 95.65% specificity). Survival analysis revealed that ZNF281 and EPHB6 were the two most promising prognostic genetic markers for CxCa among others. Our findings open new opportunities to enhance current understanding of the characteristics of CxCa pathobiology. In addition, the combination of transcriptomics-based signatures and deep learning classification may become an important approach to improve CxCa diagnosis and management in clinical practice. PMID:29312619

Deep imitation learning for 3D navigation tasks.

PubMed

Hussein, Ahmed; Elyan, Eyad; Gaber, Mohamed Medhat; Jayne, Chrisina

2018-01-01

Deep learning techniques have shown success in learning from raw high-dimensional data in various applications. While deep reinforcement learning is recently gaining popularity as a method to train intelligent agents, utilizing deep learning in imitation learning has been scarcely explored. Imitation learning can be an efficient method to teach intelligent agents by providing a set of demonstrations to learn from. However, generalizing to situations that are not represented in the demonstrations can be challenging, especially in 3D environments. In this paper, we propose a deep imitation learning method to learn navigation tasks from demonstrations in a 3D environment. The supervised policy is refined using active learning in order to generalize to unseen situations. This approach is compared to two popular deep reinforcement learning techniques: deep-Q-networks and Asynchronous actor-critic (A3C). The proposed method as well as the reinforcement learning methods employ deep convolutional neural networks and learn directly from raw visual input. Methods for combining learning from demonstrations and experience are also investigated. This combination aims to join the generalization ability of learning by experience with the efficiency of learning by imitation. The proposed methods are evaluated on 4 navigation tasks in a 3D simulated environment. Navigation tasks are a typical problem that is relevant to many real applications. They pose the challenge of requiring demonstrations of long trajectories to reach the target and only providing delayed rewards (usually terminal) to the agent. The experiments show that the proposed method can successfully learn navigation tasks from raw visual input while learning from experience methods fail to learn an effective policy. Moreover, it is shown that active learning can significantly improve the performance of the initially learned policy using a small number of active samples.

Hyperspectral Image Enhancement and Mixture Deep-Learning Classification of Corneal Epithelium Injuries.

PubMed

Noor, Siti Salwa Md; Michael, Kaleena; Marshall, Stephen; Ren, Jinchang

2017-11-16

In our preliminary study, the reflectance signatures obtained from hyperspectral imaging (HSI) of normal and abnormal corneal epithelium tissues of porcine show similar morphology with subtle differences. Here we present image enhancement algorithms that can be used to improve the interpretability of data into clinically relevant information to facilitate diagnostics. A total of 25 corneal epithelium images without the application of eye staining were used. Three image feature extraction approaches were applied for image classification: (i) image feature classification from histogram using a support vector machine with a Gaussian radial basis function (SVM-GRBF); (ii) physical image feature classification using deep-learning Convolutional Neural Networks (CNNs) only; and (iii) the combined classification of CNNs and SVM-Linear. The performance results indicate that our chosen image features from the histogram and length-scale parameter were able to classify with up to 100% accuracy; particularly, at CNNs and CNNs-SVM, by employing 80% of the data sample for training and 20% for testing. Thus, in the assessment of corneal epithelium injuries, HSI has high potential as a method that could surpass current technologies regarding speed, objectivity, and reliability.

Deep learning with convolutional neural network in radiology.

PubMed

Yasaka, Koichiro; Akai, Hiroyuki; Kunimatsu, Akira; Kiryu, Shigeru; Abe, Osamu

2018-04-01

Deep learning with a convolutional neural network (CNN) is gaining attention recently for its high performance in image recognition. Images themselves can be utilized in a learning process with this technique, and feature extraction in advance of the learning process is not required. Important features can be automatically learned. Thanks to the development of hardware and software in addition to techniques regarding deep learning, application of this technique to radiological images for predicting clinically useful information, such as the detection and the evaluation of lesions, etc., are beginning to be investigated. This article illustrates basic technical knowledge regarding deep learning with CNNs along the actual course (collecting data, implementing CNNs, and training and testing phases). Pitfalls regarding this technique and how to manage them are also illustrated. We also described some advanced topics of deep learning, results of recent clinical studies, and the future directions of clinical application of deep learning techniques.

Recent machine learning advancements in sensor-based mobility analysis: Deep learning for Parkinson's disease assessment.

PubMed

Eskofier, Bjoern M; Lee, Sunghoon I; Daneault, Jean-Francois; Golabchi, Fatemeh N; Ferreira-Carvalho, Gabriela; Vergara-Diaz, Gloria; Sapienza, Stefano; Costante, Gianluca; Klucken, Jochen; Kautz, Thomas; Bonato, Paolo

2016-08-01

The development of wearable sensors has opened the door for long-term assessment of movement disorders. However, there is still a need for developing methods suitable to monitor motor symptoms in and outside the clinic. The purpose of this paper was to investigate deep learning as a method for this monitoring. Deep learning recently broke records in speech and image classification, but it has not been fully investigated as a potential approach to analyze wearable sensor data. We collected data from ten patients with idiopathic Parkinson's disease using inertial measurement units. Several motor tasks were expert-labeled and used for classification. We specifically focused on the detection of bradykinesia. For this, we compared standard machine learning pipelines with deep learning based on convolutional neural networks. Our results showed that deep learning outperformed other state-of-the-art machine learning algorithms by at least 4.6 % in terms of classification rate. We contribute a discussion of the advantages and disadvantages of deep learning for sensor-based movement assessment and conclude that deep learning is a promising method for this field.

Toolkits and Libraries for Deep Learning.

PubMed

Erickson, Bradley J; Korfiatis, Panagiotis; Akkus, Zeynettin; Kline, Timothy; Philbrick, Kenneth

2017-08-01

Deep learning is an important new area of machine learning which encompasses a wide range of neural network architectures designed to complete various tasks. In the medical imaging domain, example tasks include organ segmentation, lesion detection, and tumor classification. The most popular network architecture for deep learning for images is the convolutional neural network (CNN). Whereas traditional machine learning requires determination and calculation of features from which the algorithm learns, deep learning approaches learn the important features as well as the proper weighting of those features to make predictions for new data. In this paper, we will describe some of the libraries and tools that are available to aid in the construction and efficient execution of deep learning as applied to medical images.

Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions.

PubMed

Akkus, Zeynettin; Galimzianova, Alfiia; Hoogi, Assaf; Rubin, Daniel L; Erickson, Bradley J

2017-08-01

Quantitative analysis of brain MRI is routine for many neurological diseases and conditions and relies on accurate segmentation of structures of interest. Deep learning-based segmentation approaches for brain MRI are gaining interest due to their self-learning and generalization ability over large amounts of data. As the deep learning architectures are becoming more mature, they gradually outperform previous state-of-the-art classical machine learning algorithms. This review aims to provide an overview of current deep learning-based segmentation approaches for quantitative brain MRI. First we review the current deep learning architectures used for segmentation of anatomical brain structures and brain lesions. Next, the performance, speed, and properties of deep learning approaches are summarized and discussed. Finally, we provide a critical assessment of the current state and identify likely future developments and trends.

Learning Sparse Feature Representations using Probabilistic Quadtrees and Deep Belief Nets

DTIC Science & Technology

2015-04-24

Feature Representations usingProbabilistic Quadtrees and Deep Belief Nets Learning sparse feature representations is a useful instru- ment for solving an...novel framework for the classifi cation of handwritten digits that learns sparse representations using probabilistic quadtrees and Deep Belief Nets... Learning Sparse Feature Representations usingProbabilistic Quadtrees and Deep Belief Nets Report Title Learning sparse feature representations is a useful

HD-MTL: Hierarchical Deep Multi-Task Learning for Large-Scale Visual Recognition.

PubMed

Fan, Jianping; Zhao, Tianyi; Kuang, Zhenzhong; Zheng, Yu; Zhang, Ji; Yu, Jun; Peng, Jinye

2017-02-09

In this paper, a hierarchical deep multi-task learning (HD-MTL) algorithm is developed to support large-scale visual recognition (e.g., recognizing thousands or even tens of thousands of atomic object classes automatically). First, multiple sets of multi-level deep features are extracted from different layers of deep convolutional neural networks (deep CNNs), and they are used to achieve more effective accomplishment of the coarseto- fine tasks for hierarchical visual recognition. A visual tree is then learned by assigning the visually-similar atomic object classes with similar learning complexities into the same group, which can provide a good environment for determining the interrelated learning tasks automatically. By leveraging the inter-task relatedness (inter-class similarities) to learn more discriminative group-specific deep representations, our deep multi-task learning algorithm can train more discriminative node classifiers for distinguishing the visually-similar atomic object classes effectively. Our hierarchical deep multi-task learning (HD-MTL) algorithm can integrate two discriminative regularization terms to control the inter-level error propagation effectively, and it can provide an end-to-end approach for jointly learning more representative deep CNNs (for image representation) and more discriminative tree classifier (for large-scale visual recognition) and updating them simultaneously. Our incremental deep learning algorithms can effectively adapt both the deep CNNs and the tree classifier to the new training images and the new object classes. Our experimental results have demonstrated that our HD-MTL algorithm can achieve very competitive results on improving the accuracy rates for large-scale visual recognition.

ShapeShop: Towards Understanding Deep Learning Representations via Interactive Experimentation.

PubMed

Hohman, Fred; Hodas, Nathan; Chau, Duen Horng

2017-05-01

Deep learning is the driving force behind many recent technologies; however, deep neural networks are often viewed as "black-boxes" due to their internal complexity that is hard to understand. Little research focuses on helping people explore and understand the relationship between a user's data and the learned representations in deep learning models. We present our ongoing work, ShapeShop, an interactive system for visualizing and understanding what semantics a neural network model has learned. Built using standard web technologies, ShapeShop allows users to experiment with and compare deep learning models to help explore the robustness of image classifiers.

Motivation, learning strategies, participation and medical school performance.

PubMed

Stegers-Jager, Karen M; Cohen-Schotanus, Janke; Themmen, Axel P N

2012-07-01

Medical schools wish to better understand why some students excel academically and others have difficulty in passing medical courses. Components of self-regulated learning (SRL), such as motivational beliefs and learning strategies, as well as participation in scheduled learning activities, have been found to relate to student performance. Although participation may be a form of SRL, little is known about the relationships among motivational beliefs, learning strategies, participation and medical school performance. This study aimed to test and cross-validate a hypothesised model of relationships among motivational beliefs (value and self-efficacy), learning strategies (deep learning and resource management), participation (lecture attendance, skills training attendance and completion of optional study assignments) and Year 1 performance at medical school. Year 1 medical students in the cohorts of 2008 (n = 303) and 2009 (n = 369) completed a questionnaire on motivational beliefs and learning strategies (sourced from the Motivated Strategies for Learning Questionnaire) and participation. Year 1 performance was operationalised as students' average Year 1 course examination grades. Structural equation modelling was used to analyse the data. Participation and self-efficacy beliefs were positively associated with Year 1 performance (β = 0.78 and β = 0.19, respectively). Deep learning strategies were negatively associated with Year 1 performance (β =- 0.31), but positively related to resource management strategies (β = 0.77), which, in turn, were positively related to participation (β = 0.79). Value beliefs were positively related to deep learning strategies only (β = 0.71). The overall structural model for the 2008 cohort accounted for 47% of the variance in Year 1 grade point average and was cross-validated in the 2009 cohort. This study suggests that participation mediates the relationships between motivation and learning strategies, and medical school performance. However, participation and self-efficacy beliefs also made unique contributions towards performance. Encouraging participation and strengthening self-efficacy may help to enhance medical student performance. © Blackwell Publishing Ltd 2012.

Deep Learning with Convolutional Neural Network for Differentiation of Liver Masses at Dynamic Contrast-enhanced CT: A Preliminary Study.

PubMed

Yasaka, Koichiro; Akai, Hiroyuki; Abe, Osamu; Kiryu, Shigeru

2018-03-01

Purpose To investigate diagnostic performance by using a deep learning method with a convolutional neural network (CNN) for the differentiation of liver masses at dynamic contrast agent-enhanced computed tomography (CT). Materials and Methods This clinical retrospective study used CT image sets of liver masses over three phases (noncontrast-agent enhanced, arterial, and delayed). Masses were diagnosed according to five categories (category A, classic hepatocellular carcinomas [HCCs]; category B, malignant liver tumors other than classic and early HCCs; category C, indeterminate masses or mass-like lesions [including early HCCs and dysplastic nodules] and rare benign liver masses other than hemangiomas and cysts; category D, hemangiomas; and category E, cysts). Supervised training was performed by using 55 536 image sets obtained in 2013 (from 460 patients, 1068 sets were obtained and they were augmented by a factor of 52 [rotated, parallel-shifted, strongly enlarged, and noise-added images were generated from the original images]). The CNN was composed of six convolutional, three maximum pooling, and three fully connected layers. The CNN was tested with 100 liver mass image sets obtained in 2016 (74 men and 26 women; mean age, 66.4 years ± 10.6 [standard deviation]; mean mass size, 26.9 mm ± 25.9; 21, nine, 35, 20, and 15 liver masses for categories A, B, C, D, and E, respectively). Training and testing were performed five times. Accuracy for categorizing liver masses with CNN model and the area under receiver operating characteristic curve for differentiating categories A-B versus categories C-E were calculated. Results Median accuracy of differential diagnosis of liver masses for test data were 0.84. Median area under the receiver operating characteristic curve for differentiating categories A-B from C-E was 0.92. Conclusion Deep learning with CNN showed high diagnostic performance in differentiation of liver masses at dynamic CT. © RSNA, 2017 Online supplemental material is available for this article.

An adaptive deep Q-learning strategy for handwritten digit recognition.

PubMed

Qiao, Junfei; Wang, Gongming; Li, Wenjing; Chen, Min

2018-02-22

Handwritten digits recognition is a challenging problem in recent years. Although many deep learning-based classification algorithms are studied for handwritten digits recognition, the recognition accuracy and running time still need to be further improved. In this paper, an adaptive deep Q-learning strategy is proposed to improve accuracy and shorten running time for handwritten digit recognition. The adaptive deep Q-learning strategy combines the feature-extracting capability of deep learning and the decision-making of reinforcement learning to form an adaptive Q-learning deep belief network (Q-ADBN). First, Q-ADBN extracts the features of original images using an adaptive deep auto-encoder (ADAE), and the extracted features are considered as the current states of Q-learning algorithm. Second, Q-ADBN receives Q-function (reward signal) during recognition of the current states, and the final handwritten digits recognition is implemented by maximizing the Q-function using Q-learning algorithm. Finally, experimental results from the well-known MNIST dataset show that the proposed Q-ADBN has a superiority to other similar methods in terms of accuracy and running time. Copyright © 2018 Elsevier Ltd. All rights reserved.

An Efficient Implementation of Deep Convolutional Neural Networks for MRI Segmentation.

PubMed

Hoseini, Farnaz; Shahbahrami, Asadollah; Bayat, Peyman

2018-02-27

Image segmentation is one of the most common steps in digital image processing, classifying a digital image into different segments. The main goal of this paper is to segment brain tumors in magnetic resonance images (MRI) using deep learning. Tumors having different shapes, sizes, brightness and textures can appear anywhere in the brain. These complexities are the reasons to choose a high-capacity Deep Convolutional Neural Network (DCNN) containing more than one layer. The proposed DCNN contains two parts: architecture and learning algorithms. The architecture and the learning algorithms are used to design a network model and to optimize parameters for the network training phase, respectively. The architecture contains five convolutional layers, all using 3 × 3 kernels, and one fully connected layer. Due to the advantage of using small kernels with fold, it allows making the effect of larger kernels with smaller number of parameters and fewer computations. Using the Dice Similarity Coefficient metric, we report accuracy results on the BRATS 2016, brain tumor segmentation challenge dataset, for the complete, core, and enhancing regions as 0.90, 0.85, and 0.84 respectively. The learning algorithm includes the task-level parallelism. All the pixels of an MR image are classified using a patch-based approach for segmentation. We attain a good performance and the experimental results show that the proposed DCNN increases the segmentation accuracy compared to previous techniques.

ShapeShop: Towards Understanding Deep Learning Representations via Interactive Experimentation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hohman, Frederick M.; Hodas, Nathan O.; Chau, Duen Horng

Deep learning is the driving force behind many recent technologies; however, deep neural networks are often viewed as “black-boxes” due to their internal complexity that is hard to understand. Little research focuses on helping people explore and understand the relationship between a user’s data and the learned representations in deep learning models. We present our ongoing work, ShapeShop, an interactive system for visualizing and understanding what semantics a neural network model has learned. Built using standard web technologies, ShapeShop allows users to experiment with and compare deep learning models to help explore the robustness of image classifiers.

An Energy-Efficient and Scalable Deep Learning/Inference Processor With Tetra-Parallel MIMD Architecture for Big Data Applications.

PubMed

Park, Seong-Wook; Park, Junyoung; Bong, Kyeongryeol; Shin, Dongjoo; Lee, Jinmook; Choi, Sungpill; Yoo, Hoi-Jun

2015-12-01

Deep Learning algorithm is widely used for various pattern recognition applications such as text recognition, object recognition and action recognition because of its best-in-class recognition accuracy compared to hand-crafted algorithm and shallow learning based algorithms. Long learning time caused by its complex structure, however, limits its usage only in high-cost servers or many-core GPU platforms so far. On the other hand, the demand on customized pattern recognition within personal devices will grow gradually as more deep learning applications will be developed. This paper presents a SoC implementation to enable deep learning applications to run with low cost platforms such as mobile or portable devices. Different from conventional works which have adopted massively-parallel architecture, this work adopts task-flexible architecture and exploits multiple parallelism to cover complex functions of convolutional deep belief network which is one of popular deep learning/inference algorithms. In this paper, we implement the most energy-efficient deep learning and inference processor for wearable system. The implemented 2.5 mm × 4.0 mm deep learning/inference processor is fabricated using 65 nm 8-metal CMOS technology for a battery-powered platform with real-time deep inference and deep learning operation. It consumes 185 mW average power, and 213.1 mW peak power at 200 MHz operating frequency and 1.2 V supply voltage. It achieves 411.3 GOPS peak performance and 1.93 TOPS/W energy efficiency, which is 2.07× higher than the state-of-the-art.

Model United Nations and Deep Learning: Theoretical and Professional Learning

ERIC Educational Resources Information Center

Engel, Susan; Pallas, Josh; Lambert, Sarah

2017-01-01

This article demonstrates that the purposeful subject design, incorporating a Model United Nations (MUN), facilitated deep learning and professional skills attainment in the field of International Relations. Deep learning was promoted in subject design by linking learning objectives to Anderson and Krathwohl's (2001) four levels of knowledge or…

Deep learning in bioinformatics.

PubMed

Min, Seonwoo; Lee, Byunghan; Yoon, Sungroh

2017-09-01

In the era of big data, transformation of biomedical big data into valuable knowledge has been one of the most important challenges in bioinformatics. Deep learning has advanced rapidly since the early 2000s and now demonstrates state-of-the-art performance in various fields. Accordingly, application of deep learning in bioinformatics to gain insight from data has been emphasized in both academia and industry. Here, we review deep learning in bioinformatics, presenting examples of current research. To provide a useful and comprehensive perspective, we categorize research both by the bioinformatics domain (i.e. omics, biomedical imaging, biomedical signal processing) and deep learning architecture (i.e. deep neural networks, convolutional neural networks, recurrent neural networks, emergent architectures) and present brief descriptions of each study. Additionally, we discuss theoretical and practical issues of deep learning in bioinformatics and suggest future research directions. We believe that this review will provide valuable insights and serve as a starting point for researchers to apply deep learning approaches in their bioinformatics studies. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

When pretesting fails to enhance learning concepts from reading texts.

PubMed

Hausman, Hannah; Rhodes, Matthew G

2018-05-03

Prior research suggests that people can learn more from reading a text when they attempt to answer pretest questions first. Specifically, pretests on factual information explicitly stated in a text increases the likelihood that participants can answer identical questions after reading than if they had not answered pretest questions. Yet, a central goal of education is to develop deep conceptual understanding. The present experiments investigated whether conceptual pretests facilitate learning concepts from reading texts. In Experiment 1, participants were given factual or conceptual pretest questions; a control group was not given a pretest. Participants then read a passage and took a final test consisting of both factual and conceptual questions. Some of the final test questions were repeated from the pretest and some were new. Although factual pretesting improved learning for identical factual questions, conceptual pretesting did not enhance conceptual learning. Conceptual pretest errors were significantly more likely to be repeated on the final test than factual pretest errors. Providing correct answers (Experiment 2) or correct/incorrect feedback (Experiment 3) following pretest questions enhanced performance on repeated conceptual test items, although these benefits likely reflect memorization and not conceptual understanding. Thus, pretesting appears to provide little benefit for learning conceptual information. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

Some aspects of using new techniques of teaching/learning in education in optics (Abstract only)

NASA Astrophysics Data System (ADS)

Suchanska, Malgorzata

2003-11-01

The deep learning in Optics can be encouraged by stimulating and considerate teaching. It means that teacher should demonstrate his/her personal commitment to the subject and stress its meaning, relevance and importance to the students. It is also important to allow students to be creative in solving problems and in interpretation of its contents. In order to help the students to become more creative persons it is necessary to enhance the learning process of modern knowledge in Optics, to design and conduct experiments, stimulate passions and interests, allow an access to the e-learning system (Internet) and introduce the psychological training (creativity, communication, lateral thinking etc.) (Abstract only available)

Autonomous development and learning in artificial intelligence and robotics: Scaling up deep learning to human-like learning.

PubMed

Oudeyer, Pierre-Yves

2017-01-01

Autonomous lifelong development and learning are fundamental capabilities of humans, differentiating them from current deep learning systems. However, other branches of artificial intelligence have designed crucial ingredients towards autonomous learning: curiosity and intrinsic motivation, social learning and natural interaction with peers, and embodiment. These mechanisms guide exploration and autonomous choice of goals, and integrating them with deep learning opens stimulating perspectives.

Stable architectures for deep neural networks

NASA Astrophysics Data System (ADS)

Haber, Eldad; Ruthotto, Lars

2018-01-01

Deep neural networks have become invaluable tools for supervised machine learning, e.g. classification of text or images. While often offering superior results over traditional techniques and successfully expressing complicated patterns in data, deep architectures are known to be challenging to design and train such that they generalize well to new data. Critical issues with deep architectures are numerical instabilities in derivative-based learning algorithms commonly called exploding or vanishing gradients. In this paper, we propose new forward propagation techniques inspired by systems of ordinary differential equations (ODE) that overcome this challenge and lead to well-posed learning problems for arbitrarily deep networks. The backbone of our approach is our interpretation of deep learning as a parameter estimation problem of nonlinear dynamical systems. Given this formulation, we analyze stability and well-posedness of deep learning and use this new understanding to develop new network architectures. We relate the exploding and vanishing gradient phenomenon to the stability of the discrete ODE and present several strategies for stabilizing deep learning for very deep networks. While our new architectures restrict the solution space, several numerical experiments show their competitiveness with state-of-the-art networks.

Deep learning methods for protein torsion angle prediction.

PubMed

Li, Haiou; Hou, Jie; Adhikari, Badri; Lyu, Qiang; Cheng, Jianlin

2017-09-18

Deep learning is one of the most powerful machine learning methods that has achieved the state-of-the-art performance in many domains. Since deep learning was introduced to the field of bioinformatics in 2012, it has achieved success in a number of areas such as protein residue-residue contact prediction, secondary structure prediction, and fold recognition. In this work, we developed deep learning methods to improve the prediction of torsion (dihedral) angles of proteins. We design four different deep learning architectures to predict protein torsion angles. The architectures including deep neural network (DNN) and deep restricted Boltzmann machine (DRBN), deep recurrent neural network (DRNN) and deep recurrent restricted Boltzmann machine (DReRBM) since the protein torsion angle prediction is a sequence related problem. In addition to existing protein features, two new features (predicted residue contact number and the error distribution of torsion angles extracted from sequence fragments) are used as input to each of the four deep learning architectures to predict phi and psi angles of protein backbone. The mean absolute error (MAE) of phi and psi angles predicted by DRNN, DReRBM, DRBM and DNN is about 20-21° and 29-30° on an independent dataset. The MAE of phi angle is comparable to the existing methods, but the MAE of psi angle is 29°, 2° lower than the existing methods. On the latest CASP12 targets, our methods also achieved the performance better than or comparable to a state-of-the art method. Our experiment demonstrates that deep learning is a valuable method for predicting protein torsion angles. The deep recurrent network architecture performs slightly better than deep feed-forward architecture, and the predicted residue contact number and the error distribution of torsion angles extracted from sequence fragments are useful features for improving prediction accuracy.

The Role of Mental Imagery in Imaginative and Ecological Teaching

ERIC Educational Resources Information Center

Judson, Gillian

2014-01-01

This article explores how mental imagery evoked from words might enhance the learning of cross-curricular content and how it may help cultivate students' "ecological understanding": that deep sense of connection to a living world and the care and concern to live differently within it. With reference to Elliott Eisner's and Kieran Egan's…

Using "Big Ideas" to Enhance Teaching and Student Learning

ERIC Educational Resources Information Center

Mitchell, Ian; Keast, Stephen; Panizzon, Debra; Mitchell, Judie

2017-01-01

Organising teaching of a topic around a small number of "big ideas" has been argued by many to be important in teaching for deep understanding, with big ideas being able to link different activities and to be framed in ways that provide perceived relevance and routes into engagement. However it is our view that, at present, the…

Towards deep learning with segregated dendrites

PubMed Central

Guerguiev, Jordan; Lillicrap, Timothy P

2017-01-01

Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the neocortex optimizes cost functions. Like neocortical pyramidal neurons, neurons in our model receive sensory information and higher-order feedback in electrotonically segregated compartments. Thanks to this segregation, neurons in different layers of the network can coordinate synaptic weight updates. As a result, the network learns to categorize images better than a single layer network. Furthermore, we show that our algorithm takes advantage of multilayer architectures to identify useful higher-order representations—the hallmark of deep learning. This work demonstrates that deep learning can be achieved using segregated dendritic compartments, which may help to explain the morphology of neocortical pyramidal neurons. PMID:29205151

Towards deep learning with segregated dendrites.

PubMed

Guerguiev, Jordan; Lillicrap, Timothy P; Richards, Blake A

2017-12-05

Deep learning has led to significant advances in artificial intelligence, in part, by adopting strategies motivated by neurophysiology. However, it is unclear whether deep learning could occur in the real brain. Here, we show that a deep learning algorithm that utilizes multi-compartment neurons might help us to understand how the neocortex optimizes cost functions. Like neocortical pyramidal neurons, neurons in our model receive sensory information and higher-order feedback in electrotonically segregated compartments. Thanks to this segregation, neurons in different layers of the network can coordinate synaptic weight updates. As a result, the network learns to categorize images better than a single layer network. Furthermore, we show that our algorithm takes advantage of multilayer architectures to identify useful higher-order representations-the hallmark of deep learning. This work demonstrates that deep learning can be achieved using segregated dendritic compartments, which may help to explain the morphology of neocortical pyramidal neurons.

Deep learning for neuroimaging: a validation study.

PubMed

Plis, Sergey M; Hjelm, Devon R; Salakhutdinov, Ruslan; Allen, Elena A; Bockholt, Henry J; Long, Jeffrey D; Johnson, Hans J; Paulsen, Jane S; Turner, Jessica A; Calhoun, Vince D

2014-01-01

Deep learning methods have recently made notable advances in the tasks of classification and representation learning. These tasks are important for brain imaging and neuroscience discovery, making the methods attractive for porting to a neuroimager's toolbox. Success of these methods is, in part, explained by the flexibility of deep learning models. However, this flexibility makes the process of porting to new areas a difficult parameter optimization problem. In this work we demonstrate our results (and feasible parameter ranges) in application of deep learning methods to structural and functional brain imaging data. These methods include deep belief networks and their building block the restricted Boltzmann machine. We also describe a novel constraint-based approach to visualizing high dimensional data. We use it to analyze the effect of parameter choices on data transformations. Our results show that deep learning methods are able to learn physiologically important representations and detect latent relations in neuroimaging data.

Deep Learning and Developmental Learning: Emergence of Fine-to-Coarse Conceptual Categories at Layers of Deep Belief Network.

PubMed

Sadeghi, Zahra

2016-09-01

In this paper, I investigate conceptual categories derived from developmental processing in a deep neural network. The similarity matrices of deep representation at each layer of neural network are computed and compared with their raw representation. While the clusters generated by raw representation stand at the basic level of abstraction, conceptual categories obtained from deep representation shows a bottom-up transition procedure. Results demonstrate a developmental course of learning from specific to general level of abstraction through learned layers of representations in a deep belief network. © The Author(s) 2016.

The Effects of Discipline on Deep Approaches to Student Learning and College Outcomes

ERIC Educational Resources Information Center

Nelson Laird, Thomas F.; Shoup, Rick; Kuh, George D.; Schwarz, Michael J.

2008-01-01

"Deep learning" represents student engagement in approaches to learning that emphasize integration, synthesis, and reflection. Because learning is a shared responsibility between students and faculty, it is important to determine whether faculty members emphasize deep approaches to learning and to assess how much students employ these approaches.…

RNA-protein binding motifs mining with a new hybrid deep learning based cross-domain knowledge integration approach.

PubMed

Pan, Xiaoyong; Shen, Hong-Bin

2017-02-28

RNAs play key roles in cells through the interactions with proteins known as the RNA-binding proteins (RBP) and their binding motifs enable crucial understanding of the post-transcriptional regulation of RNAs. How the RBPs correctly recognize the target RNAs and why they bind specific positions is still far from clear. Machine learning-based algorithms are widely acknowledged to be capable of speeding up this process. Although many automatic tools have been developed to predict the RNA-protein binding sites from the rapidly growing multi-resource data, e.g. sequence, structure, their domain specific features and formats have posed significant computational challenges. One of current difficulties is that the cross-source shared common knowledge is at a higher abstraction level beyond the observed data, resulting in a low efficiency of direct integration of observed data across domains. The other difficulty is how to interpret the prediction results. Existing approaches tend to terminate after outputting the potential discrete binding sites on the sequences, but how to assemble them into the meaningful binding motifs is a topic worth of further investigation. In viewing of these challenges, we propose a deep learning-based framework (iDeep) by using a novel hybrid convolutional neural network and deep belief network to predict the RBP interaction sites and motifs on RNAs. This new protocol is featured by transforming the original observed data into a high-level abstraction feature space using multiple layers of learning blocks, where the shared representations across different domains are integrated. To validate our iDeep method, we performed experiments on 31 large-scale CLIP-seq datasets, and our results show that by integrating multiple sources of data, the average AUC can be improved by 8% compared to the best single-source-based predictor; and through cross-domain knowledge integration at an abstraction level, it outperforms the state-of-the-art predictors by 6%. Besides the overall enhanced prediction performance, the convolutional neural network module embedded in iDeep is also able to automatically capture the interpretable binding motifs for RBPs. Large-scale experiments demonstrate that these mined binding motifs agree well with the experimentally verified results, suggesting iDeep is a promising approach in the real-world applications. The iDeep framework not only can achieve promising performance than the state-of-the-art predictors, but also easily capture interpretable binding motifs. iDeep is available at http://www.csbio.sjtu.edu.cn/bioinf/iDeep.

Deep-Elaborative Learning of Introductory Management Accounting for Business Students

ERIC Educational Resources Information Center

Choo, Freddie; Tan, Kim B.

2005-01-01

Research by Choo and Tan (1990; 1995) suggests that accounting students, who engage in deep-elaborative learning, have a better understanding of the course materials. The purposes of this paper are: (1) to describe a deep-elaborative instructional approach (hereafter DEIA) that promotes deep-elaborative learning of introductory management…

Epithelium-Stroma Classification via Convolutional Neural Networks and Unsupervised Domain Adaptation in Histopathological Images.

PubMed

Huang, Yue; Zheng, Han; Liu, Chi; Ding, Xinghao; Rohde, Gustavo K

2017-11-01

Epithelium-stroma classification is a necessary preprocessing step in histopathological image analysis. Current deep learning based recognition methods for histology data require collection of large volumes of labeled data in order to train a new neural network when there are changes to the image acquisition procedure. However, it is extremely expensive for pathologists to manually label sufficient volumes of data for each pathology study in a professional manner, which results in limitations in real-world applications. A very simple but effective deep learning method, that introduces the concept of unsupervised domain adaptation to a simple convolutional neural network (CNN), has been proposed in this paper. Inspired by transfer learning, our paper assumes that the training data and testing data follow different distributions, and there is an adaptation operation to more accurately estimate the kernels in CNN in feature extraction, in order to enhance performance by transferring knowledge from labeled data in source domain to unlabeled data in target domain. The model has been evaluated using three independent public epithelium-stroma datasets by cross-dataset validations. The experimental results demonstrate that for epithelium-stroma classification, the proposed framework outperforms the state-of-the-art deep neural network model, and it also achieves better performance than other existing deep domain adaptation methods. The proposed model can be considered to be a better option for real-world applications in histopathological image analysis, since there is no longer a requirement for large-scale labeled data in each specified domain.

Hello World Deep Learning in Medical Imaging.

PubMed

Lakhani, Paras; Gray, Daniel L; Pett, Carl R; Nagy, Paul; Shih, George

2018-05-03

There is recent popularity in applying machine learning to medical imaging, notably deep learning, which has achieved state-of-the-art performance in image analysis and processing. The rapid adoption of deep learning may be attributed to the availability of machine learning frameworks and libraries to simplify their use. In this tutorial, we provide a high-level overview of how to build a deep neural network for medical image classification, and provide code that can help those new to the field begin their informatics projects.

EEG-based driver fatigue detection using hybrid deep generic model.

PubMed

Phyo Phyo San; Sai Ho Ling; Rifai Chai; Tran, Yvonne; Craig, Ashley; Hung Nguyen

2016-08-01

Classification of electroencephalography (EEG)-based application is one of the important process for biomedical engineering. Driver fatigue is a major case of traffic accidents worldwide and considered as a significant problem in recent decades. In this paper, a hybrid deep generic model (DGM)-based support vector machine is proposed for accurate detection of driver fatigue. Traditionally, a probabilistic DGM with deep architecture is quite good at learning invariant features, but it is not always optimal for classification due to its trainable parameters are in the middle layer. Alternatively, Support Vector Machine (SVM) itself is unable to learn complicated invariance, but produces good decision surface when applied to well-behaved features. Consolidating unsupervised high-level feature extraction techniques, DGM and SVM classification makes the integrated framework stronger and enhance mutually in feature extraction and classification. The experimental results showed that the proposed DBN-based driver fatigue monitoring system achieves better testing accuracy of 73.29 % with 91.10 % sensitivity and 55.48 % specificity. In short, the proposed hybrid DGM-based SVM is an effective method for the detection of driver fatigue in EEG.

Deep learning predictions of survival based on MRI in amyotrophic lateral sclerosis.

PubMed

van der Burgh, Hannelore K; Schmidt, Ruben; Westeneng, Henk-Jan; de Reus, Marcel A; van den Berg, Leonard H; van den Heuvel, Martijn P

2017-01-01

Amyotrophic lateral sclerosis (ALS) is a progressive neuromuscular disease, with large variation in survival between patients. Currently, it remains rather difficult to predict survival based on clinical parameters alone. Here, we set out to use clinical characteristics in combination with MRI data to predict survival of ALS patients using deep learning, a machine learning technique highly effective in a broad range of big-data analyses. A group of 135 ALS patients was included from whom high-resolution diffusion-weighted and T1-weighted images were acquired at the first visit to the outpatient clinic. Next, each of the patients was monitored carefully and survival time to death was recorded. Patients were labeled as short, medium or long survivors, based on their recorded time to death as measured from the time of disease onset. In the deep learning procedure, the total group of 135 patients was split into a training set for deep learning (n = 83 patients), a validation set (n = 20) and an independent evaluation set (n = 32) to evaluate the performance of the obtained deep learning networks. Deep learning based on clinical characteristics predicted survival category correctly in 68.8% of the cases. Deep learning based on MRI predicted 62.5% correctly using structural connectivity and 62.5% using brain morphology data. Notably, when we combined the three sources of information, deep learning prediction accuracy increased to 84.4%. Taken together, our findings show the added value of MRI with respect to predicting survival in ALS, demonstrating the advantage of deep learning in disease prognostication.

Reflective education for professional practice: discovering knowledge from experience.

PubMed

Lyons, J

1999-01-01

To continually develop as a discipline, a profession needs to generate a knowledge base that can evolve from education and practice. Midwifery reflective practitioners have the potential to develop clinical expertise directed towards achieving desirable, safe and effective practice. Midwives are 'with woman', providing the family with supportive and helpful relationships as they share the deep and profound experiences of childbirth. To become skilled helpers students need to develop reflective skills and valid midwifery knowledge grounded in their personal experiences and practice. Midwife educators and practitioners can assist students and enhance their learning by expanding the scope of practice, encouraging self-assessment and the development of reflective and professional skills. This paper explores journal writing as a learning strategy for the development of reflective skills within midwifery and explores its value for midwifery education. It also examines, through the use of critical social theory and adult learning principles, how midwives can assist and thus enhance students learning through the development of professional and reflective skills for midwifery practice.

A Deep Learning Approach to Digitally Stain Optical Coherence Tomography Images of the Optic Nerve Head.

PubMed

Devalla, Sripad Krishna; Chin, Khai Sing; Mari, Jean-Martial; Tun, Tin A; Strouthidis, Nicholas G; Aung, Tin; Thiéry, Alexandre H; Girard, Michaël J A

2018-01-01

To develop a deep learning approach to digitally stain optical coherence tomography (OCT) images of the optic nerve head (ONH). A horizontal B-scan was acquired through the center of the ONH using OCT (Spectralis) for one eye of each of 100 subjects (40 healthy and 60 glaucoma). All images were enhanced using adaptive compensation. A custom deep learning network was then designed and trained with the compensated images to digitally stain (i.e., highlight) six tissue layers of the ONH. The accuracy of our algorithm was assessed (against manual segmentations) using the dice coefficient, sensitivity, specificity, intersection over union (IU), and accuracy. We studied the effect of compensation, number of training images, and performance comparison between glaucoma and healthy subjects. For images it had not yet assessed, our algorithm was able to digitally stain the retinal nerve fiber layer + prelamina, the RPE, all other retinal layers, the choroid, and the peripapillary sclera and lamina cribrosa. For all tissues, the dice coefficient, sensitivity, specificity, IU, and accuracy (mean) were 0.84 ± 0.03, 0.92 ± 0.03, 0.99 ± 0.00, 0.89 ± 0.03, and 0.94 ± 0.02, respectively. Our algorithm performed significantly better when compensated images were used for training (P < 0.001). Besides offering a good reliability, digital staining also performed well on OCT images of both glaucoma and healthy individuals. Our deep learning algorithm can simultaneously stain the neural and connective tissues of the ONH, offering a framework to automatically measure multiple key structural parameters of the ONH that may be critical to improve glaucoma management.

Thai visitors' expectations and experiences of explainer interaction within a science museum context.

PubMed

Kamolpattana, Supara; Chen, Ganigar; Sonchaeng, Pichai; Wilkinson, Clare; Willey, Neil; Bultitude, Karen

2015-01-01

In Western literature, there is evidence that museum explainers offer significant potential for enhancing visitors' learning through influencing their knowledge, content, action, behaviour and attitudes. However, little research has focused on the role of explainers in other cultural contexts. This study explored interactions between visitors and museum explainers within the setting of Thailand. Two questionnaires were distributed to 600 visitors and 41 museum explainers. The results demonstrated both potential similarities and differences with Western contexts. Explainers appeared to prefer didactic approaches, focussing on factual knowledge rather than encouraging deep learning. Two-way communication, however, appeared to be enhanced by the use of a 'pseudo-sibling relationship' by explainers. Traditional Thai social reserve was reduced through such approaches, with visitors taking on active learning roles. These findings have implications for training museum explainers in non-Western cultures, as well as museum communication practice more generally. © The Author(s) 2014.

Thai visitors’ expectations and experiences of explainer interaction within a science museum context

PubMed Central

Chen, Ganigar; Sonchaeng, Pichai; Wilkinson, Clare; Willey, Neil; Bultitude, Karen

2015-01-01

In Western literature, there is evidence that museum explainers offer significant potential for enhancing visitors’ learning through influencing their knowledge, content, action, behaviour and attitudes. However, little research has focused on the role of explainers in other cultural contexts. This study explored interactions between visitors and museum explainers within the setting of Thailand. Two questionnaires were distributed to 600 visitors and 41 museum explainers. The results demonstrated both potential similarities and differences with Western contexts. Explainers appeared to prefer didactic approaches, focussing on factual knowledge rather than encouraging deep learning. Two-way communication, however, appeared to be enhanced by the use of a ‘pseudo-sibling relationship’ by explainers. Traditional Thai social reserve was reduced through such approaches, with visitors taking on active learning roles. These findings have implications for training museum explainers in non-Western cultures, as well as museum communication practice more generally. PMID:24751689

Integrative and Deep Learning through a Learning Community: A Process View of Self

ERIC Educational Resources Information Center

Mahoney, Sandra; Schamber, Jon

2011-01-01

This study investigated deep learning produced in a community of general education courses. Student speeches on liberal education were analyzed for discovering a grounded theory of ideas about self. The study found that learning communities cultivate deep, integrative learning that makes the value of a liberal education relevant to students.…

Problem-Based Learning to Foster Deep Learning in Preservice Geography Teacher Education

ERIC Educational Resources Information Center

Golightly, Aubrey; Raath, Schalk

2015-01-01

In South Africa, geography education students' approach to deep learning has received little attention. Therefore the purpose of this one-shot experimental case study was to evaluate the extent to which first-year geography education students used deep or surface learning in an embedded problem-based learning (PBL) format. The researchers measured…

Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security.

PubMed

Kang, Min-Joo; Kang, Je-Won

2016-01-01

A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus.

Intrusion Detection System Using Deep Neural Network for In-Vehicle Network Security

PubMed Central

Kang, Min-Joo

2016-01-01

A novel intrusion detection system (IDS) using a deep neural network (DNN) is proposed to enhance the security of in-vehicular network. The parameters building the DNN structure are trained with probability-based feature vectors that are extracted from the in-vehicular network packets. For a given packet, the DNN provides the probability of each class discriminating normal and attack packets, and, thus the sensor can identify any malicious attack to the vehicle. As compared to the traditional artificial neural network applied to the IDS, the proposed technique adopts recent advances in deep learning studies such as initializing the parameters through the unsupervised pre-training of deep belief networks (DBN), therefore improving the detection accuracy. It is demonstrated with experimental results that the proposed technique can provide a real-time response to the attack with a significantly improved detection ratio in controller area network (CAN) bus. PMID:27271802

Arts-Based Learning: A New Approach to Nursing Education Using Andragogy.

PubMed

Nguyen, Megan; Miranda, Joyal; Lapum, Jennifer; Donald, Faith

2016-07-01

Learner-oriented strategies focusing on learning processes are needed to prepare nursing students for complex practice situations. An arts-based learning approach uses art to nurture cognitive and emotional learning. Knowles' theory of andragogy aims to develop the skill of learning and can inform the process of implementing arts-based learning. This article explores the use and evaluation of andragogy-informed arts-based learning for teaching nursing theory at the undergraduate level. Arts-based learning activities were implemented and then evaluated by students and instructors using anonymous questionnaires. Most students reported that the activities promoted learning. All instructors indicated an interest in integrating arts-based learning into the curricula. Facilitators and barriers to mainstreaming arts-based learning were highlighted. Findings stimulate implications for prospective research and education. Findings suggest that arts-based learning approaches enhance learning by supporting deep inquiry and different learning styles. Further exploration of andragogy-informed arts-based learning in nursing and other disciplines is warranted. [J Nurs Educ. 2016;55(7):407-410.]. Copyright 2016, SLACK Incorporated.

Deep Direct Reinforcement Learning for Financial Signal Representation and Trading.

PubMed

Deng, Yue; Bao, Feng; Kong, Youyong; Ren, Zhiquan; Dai, Qionghai

2017-03-01

Can we train the computer to beat experienced traders for financial assert trading? In this paper, we try to address this challenge by introducing a recurrent deep neural network (NN) for real-time financial signal representation and trading. Our model is inspired by two biological-related learning concepts of deep learning (DL) and reinforcement learning (RL). In the framework, the DL part automatically senses the dynamic market condition for informative feature learning. Then, the RL module interacts with deep representations and makes trading decisions to accumulate the ultimate rewards in an unknown environment. The learning system is implemented in a complex NN that exhibits both the deep and recurrent structures. Hence, we propose a task-aware backpropagation through time method to cope with the gradient vanishing issue in deep training. The robustness of the neural system is verified on both the stock and the commodity future markets under broad testing conditions.

Deep Logic Networks: Inserting and Extracting Knowledge From Deep Belief Networks.

PubMed

Tran, Son N; d'Avila Garcez, Artur S

2018-02-01

Developments in deep learning have seen the use of layerwise unsupervised learning combined with supervised learning for fine-tuning. With this layerwise approach, a deep network can be seen as a more modular system that lends itself well to learning representations. In this paper, we investigate whether such modularity can be useful to the insertion of background knowledge into deep networks, whether it can improve learning performance when it is available, and to the extraction of knowledge from trained deep networks, and whether it can offer a better understanding of the representations learned by such networks. To this end, we use a simple symbolic language-a set of logical rules that we call confidence rules-and show that it is suitable for the representation of quantitative reasoning in deep networks. We show by knowledge extraction that confidence rules can offer a low-cost representation for layerwise networks (or restricted Boltzmann machines). We also show that layerwise extraction can produce an improvement in the accuracy of deep belief networks. Furthermore, the proposed symbolic characterization of deep networks provides a novel method for the insertion of prior knowledge and training of deep networks. With the use of this method, a deep neural-symbolic system is proposed and evaluated, with the experimental results indicating that modularity through the use of confidence rules and knowledge insertion can be beneficial to network performance.

Deep Learning for Computer Vision: A Brief Review

PubMed Central

Doulamis, Nikolaos; Doulamis, Anastasios; Protopapadakis, Eftychios

2018-01-01

Over the last years deep learning methods have been shown to outperform previous state-of-the-art machine learning techniques in several fields, with computer vision being one of the most prominent cases. This review paper provides a brief overview of some of the most significant deep learning schemes used in computer vision problems, that is, Convolutional Neural Networks, Deep Boltzmann Machines and Deep Belief Networks, and Stacked Denoising Autoencoders. A brief account of their history, structure, advantages, and limitations is given, followed by a description of their applications in various computer vision tasks, such as object detection, face recognition, action and activity recognition, and human pose estimation. Finally, a brief overview is given of future directions in designing deep learning schemes for computer vision problems and the challenges involved therein. PMID:29487619

Deep Belief Networks for Electroencephalography: A Review of Recent Contributions and Future Outlooks.

PubMed

Movahedi, Faezeh; Coyle, James L; Sejdic, Ervin

2018-05-01

Deep learning, a relatively new branch of machine learning, has been investigated for use in a variety of biomedical applications. Deep learning algorithms have been used to analyze different physiological signals and gain a better understanding of human physiology for automated diagnosis of abnormal conditions. In this paper, we provide an overview of deep learning approaches with a focus on deep belief networks in electroencephalography applications. We investigate the state-of-the-art algorithms for deep belief networks and then cover the application of these algorithms and their performances in electroencephalographic applications. We covered various applications of electroencephalography in medicine, including emotion recognition, sleep stage classification, and seizure detection, in order to understand how deep learning algorithms could be modified to better suit the tasks desired. This review is intended to provide researchers with a broad overview of the currently existing deep belief network methodology for electroencephalography signals, as well as to highlight potential challenges for future research.

Hyperspectral Image Enhancement and Mixture Deep-Learning Classification of Corneal Epithelium Injuries

PubMed Central

Md Noor, Siti Salwa; Michael, Kaleena; Marshall, Stephen; Ren, Jinchang

2017-01-01

In our preliminary study, the reflectance signatures obtained from hyperspectral imaging (HSI) of normal and abnormal corneal epithelium tissues of porcine show similar morphology with subtle differences. Here we present image enhancement algorithms that can be used to improve the interpretability of data into clinically relevant information to facilitate diagnostics. A total of 25 corneal epithelium images without the application of eye staining were used. Three image feature extraction approaches were applied for image classification: (i) image feature classification from histogram using a support vector machine with a Gaussian radial basis function (SVM-GRBF); (ii) physical image feature classification using deep-learning Convolutional Neural Networks (CNNs) only; and (iii) the combined classification of CNNs and SVM-Linear. The performance results indicate that our chosen image features from the histogram and length-scale parameter were able to classify with up to 100% accuracy; particularly, at CNNs and CNNs-SVM, by employing 80% of the data sample for training and 20% for testing. Thus, in the assessment of corneal epithelium injuries, HSI has high potential as a method that could surpass current technologies regarding speed, objectivity, and reliability. PMID:29144388

Deep Learning as an Individual, Conditional, and Contextual Influence on First-Year Student Outcomes

ERIC Educational Resources Information Center

Reason, Robert D.; Cox, Bradley E.; McIntosh, Kadian; Terenzini, Patrick T.

2010-01-01

For years, educators have drawn a distinction between deep cognitive processing and surface-level cognitive processing, with the former resulting in greater learning. In recent years, researchers at NSSE have created DEEP Learning scales, which consist of items related to students' experiences which are believed to encourage deep processing. In…

Deep Neural Architectures for Mapping Scalp to Intracranial EEG.

PubMed

Antoniades, Andreas; Spyrou, Loukianos; Martin-Lopez, David; Valentin, Antonio; Alarcon, Gonzalo; Sanei, Saeid; Took, Clive Cheong

2018-03-19

Data is often plagued by noise which encumbers machine learning of clinically useful biomarkers and electroencephalogram (EEG) data is no exemption. Intracranial EEG (iEEG) data enhances the training of deep learning models of the human brain, yet is often prohibitive due to the invasive recording process. A more convenient alternative is to record brain activity using scalp electrodes. However, the inherent noise associated with scalp EEG data often impedes the learning process of neural models, achieving substandard performance. Here, an ensemble deep learning architecture for nonlinearly mapping scalp to iEEG data is proposed. The proposed architecture exploits the information from a limited number of joint scalp-intracranial recording to establish a novel methodology for detecting the epileptic discharges from the sEEG of a general population of subjects. Statistical tests and qualitative analysis have revealed that the generated pseudo-intracranial data are highly correlated with the true intracranial data. This facilitated the detection of IEDs from the scalp recordings where such waveforms are not often visible. As a real-world clinical application, these pseudo-iEEGs are then used by a convolutional neural network for the automated classification of intracranial epileptic discharges (IEDs) and non-IED of trials in the context of epilepsy analysis. Although the aim of this work was to circumvent the unavailability of iEEG and the limitations of sEEG, we have achieved a classification accuracy of 68% an increase of 6% over the previously proposed linear regression mapping.

Deep Learning to Classify Radiology Free-Text Reports.

PubMed

Chen, Matthew C; Ball, Robyn L; Yang, Lingyao; Moradzadeh, Nathaniel; Chapman, Brian E; Larson, David B; Langlotz, Curtis P; Amrhein, Timothy J; Lungren, Matthew P

2018-03-01

Purpose To evaluate the performance of a deep learning convolutional neural network (CNN) model compared with a traditional natural language processing (NLP) model in extracting pulmonary embolism (PE) findings from thoracic computed tomography (CT) reports from two institutions. Materials and Methods Contrast material-enhanced CT examinations of the chest performed between January 1, 1998, and January 1, 2016, were selected. Annotations by two human radiologists were made for three categories: the presence, chronicity, and location of PE. Classification of performance of a CNN model with an unsupervised learning algorithm for obtaining vector representations of words was compared with the open-source application PeFinder. Sensitivity, specificity, accuracy, and F1 scores for both the CNN model and PeFinder in the internal and external validation sets were determined. Results The CNN model demonstrated an accuracy of 99% and an area under the curve value of 0.97. For internal validation report data, the CNN model had a statistically significant larger F1 score (0.938) than did PeFinder (0.867) when classifying findings as either PE positive or PE negative, but no significant difference in sensitivity, specificity, or accuracy was found. For external validation report data, no statistical difference between the performance of the CNN model and PeFinder was found. Conclusion A deep learning CNN model can classify radiology free-text reports with accuracy equivalent to or beyond that of an existing traditional NLP model. © RSNA, 2017 Online supplemental material is available for this article.

Deep learning of unsteady laminar flow over a cylinder

NASA Astrophysics Data System (ADS)

Lee, Sangseung; You, Donghyun

2017-11-01

Unsteady flow over a circular cylinder is reconstructed using deep learning with a particular emphasis on elucidating the potential of learning the solution of the Navier-Stokes equations. A deep neural network (DNN) is employed for deep learning, while numerical simulations are conducted to produce training database. Instantaneous and mean flow fields which are reconstructed by deep learning are compared with the simulation results. Fourier transform of flow variables has been conducted to validate the ability of DNN to capture both amplitudes and frequencies of flow motions. Basis decomposition of learned flow is performed to understand the underlying mechanisms of learning flow through DNN. The present study suggests that a deep learning technique can be utilized for reconstruction and, potentially, for prediction of fluid flow instead of solving the Navier-Stokes equations. This work was supported by the National Research Foundation of Korea(NRF) Grant funded by the Korea government(Ministry of Science, ICT and Future Planning) (No. 2014R1A2A1A11049599, No. 2015R1A2A1A15056086, No. 2016R1E1A2A01939553).

Combining deep learning with anatomical analysis for segmentation of the portal vein for liver SBRT planning

NASA Astrophysics Data System (ADS)

Ibragimov, Bulat; Toesca, Diego; Chang, Daniel; Koong, Albert; Xing, Lei

2017-12-01

Automated segmentation of the portal vein (PV) for liver radiotherapy planning is a challenging task due to potentially low vasculature contrast, complex PV anatomy and image artifacts originated from fiducial markers and vasculature stents. In this paper, we propose a novel framework for automated segmentation of the PV from computed tomography (CT) images. We apply convolutional neural networks (CNNs) to learn the consistent appearance patterns of the PV using a training set of CT images with reference annotations and then enhance the PV in previously unseen CT images. Markov random fields (MRFs) were further used to smooth the results of the enhancement of the CNN enhancement and remove isolated mis-segmented regions. Finally, CNN-MRF-based enhancement was augmented with PV centerline detection that relied on PV anatomical properties such as tubularity and branch composition. The framework was validated on a clinical database with 72 CT images of patients scheduled for liver stereotactic body radiation therapy. The obtained accuracy of the segmentation was DSC= 0.83 and \

Boosting compound-protein interaction prediction by deep learning.

PubMed

Tian, Kai; Shao, Mingyu; Wang, Yang; Guan, Jihong; Zhou, Shuigeng

2016-11-01

The identification of interactions between compounds and proteins plays an important role in network pharmacology and drug discovery. However, experimentally identifying compound-protein interactions (CPIs) is generally expensive and time-consuming, computational approaches are thus introduced. Among these, machine-learning based methods have achieved a considerable success. However, due to the nonlinear and imbalanced nature of biological data, many machine learning approaches have their own limitations. Recently, deep learning techniques show advantages over many state-of-the-art machine learning methods in some applications. In this study, we aim at improving the performance of CPI prediction based on deep learning, and propose a method called DL-CPI (the abbreviation of Deep Learning for Compound-Protein Interactions prediction), which employs deep neural network (DNN) to effectively learn the representations of compound-protein pairs. Extensive experiments show that DL-CPI can learn useful features of compound-protein pairs by a layerwise abstraction, and thus achieves better prediction performance than existing methods on both balanced and imbalanced datasets. Copyright © 2016 Elsevier Inc. All rights reserved.

A Deep Machine Learning Method for Classifying Cyclic Time Series of Biological Signals Using Time-Growing Neural Network.

PubMed

Gharehbaghi, Arash; Linden, Maria

2017-10-12

This paper presents a novel method for learning the cyclic contents of stochastic time series: the deep time-growing neural network (DTGNN). The DTGNN combines supervised and unsupervised methods in different levels of learning for an enhanced performance. It is employed by a multiscale learning structure to classify cyclic time series (CTS), in which the dynamic contents of the time series are preserved in an efficient manner. This paper suggests a systematic procedure for finding the design parameter of the classification method for a one-versus-multiple class application. A novel validation method is also suggested for evaluating the structural risk, both in a quantitative and a qualitative manner. The effect of the DTGNN on the performance of the classifier is statistically validated through the repeated random subsampling using different sets of CTS, from different medical applications. The validation involves four medical databases, comprised of 108 recordings of the electroencephalogram signal, 90 recordings of the electromyogram signal, 130 recordings of the heart sound signal, and 50 recordings of the respiratory sound signal. Results of the statistical validations show that the DTGNN significantly improves the performance of the classification and also exhibits an optimal structural risk.

Performance evaluation of 2D and 3D deep learning approaches for automatic segmentation of multiple organs on CT images

NASA Astrophysics Data System (ADS)

Zhou, Xiangrong; Yamada, Kazuma; Kojima, Takuya; Takayama, Ryosuke; Wang, Song; Zhou, Xinxin; Hara, Takeshi; Fujita, Hiroshi

2018-02-01

The purpose of this study is to evaluate and compare the performance of modern deep learning techniques for automatically recognizing and segmenting multiple organ regions on 3D CT images. CT image segmentation is one of the important task in medical image analysis and is still very challenging. Deep learning approaches have demonstrated the capability of scene recognition and semantic segmentation on nature images and have been used to address segmentation problems of medical images. Although several works showed promising results of CT image segmentation by using deep learning approaches, there is no comprehensive evaluation of segmentation performance of the deep learning on segmenting multiple organs on different portions of CT scans. In this paper, we evaluated and compared the segmentation performance of two different deep learning approaches that used 2D- and 3D deep convolutional neural networks (CNN) without- and with a pre-processing step. A conventional approach that presents the state-of-the-art performance of CT image segmentation without deep learning was also used for comparison. A dataset that includes 240 CT images scanned on different portions of human bodies was used for performance evaluation. The maximum number of 17 types of organ regions in each CT scan were segmented automatically and compared to the human annotations by using ratio of intersection over union (IU) as the criterion. The experimental results demonstrated the IUs of the segmentation results had a mean value of 79% and 67% by averaging 17 types of organs that segmented by a 3D- and 2D deep CNN, respectively. All the results of the deep learning approaches showed a better accuracy and robustness than the conventional segmentation method that used probabilistic atlas and graph-cut methods. The effectiveness and the usefulness of deep learning approaches were demonstrated for solving multiple organs segmentation problem on 3D CT images.

Deep Learning: A Primer for Radiologists.

PubMed

Chartrand, Gabriel; Cheng, Phillip M; Vorontsov, Eugene; Drozdzal, Michal; Turcotte, Simon; Pal, Christopher J; Kadoury, Samuel; Tang, An

2017-01-01

Deep learning is a class of machine learning methods that are gaining success and attracting interest in many domains, including computer vision, speech recognition, natural language processing, and playing games. Deep learning methods produce a mapping from raw inputs to desired outputs (eg, image classes). Unlike traditional machine learning methods, which require hand-engineered feature extraction from inputs, deep learning methods learn these features directly from data. With the advent of large datasets and increased computing power, these methods can produce models with exceptional performance. These models are multilayer artificial neural networks, loosely inspired by biologic neural systems. Weighted connections between nodes (neurons) in the network are iteratively adjusted based on example pairs of inputs and target outputs by back-propagating a corrective error signal through the network. For computer vision tasks, convolutional neural networks (CNNs) have proven to be effective. Recently, several clinical applications of CNNs have been proposed and studied in radiology for classification, detection, and segmentation tasks. This article reviews the key concepts of deep learning for clinical radiologists, discusses technical requirements, describes emerging applications in clinical radiology, and outlines limitations and future directions in this field. Radiologists should become familiar with the principles and potential applications of deep learning in medical imaging. © RSNA, 2017.

Distributed deep learning networks among institutions for medical imaging.

PubMed

Chang, Ken; Balachandar, Niranjan; Lam, Carson; Yi, Darvin; Brown, James; Beers, Andrew; Rosen, Bruce; Rubin, Daniel L; Kalpathy-Cramer, Jayashree

2018-03-29

Deep learning has become a promising approach for automated support for clinical diagnosis. When medical data samples are limited, collaboration among multiple institutions is necessary to achieve high algorithm performance. However, sharing patient data often has limitations due to technical, legal, or ethical concerns. In this study, we propose methods of distributing deep learning models as an attractive alternative to sharing patient data. We simulate the distribution of deep learning models across 4 institutions using various training heuristics and compare the results with a deep learning model trained on centrally hosted patient data. The training heuristics investigated include ensembling single institution models, single weight transfer, and cyclical weight transfer. We evaluated these approaches for image classification in 3 independent image collections (retinal fundus photos, mammography, and ImageNet). We find that cyclical weight transfer resulted in a performance that was comparable to that of centrally hosted patient data. We also found that there is an improvement in the performance of cyclical weight transfer heuristic with a high frequency of weight transfer. We show that distributing deep learning models is an effective alternative to sharing patient data. This finding has implications for any collaborative deep learning study.

Enhancing project-oriented learning by joining communities of practice and opening spaces for relatedness

NASA Astrophysics Data System (ADS)

Pascual, R.

2010-03-01

This article describes an extension to project-oriented learning to increase social construction of knowledge and learning. The focus is on: (a) maximising opportunities for students to share their knowledge with practitioners by joining communities of practice, and (b) increasing their intrinsic motivation by creating conditions for student's relatedness. The case study considers a last year capstone course in Mechanical Engineering. The work addresses innovative practices of active learning and beyond project-oriented learning through: (a) the development of a web-based decision support system, (b) meetings between the communities of students, maintenance engineers and academics, and (c) new off-campus group instances. The author hypothesises that this multi-modal approach increases deep learning and social impact of the educational process. Surveys to the actors support a successful achievement of the educational goals. The methodology can easily be extended to further improve the learning process.

Strategies for Effective Faculty Involvement in Online Activities Aimed at Promoting Critical Thinking and Deep Learning

ERIC Educational Resources Information Center

Abdul Razzak, Nina

2016-01-01

Highly-traditional education systems that mainly offer what is known as "direct instruction" usually result in graduates with a surface approach to learning rather than a deep one. What is meant by deep-learning is learning that involves critical analysis, the linking of ideas and concepts, creative problem solving, and application…

Deep learning applications in ophthalmology.

PubMed

Rahimy, Ehsan

2018-05-01

To describe the emerging applications of deep learning in ophthalmology. Recent studies have shown that various deep learning models are capable of detecting and diagnosing various diseases afflicting the posterior segment of the eye with high accuracy. Most of the initial studies have centered around detection of referable diabetic retinopathy, age-related macular degeneration, and glaucoma. Deep learning has shown promising results in automated image analysis of fundus photographs and optical coherence tomography images. Additional testing and research is required to clinically validate this technology.

DeepInfer: open-source deep learning deployment toolkit for image-guided therapy

NASA Astrophysics Data System (ADS)

Mehrtash, Alireza; Pesteie, Mehran; Hetherington, Jorden; Behringer, Peter A.; Kapur, Tina; Wells, William M.; Rohling, Robert; Fedorov, Andriy; Abolmaesumi, Purang

2017-03-01

Deep learning models have outperformed some of the previous state-of-the-art approaches in medical image analysis. Instead of using hand-engineered features, deep models attempt to automatically extract hierarchical representations at multiple levels of abstraction from the data. Therefore, deep models are usually considered to be more flexible and robust solutions for image analysis problems compared to conventional computer vision models. They have demonstrated significant improvements in computer-aided diagnosis and automatic medical image analysis applied to such tasks as image segmentation, classification and registration. However, deploying deep learning models often has a steep learning curve and requires detailed knowledge of various software packages. Thus, many deep models have not been integrated into the clinical research work ows causing a gap between the state-of-the-art machine learning in medical applications and evaluation in clinical research procedures. In this paper, we propose "DeepInfer" - an open-source toolkit for developing and deploying deep learning models within the 3D Slicer medical image analysis platform. Utilizing a repository of task-specific models, DeepInfer allows clinical researchers and biomedical engineers to deploy a trained model selected from the public registry, and apply it to new data without the need for software development or configuration. As two practical use cases, we demonstrate the application of DeepInfer in prostate segmentation for targeted MRI-guided biopsy and identification of the target plane in 3D ultrasound for spinal injections.

DeepInfer: Open-Source Deep Learning Deployment Toolkit for Image-Guided Therapy.

PubMed

Mehrtash, Alireza; Pesteie, Mehran; Hetherington, Jorden; Behringer, Peter A; Kapur, Tina; Wells, William M; Rohling, Robert; Fedorov, Andriy; Abolmaesumi, Purang

2017-02-11

Deep learning models have outperformed some of the previous state-of-the-art approaches in medical image analysis. Instead of using hand-engineered features, deep models attempt to automatically extract hierarchical representations at multiple levels of abstraction from the data. Therefore, deep models are usually considered to be more flexible and robust solutions for image analysis problems compared to conventional computer vision models. They have demonstrated significant improvements in computer-aided diagnosis and automatic medical image analysis applied to such tasks as image segmentation, classification and registration. However, deploying deep learning models often has a steep learning curve and requires detailed knowledge of various software packages. Thus, many deep models have not been integrated into the clinical research workflows causing a gap between the state-of-the-art machine learning in medical applications and evaluation in clinical research procedures. In this paper, we propose "DeepInfer" - an open-source toolkit for developing and deploying deep learning models within the 3D Slicer medical image analysis platform. Utilizing a repository of task-specific models, DeepInfer allows clinical researchers and biomedical engineers to deploy a trained model selected from the public registry, and apply it to new data without the need for software development or configuration. As two practical use cases, we demonstrate the application of DeepInfer in prostate segmentation for targeted MRI-guided biopsy and identification of the target plane in 3D ultrasound for spinal injections.

DeepInfer: Open-Source Deep Learning Deployment Toolkit for Image-Guided Therapy

PubMed Central

Mehrtash, Alireza; Pesteie, Mehran; Hetherington, Jorden; Behringer, Peter A.; Kapur, Tina; Wells, William M.; Rohling, Robert; Fedorov, Andriy; Abolmaesumi, Purang

2017-01-01

Deep learning models have outperformed some of the previous state-of-the-art approaches in medical image analysis. Instead of using hand-engineered features, deep models attempt to automatically extract hierarchical representations at multiple levels of abstraction from the data. Therefore, deep models are usually considered to be more flexible and robust solutions for image analysis problems compared to conventional computer vision models. They have demonstrated significant improvements in computer-aided diagnosis and automatic medical image analysis applied to such tasks as image segmentation, classification and registration. However, deploying deep learning models often has a steep learning curve and requires detailed knowledge of various software packages. Thus, many deep models have not been integrated into the clinical research workflows causing a gap between the state-of-the-art machine learning in medical applications and evaluation in clinical research procedures. In this paper, we propose “DeepInfer” – an open-source toolkit for developing and deploying deep learning models within the 3D Slicer medical image analysis platform. Utilizing a repository of task-specific models, DeepInfer allows clinical researchers and biomedical engineers to deploy a trained model selected from the public registry, and apply it to new data without the need for software development or configuration. As two practical use cases, we demonstrate the application of DeepInfer in prostate segmentation for targeted MRI-guided biopsy and identification of the target plane in 3D ultrasound for spinal injections. PMID:28615794

Can YouTube enhance student nurse learning?

PubMed

Clifton, Andrew; Mann, Claire

2011-05-01

The delivery of nurse education has changed radically in the past two decades. Increasingly, nurse educators are using new technology in the classroom to enhance their teaching and learning. One recent technological development to emerge is the user-generated content website YouTube. Originally YouTube was used as a repository for sharing home-made videos, more recently online content is being generated by political parties, businesses and educationalists. We recently delivered a module to undergraduate student nurses in which the teaching and learning were highly populated with YouTube resources. We found that the use of YouTube videos increased student engagement, critical awareness and facilitated deep learning. Furthermore, these videos could be accessed at any time of the day and from a place to suit the student. We acknowledge that there are some constraints to using YouTube for teaching and learning particularly around the issue of unregulated content which is often misleading, inaccurate or biased. However, we strongly urge nurse educators to consider using YouTube for teaching and learning, in and outside the classroom, to a generation of students who are native of a rapidly changing digital world. Copyright © 2010 Elsevier Ltd. All rights reserved.

Landcover Classification Using Deep Fully Convolutional Neural Networks

NASA Astrophysics Data System (ADS)

Wang, J.; Li, X.; Zhou, S.; Tang, J.

2017-12-01

Land cover classification has always been an essential application in remote sensing. Certain image features are needed for land cover classification whether it is based on pixel or object-based methods. Different from other machine learning methods, deep learning model not only extracts useful information from multiple bands/attributes, but also learns spatial characteristics. In recent years, deep learning methods have been developed rapidly and widely applied in image recognition, semantic understanding, and other application domains. However, there are limited studies applying deep learning methods in land cover classification. In this research, we used fully convolutional networks (FCN) as the deep learning model to classify land covers. The National Land Cover Database (NLCD) within the state of Kansas was used as training dataset and Landsat images were classified using the trained FCN model. We also applied an image segmentation method to improve the original results from the FCN model. In addition, the pros and cons between deep learning and several machine learning methods were compared and explored. Our research indicates: (1) FCN is an effective classification model with an overall accuracy of 75%; (2) image segmentation improves the classification results with better match of spatial patterns; (3) FCN has an excellent ability of learning which can attains higher accuracy and better spatial patterns compared with several machine learning methods.

Deep kernel learning method for SAR image target recognition

NASA Astrophysics Data System (ADS)

Chen, Xiuyuan; Peng, Xiyuan; Duan, Ran; Li, Junbao

2017-10-01

With the development of deep learning, research on image target recognition has made great progress in recent years. Remote sensing detection urgently requires target recognition for military, geographic, and other scientific research. This paper aims to solve the synthetic aperture radar image target recognition problem by combining deep and kernel learning. The model, which has a multilayer multiple kernel structure, is optimized layer by layer with the parameters of Support Vector Machine and a gradient descent algorithm. This new deep kernel learning method improves accuracy and achieves competitive recognition results compared with other learning methods.

Harnessing wake vortices for efficient collective swimming via deep reinfrcement learning

NASA Astrophysics Data System (ADS)

Verma, Siddartha; Novati, Guido; Koumoutsakos, Petros; ChairComputing Science Team

2017-11-01

Collective motion may bestow evolutionary advantages to a number of animal species. Soaring flocks of birds, teeming swarms of insects, and swirling masses of schooling fish, all to some extent enjoy anti-predator benefits, increased foraging success, and enhanced problem-solving abilities. Coordinated activity may also provide energetic benefits, as in the case of large groups of fish where swimmers exploit unsteady flow-patterns generated in the wake. Both experimental and computational investigations of such scenarios are hampered by difficulties associated with studying multiple swimmers. Consequentially, the precise energy-saving mechanisms at play remain largely unknown. We combine high-fidelity numerical simulations of multiple, self propelled swimmers with novel deep reinforcement learning algorithms to discover optimal ways for swimmers to interact with unsteady wakes, in a fully unsupervised manner. We identify optimal flow-interaction strategies devised by the resulting autonomous swimmers, and use it to formulate an effective control-logic. We demonstrate, via 3D simulations of controlled groups that swimmers exploiting the learned strategy exhibit a significant reduction in energy-expenditure. ERC Advanced Investigator Award 341117.

Deep learning for computational chemistry.

PubMed

Goh, Garrett B; Hodas, Nathan O; Vishnu, Abhinav

2017-06-15

The rise and fall of artificial neural networks is well documented in the scientific literature of both computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on multilayer neural networks. Within the last few years, we have seen the transformative impact of deep learning in many domains, particularly in speech recognition and computer vision, to the extent that the majority of expert practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. In this review, we provide an introductory overview into the theory of deep neural networks and their unique properties that distinguish them from traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including quantitative structure activity relationship, virtual screening, protein structure prediction, quantum chemistry, materials design, and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non-neural networks state-of-the-art models across disparate research topics, and deep neural network-based models often exceeded the "glass ceiling" expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a valuable tool for computational chemistry. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

Deep learning for computational chemistry

DOE Office of Scientific and Technical Information (OSTI.GOV)

Goh, Garrett B.; Hodas, Nathan O.; Vishnu, Abhinav

The rise and fall of artificial neural networks is well documented in the scientific literature of both the fields of computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on “deep” neural networks. Within the last few years, we have seen the transformative impact of deep learning the computer science domain, notably in speech recognition and computer vision, to the extent that the majority of practitioners in those field are now regularly eschewing prior established models in favor of deep learning models. Inmore » this review, we provide an introductory overview into the theory of deep neural networks and their unique properties as compared to traditional machine learning algorithms used in cheminformatics. By providing an overview of the variety of emerging applications of deep neural networks, we highlight its ubiquity and broad applicability to a wide range of challenges in the field, including QSAR, virtual screening, protein structure modeling, QM calculations, materials synthesis and property prediction. In reviewing the performance of deep neural networks, we observed a consistent outperformance against non neural networks state-of-the-art models across disparate research topics, and deep neural network based models often exceeded the “glass ceiling” expectations of their respective tasks. Coupled with the maturity of GPU-accelerated computing for training deep neural networks and the exponential growth of chemical data on which to train these networks on, we anticipate that deep learning algorithms will be a useful tool and may grow into a pivotal role for various challenges in the computational chemistry field.« less

Rapid and accurate intraoperative pathological diagnosis by artificial intelligence with deep learning technology.

PubMed

Zhang, Jing; Song, Yanlin; Xia, Fan; Zhu, Chenjing; Zhang, Yingying; Song, Wenpeng; Xu, Jianguo; Ma, Xuelei

2017-09-01

Frozen section is widely used for intraoperative pathological diagnosis (IOPD), which is essential for intraoperative decision making. However, frozen section suffers from some drawbacks, such as time consuming and high misdiagnosis rate. Recently, artificial intelligence (AI) with deep learning technology has shown bright future in medicine. We hypothesize that AI with deep learning technology could help IOPD, with a computer trained by a dataset of intraoperative lesion images. Evidences supporting our hypothesis included the successful use of AI with deep learning technology in diagnosing skin cancer, and the developed method of deep-learning algorithm. Large size of the training dataset is critical to increase the diagnostic accuracy. The performance of the trained machine could be tested by new images before clinical use. Real-time diagnosis, easy to use and potential high accuracy were the advantages of AI for IOPD. In sum, AI with deep learning technology is a promising method to help rapid and accurate IOPD. Copyright © 2017 Elsevier Ltd. All rights reserved.

Automated analysis of high-content microscopy data with deep learning.

PubMed

Kraus, Oren Z; Grys, Ben T; Ba, Jimmy; Chong, Yolanda; Frey, Brendan J; Boone, Charles; Andrews, Brenda J

2017-04-18

Existing computational pipelines for quantitative analysis of high-content microscopy data rely on traditional machine learning approaches that fail to accurately classify more than a single dataset without substantial tuning and training, requiring extensive analysis. Here, we demonstrate that the application of deep learning to biological image data can overcome the pitfalls associated with conventional machine learning classifiers. Using a deep convolutional neural network (DeepLoc) to analyze yeast cell images, we show improved performance over traditional approaches in the automated classification of protein subcellular localization. We also demonstrate the ability of DeepLoc to classify highly divergent image sets, including images of pheromone-arrested cells with abnormal cellular morphology, as well as images generated in different genetic backgrounds and in different laboratories. We offer an open-source implementation that enables updating DeepLoc on new microscopy datasets. This study highlights deep learning as an important tool for the expedited analysis of high-content microscopy data. © 2017 The Authors. Published under the terms of the CC BY 4.0 license.

Enhancing Hi-C data resolution with deep convolutional neural network HiCPlus.

PubMed

Zhang, Yan; An, Lin; Xu, Jie; Zhang, Bo; Zheng, W Jim; Hu, Ming; Tang, Jijun; Yue, Feng

2018-02-21

Although Hi-C technology is one of the most popular tools for studying 3D genome organization, due to sequencing cost, the resolution of most Hi-C datasets are coarse and cannot be used to link distal regulatory elements to their target genes. Here we develop HiCPlus, a computational approach based on deep convolutional neural network, to infer high-resolution Hi-C interaction matrices from low-resolution Hi-C data. We demonstrate that HiCPlus can impute interaction matrices highly similar to the original ones, while only using 1/16 of the original sequencing reads. We show that the models learned from one cell type can be applied to make predictions in other cell or tissue types. Our work not only provides a computational framework to enhance Hi-C data resolution but also reveals features underlying the formation of 3D chromatin interactions.

Benchmarking Deep Learning Models on Large Healthcare Datasets.

PubMed

Purushotham, Sanjay; Meng, Chuizheng; Che, Zhengping; Liu, Yan

2018-06-04

Deep learning models (aka Deep Neural Networks) have revolutionized many fields including computer vision, natural language processing, speech recognition, and is being increasingly used in clinical healthcare applications. However, few works exist which have benchmarked the performance of the deep learning models with respect to the state-of-the-art machine learning models and prognostic scoring systems on publicly available healthcare datasets. In this paper, we present the benchmarking results for several clinical prediction tasks such as mortality prediction, length of stay prediction, and ICD-9 code group prediction using Deep Learning models, ensemble of machine learning models (Super Learner algorithm), SAPS II and SOFA scores. We used the Medical Information Mart for Intensive Care III (MIMIC-III) (v1.4) publicly available dataset, which includes all patients admitted to an ICU at the Beth Israel Deaconess Medical Center from 2001 to 2012, for the benchmarking tasks. Our results show that deep learning models consistently outperform all the other approaches especially when the 'raw' clinical time series data is used as input features to the models. Copyright © 2018 Elsevier Inc. All rights reserved.

A Robust Deep Model for Improved Classification of AD/MCI Patients

PubMed Central

Li, Feng; Tran, Loc; Thung, Kim-Han; Ji, Shuiwang; Shen, Dinggang; Li, Jiang

2015-01-01

Accurate classification of Alzheimer’s Disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI), plays a critical role in possibly preventing progression of memory impairment and improving quality of life for AD patients. Among many research tasks, it is of particular interest to identify noninvasive imaging biomarkers for AD diagnosis. In this paper, we present a robust deep learning system to identify different progression stages of AD patients based on MRI and PET scans. We utilized the dropout technique to improve classical deep learning by preventing its weight co-adaptation, which is a typical cause of over-fitting in deep learning. In addition, we incorporated stability selection, an adaptive learning factor, and a multi-task learning strategy into the deep learning framework. We applied the proposed method to the ADNI data set and conducted experiments for AD and MCI conversion diagnosis. Experimental results showed that the dropout technique is very effective in AD diagnosis, improving the classification accuracies by 5.9% on average as compared to the classical deep learning methods. PMID:25955998

Self-Paced Prioritized Curriculum Learning With Coverage Penalty in Deep Reinforcement Learning.

PubMed

Ren, Zhipeng; Dong, Daoyi; Li, Huaxiong; Chen, Chunlin; Zhipeng Ren; Daoyi Dong; Huaxiong Li; Chunlin Chen; Dong, Daoyi; Li, Huaxiong; Chen, Chunlin; Ren, Zhipeng

2018-06-01

In this paper, a new training paradigm is proposed for deep reinforcement learning using self-paced prioritized curriculum learning with coverage penalty. The proposed deep curriculum reinforcement learning (DCRL) takes the most advantage of experience replay by adaptively selecting appropriate transitions from replay memory based on the complexity of each transition. The criteria of complexity in DCRL consist of self-paced priority as well as coverage penalty. The self-paced priority reflects the relationship between the temporal-difference error and the difficulty of the current curriculum for sample efficiency. The coverage penalty is taken into account for sample diversity. With comparison to deep Q network (DQN) and prioritized experience replay (PER) methods, the DCRL algorithm is evaluated on Atari 2600 games, and the experimental results show that DCRL outperforms DQN and PER on most of these games. More results further show that the proposed curriculum training paradigm of DCRL is also applicable and effective for other memory-based deep reinforcement learning approaches, such as double DQN and dueling network. All the experimental results demonstrate that DCRL can achieve improved training efficiency and robustness for deep reinforcement learning.

Opportunities and obstacles for deep learning in biology and medicine.

PubMed

Ching, Travers; Himmelstein, Daniel S; Beaulieu-Jones, Brett K; Kalinin, Alexandr A; Do, Brian T; Way, Gregory P; Ferrero, Enrico; Agapow, Paul-Michael; Zietz, Michael; Hoffman, Michael M; Xie, Wei; Rosen, Gail L; Lengerich, Benjamin J; Israeli, Johnny; Lanchantin, Jack; Woloszynek, Stephen; Carpenter, Anne E; Shrikumar, Avanti; Xu, Jinbo; Cofer, Evan M; Lavender, Christopher A; Turaga, Srinivas C; Alexandari, Amr M; Lu, Zhiyong; Harris, David J; DeCaprio, Dave; Qi, Yanjun; Kundaje, Anshul; Peng, Yifan; Wiley, Laura K; Segler, Marwin H S; Boca, Simina M; Swamidass, S Joshua; Huang, Austin; Gitter, Anthony; Greene, Casey S

2018-04-01

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine. © 2018 The Authors.

Opportunities and obstacles for deep learning in biology and medicine

PubMed Central

2018-01-01

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems—patient classification, fundamental biological processes and treatment of patients—and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine. PMID:29618526

Unsupervised deep learning reveals prognostically relevant subtypes of glioblastoma.

PubMed

Young, Jonathan D; Cai, Chunhui; Lu, Xinghua

2017-10-03

One approach to improving the personalized treatment of cancer is to understand the cellular signaling transduction pathways that cause cancer at the level of the individual patient. In this study, we used unsupervised deep learning to learn the hierarchical structure within cancer gene expression data. Deep learning is a group of machine learning algorithms that use multiple layers of hidden units to capture hierarchically related, alternative representations of the input data. We hypothesize that this hierarchical structure learned by deep learning will be related to the cellular signaling system. Robust deep learning model selection identified a network architecture that is biologically plausible. Our model selection results indicated that the 1st hidden layer of our deep learning model should contain about 1300 hidden units to most effectively capture the covariance structure of the input data. This agrees with the estimated number of human transcription factors, which is approximately 1400. This result lends support to our hypothesis that the 1st hidden layer of a deep learning model trained on gene expression data may represent signals related to transcription factor activation. Using the 3rd hidden layer representation of each tumor as learned by our unsupervised deep learning model, we performed consensus clustering on all tumor samples-leading to the discovery of clusters of glioblastoma multiforme with differential survival. One of these clusters contained all of the glioblastoma samples with G-CIMP, a known methylation phenotype driven by the IDH1 mutation and associated with favorable prognosis, suggesting that the hidden units in the 3rd hidden layer representations captured a methylation signal without explicitly using methylation data as input. We also found differentially expressed genes and well-known mutations (NF1, IDH1, EGFR) that were uniquely correlated with each of these clusters. Exploring these unique genes and mutations will allow us to further investigate the disease mechanisms underlying each of these clusters. In summary, we show that a deep learning model can be trained to represent biologically and clinically meaningful abstractions of cancer gene expression data. Understanding what additional relationships these hidden layer abstractions have with the cancer cellular signaling system could have a significant impact on the understanding and treatment of cancer.

Ferengi Business Practices in "Star Trek: Deep Space Nine"--To Enhance Student Engagement and Teach a Wide Range of Business Concepts

ERIC Educational Resources Information Center

Lopez, Katherine J.; Pletcher, Gary; Williams, Craig L.; Zehner, William Bradley, II

2017-01-01

The purpose of this article is to provide examples of business concepts appearing in science fiction, offering accounting and business educators a means to engage students and allow students to make connections with business concepts outside of the strict business realm, resulting in increased long-term learning. To accomplish this, the "Star…

Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review.

PubMed

Xiao, Cao; Choi, Edward; Sun, Jimeng

2018-06-08

To conduct a systematic review of deep learning models for electronic health record (EHR) data, and illustrate various deep learning architectures for analyzing different data sources and their target applications. We also highlight ongoing research and identify open challenges in building deep learning models of EHRs. We searched PubMed and Google Scholar for papers on deep learning studies using EHR data published between January 1, 2010, and January 31, 2018. We summarize them according to these axes: types of analytics tasks, types of deep learning model architectures, special challenges arising from health data and tasks and their potential solutions, as well as evaluation strategies. We surveyed and analyzed multiple aspects of the 98 articles we found and identified the following analytics tasks: disease detection/classification, sequential prediction of clinical events, concept embedding, data augmentation, and EHR data privacy. We then studied how deep architectures were applied to these tasks. We also discussed some special challenges arising from modeling EHR data and reviewed a few popular approaches. Finally, we summarized how performance evaluations were conducted for each task. Despite the early success in using deep learning for health analytics applications, there still exist a number of issues to be addressed. We discuss them in detail including data and label availability, the interpretability and transparency of the model, and ease of deployment.

Learning Deep Representations for Ground to Aerial Geolocalization (Open Access)

DTIC Science & Technology

2015-10-15

proposed approach, Where-CNN, is inspired by deep learning success in face verification and achieves significant improvements over tra- ditional hand...crafted features and existing deep features learned from other large-scale databases. We show the ef- fectiveness of Where-CNN in finding matches

Do Students Develop towards More Deep Approaches to Learning during Studies? A Systematic Review on the Development of Students' Deep and Surface Approaches to Learning in Higher Education

ERIC Educational Resources Information Center

Asikainen, Henna; Gijbels, David

2017-01-01

The focus of the present paper is on the contribution of the research in the student approaches to learning tradition. Several studies in this field have started from the assumption that students' approaches to learning develop towards more deep approaches to learning in higher education. This paper reports on a systematic review of longitudinal…

Machine Learning, deep learning and optimization in computer vision

NASA Astrophysics Data System (ADS)

Canu, Stéphane

2017-03-01

As quoted in the Large Scale Computer Vision Systems NIPS workshop, computer vision is a mature field with a long tradition of research, but recent advances in machine learning, deep learning, representation learning and optimization have provided models with new capabilities to better understand visual content. The presentation will go through these new developments in machine learning covering basic motivations, ideas, models and optimization in deep learning for computer vision, identifying challenges and opportunities. It will focus on issues related with large scale learning that is: high dimensional features, large variety of visual classes, and large number of examples.

Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines

PubMed Central

Neftci, Emre O.; Augustine, Charles; Paul, Somnath; Detorakis, Georgios

2017-01-01

An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful approach is to take inspiration from inference and learning algorithms used in deep neural networks. However, the workhorse of deep learning, the gradient descent Gradient Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory during learning, and precise operations that are difficult to realize in neuromorphic hardware. Remarkably, recent work showed that exact backpropagated gradients are not essential for learning deep representations. Building on these results, we demonstrate an event-driven random BP (eRBP) rule that uses an error-modulated synaptic plasticity for learning deep representations. Using a two-compartment Leaky Integrate & Fire (I&F) neuron, the rule requires only one addition and two comparisons for each synaptic weight, making it very suitable for implementation in digital or mixed-signal neuromorphic hardware. Our results show that using eRBP, deep representations are rapidly learned, achieving classification accuracies on permutation invariant datasets comparable to those obtained in artificial neural network simulations on GPUs, while being robust to neural and synaptic state quantizations during learning. PMID:28680387

Event-Driven Random Back-Propagation: Enabling Neuromorphic Deep Learning Machines.

PubMed

Neftci, Emre O; Augustine, Charles; Paul, Somnath; Detorakis, Georgios

2017-01-01

An ongoing challenge in neuromorphic computing is to devise general and computationally efficient models of inference and learning which are compatible with the spatial and temporal constraints of the brain. One increasingly popular and successful approach is to take inspiration from inference and learning algorithms used in deep neural networks. However, the workhorse of deep learning, the gradient descent Gradient Back Propagation (BP) rule, often relies on the immediate availability of network-wide information stored with high-precision memory during learning, and precise operations that are difficult to realize in neuromorphic hardware. Remarkably, recent work showed that exact backpropagated gradients are not essential for learning deep representations. Building on these results, we demonstrate an event-driven random BP (eRBP) rule that uses an error-modulated synaptic plasticity for learning deep representations. Using a two-compartment Leaky Integrate & Fire (I&F) neuron, the rule requires only one addition and two comparisons for each synaptic weight, making it very suitable for implementation in digital or mixed-signal neuromorphic hardware. Our results show that using eRBP, deep representations are rapidly learned, achieving classification accuracies on permutation invariant datasets comparable to those obtained in artificial neural network simulations on GPUs, while being robust to neural and synaptic state quantizations during learning.

Is the Cognitive Complexity of Commitment-to-Change Statements Associated With Change in Clinical Practice? An Application of Bloom's Taxonomy.

PubMed

Armson, Heather; Elmslie, Tom; Roder, Stefanie; Wakefield, Jacqueline

2015-01-01

This study categorizes 4 practice change options, including commitment-to-change (CTC) statements using Bloom's taxonomy to explore the relationship between a hierarchy of CTC statements and implementation of changes in practice. Our hypothesis was that deeper learning would be positively associated with implementation of planned practice changes. Thirty-five family physicians were recruited from existing practice-based small learning groups. They were asked to use their usual small-group process while exploring an educational module on peripheral neuropathy. Part of this process included the completion of a practice reflection tool (PRT) that incorporates CTC statements containing a broader set of practice change options-considering change, confirmation of practice, and not convinced a change is needed ("enhanced" CTC). The statements were categorized using Bloom's taxonomy and then compared to reported practice implementation after 3 months. Nearly all participants made a CTC statement and successful practice implementation at 3 months. By using the "enhanced" CTC options, additional components that contribute to practice change were captured. Unanticipated changes accounted for one-third of all successful changes. Categorizing statements on the PRT using Bloom's taxonomy highlighted the progression from knowledge/comprehension to application/analysis to synthesis/evaluation. All PRT statements were classified in the upper 2 levels of the taxonomy, and these higher-level (deep learning) statements were related to higher levels of practice implementation. The "enhanced" CTC options captured changes that would not otherwise be identified and may be worthy of further exploration in other CME activities. Using Bloom's taxonomy to code the PRT statements proved useful in highlighting the progression through increasing levels of cognitive complexity-reflecting deep learning. © 2015 The Alliance for Continuing Education in the Health Professions, the Society for Academic Continuing Medical Education, and the Council on Continuing Medical Education, Association for Hospital Medical Education.

A Deep Learning Method to Automatically Identify Reports of Scientifically Rigorous Clinical Research from the Biomedical Literature: Comparative Analytic Study.

PubMed

Del Fiol, Guilherme; Michelson, Matthew; Iorio, Alfonso; Cotoi, Chris; Haynes, R Brian

2018-06-25

A major barrier to the practice of evidence-based medicine is efficiently finding scientifically sound studies on a given clinical topic. To investigate a deep learning approach to retrieve scientifically sound treatment studies from the biomedical literature. We trained a Convolutional Neural Network using a noisy dataset of 403,216 PubMed citations with title and abstract as features. The deep learning model was compared with state-of-the-art search filters, such as PubMed's Clinical Query Broad treatment filter, McMaster's textword search strategy (no Medical Subject Heading, MeSH, terms), and Clinical Query Balanced treatment filter. A previously annotated dataset (Clinical Hedges) was used as the gold standard. The deep learning model obtained significantly lower recall than the Clinical Queries Broad treatment filter (96.9% vs 98.4%; P<.001); and equivalent recall to McMaster's textword search (96.9% vs 97.1%; P=.57) and Clinical Queries Balanced filter (96.9% vs 97.0%; P=.63). Deep learning obtained significantly higher precision than the Clinical Queries Broad filter (34.6% vs 22.4%; P<.001) and McMaster's textword search (34.6% vs 11.8%; P<.001), but was significantly lower than the Clinical Queries Balanced filter (34.6% vs 40.9%; P<.001). Deep learning performed well compared to state-of-the-art search filters, especially when citations were not indexed. Unlike previous machine learning approaches, the proposed deep learning model does not require feature engineering, or time-sensitive or proprietary features, such as MeSH terms and bibliometrics. Deep learning is a promising approach to identifying reports of scientifically rigorous clinical research. Further work is needed to optimize the deep learning model and to assess generalizability to other areas, such as diagnosis, etiology, and prognosis. ©Guilherme Del Fiol, Matthew Michelson, Alfonso Iorio, Chris Cotoi, R Brian Haynes. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 25.06.2018.

A Constructivist View of Music Education: Perspectives for Deep Learning

ERIC Educational Resources Information Center

Scott, Sheila

2006-01-01

The article analyzes a constructivist view of music education. A constructivist music classroom exemplifies deep learning when students formulate questions, acquire new knowledge by developing and implementing plans for investigating these questions, and reflect on the results. A context for deep learning requires that teachers and students work…

Active semi-supervised learning method with hybrid deep belief networks.

PubMed

Zhou, Shusen; Chen, Qingcai; Wang, Xiaolong

2014-01-01

In this paper, we develop a novel semi-supervised learning algorithm called active hybrid deep belief networks (AHD), to address the semi-supervised sentiment classification problem with deep learning. First, we construct the previous several hidden layers using restricted Boltzmann machines (RBM), which can reduce the dimension and abstract the information of the reviews quickly. Second, we construct the following hidden layers using convolutional restricted Boltzmann machines (CRBM), which can abstract the information of reviews effectively. Third, the constructed deep architecture is fine-tuned by gradient-descent based supervised learning with an exponential loss function. Finally, active learning method is combined based on the proposed deep architecture. We did several experiments on five sentiment classification datasets, and show that AHD is competitive with previous semi-supervised learning algorithm. Experiments are also conducted to verify the effectiveness of our proposed method with different number of labeled reviews and unlabeled reviews respectively.

Deep dissection: motivating students beyond rote learning in veterinary anatomy.

PubMed

Cake, Martin A

2006-01-01

The profusion of descriptive, factual information in veterinary anatomy inevitably creates pressure on students to employ surface learning approaches and "rote learning." This phenomenon may contribute to negative perceptions of the relevance of anatomy as a discipline. Thus, encouraging deep learning outcomes will not only lead to greater satisfaction for both instructors and learners but may have the added effect of raising the profile of and respect for the discipline. Consideration of the literature reveals the broad scope of interventions required to motivate students to go beyond rote learning. While many of these are common to all disciplines (e.g., promoting active learning, making higher-order goals explicit, reducing content in favor of concepts, aligning assessment with outcomes), other factors are peculiar to anatomy, such as the benefits of incorporating clinical tidbits, "living anatomy," the anatomy museum, and dissection classes into a "learning context" that fosters deep approaches. Surprisingly, the 10 interventions discussed focus more on factors contributing to student perceptions of the course than on drastic changes to the anatomy course itself. This is because many traditional anatomy practices, such as dissection and museum-based classes, are eminently compatible with active, student-centered learning strategies and the adoption of deep learning approaches by veterinary students. Thus the key to encouraging, for example, dissection for deep learning ("deep dissection") lies more in student motivation, personal engagement, curriculum structure, and "learning context" than in the nature of the learning activity itself.

Deep learning based classification for head and neck cancer detection with hyperspectral imaging in an animal model

NASA Astrophysics Data System (ADS)

Ma, Ling; Lu, Guolan; Wang, Dongsheng; Wang, Xu; Chen, Zhuo Georgia; Muller, Susan; Chen, Amy; Fei, Baowei

2017-03-01

Hyperspectral imaging (HSI) is an emerging imaging modality that can provide a noninvasive tool for cancer detection and image-guided surgery. HSI acquires high-resolution images at hundreds of spectral bands, providing big data to differentiating different types of tissue. We proposed a deep learning based method for the detection of head and neck cancer with hyperspectral images. Since the deep learning algorithm can learn the feature hierarchically, the learned features are more discriminative and concise than the handcrafted features. In this study, we adopt convolutional neural networks (CNN) to learn the deep feature of pixels for classifying each pixel into tumor or normal tissue. We evaluated our proposed classification method on the dataset containing hyperspectral images from 12 tumor-bearing mice. Experimental results show that our method achieved an average accuracy of 91.36%. The preliminary study demonstrated that our deep learning method can be applied to hyperspectral images for detecting head and neck tumors in animal models.

Visualizing and enhancing a deep learning framework using patients age and gender for chest x-ray image retrieval

NASA Astrophysics Data System (ADS)

Anavi, Yaron; Kogan, Ilya; Gelbart, Elad; Geva, Ofer; Greenspan, Hayit

2016-03-01

We explore the combination of text metadata, such as patients' age and gender, with image-based features, for X-ray chest pathology image retrieval. We focus on a feature set extracted from a pre-trained deep convolutional network shown in earlier work to achieve state-of-the-art results. Two distance measures are explored: a descriptor-based measure, which computes the distance between image descriptors, and a classification-based measure, which performed by a comparison of the corresponding SVM classification probabilities. We show that retrieval results increase once the age and gender information combined with the features extracted from the last layers of the network, with best results using the classification-based scheme. Visualization of the X-ray data is presented by embedding the high dimensional deep learning features in a 2-D dimensional space while preserving the pairwise distances using the t-SNE algorithm. The 2-D visualization gives the unique ability to find groups of X-ray images that are similar to the query image and among themselves, which is a characteristic we do not see in a 1-D traditional ranking.

The Mediating Effect of Intrinsic Motivation to Learn on the Relationship between Student´s Autonomy Support and Vitality and Deep Learning.

PubMed

Núñez, Juan L; León, Jaime

2016-07-18

Self-determination theory has shown that autonomy support in the classroom is associated with an increase of students' intrinsic motivation. Moreover, intrinsic motivation is related with positive outcomes. This study examines the relationships between autonomy support, intrinsic motivation to learn and two motivational consequences, deep learning and vitality. Specifically, the hypotheses were that autonomy support predicts the two types of consequences, and that autonomy support directly and indirectly predicts the vitality and the deep learning through intrinsic motivation to learn. Participants were 276 undergraduate students. The mean age was 21.80 years (SD = 2.94). Structural equation modeling was used to test the relationships between variables and delta method was used to analyze the mediating effect of intrinsic motivation to learn. Results indicated that student perception of autonomy support had a positive effect on deep learning and vitality (p < .001). In addition, these associations were mediated by intrinsic motivation to learn. These findings suggest that teachers are key elements in generating of autonomy support environment to promote intrinsic motivation, deep learning, and vitality in classroom. Educational implications are discussed.

Deep learning with convolutional neural networks for EEG decoding and visualization

PubMed Central

Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

2017-01-01

Abstract Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end‐to‐end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end‐to‐end EEG analysis, but a better understanding of how to design and train ConvNets for end‐to‐end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task‐related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG‐based brain mapping. Hum Brain Mapp 38:5391–5420, 2017. © 2017 Wiley Periodicals, Inc. PMID:28782865

Deep learning with convolutional neural networks for EEG decoding and visualization.

PubMed

Schirrmeister, Robin Tibor; Springenberg, Jost Tobias; Fiederer, Lukas Dominique Josef; Glasstetter, Martin; Eggensperger, Katharina; Tangermann, Michael; Hutter, Frank; Burgard, Wolfram; Ball, Tonio

2017-11-01

Deep learning with convolutional neural networks (deep ConvNets) has revolutionized computer vision through end-to-end learning, that is, learning from the raw data. There is increasing interest in using deep ConvNets for end-to-end EEG analysis, but a better understanding of how to design and train ConvNets for end-to-end EEG decoding and how to visualize the informative EEG features the ConvNets learn is still needed. Here, we studied deep ConvNets with a range of different architectures, designed for decoding imagined or executed tasks from raw EEG. Our results show that recent advances from the machine learning field, including batch normalization and exponential linear units, together with a cropped training strategy, boosted the deep ConvNets decoding performance, reaching at least as good performance as the widely used filter bank common spatial patterns (FBCSP) algorithm (mean decoding accuracies 82.1% FBCSP, 84.0% deep ConvNets). While FBCSP is designed to use spectral power modulations, the features used by ConvNets are not fixed a priori. Our novel methods for visualizing the learned features demonstrated that ConvNets indeed learned to use spectral power modulations in the alpha, beta, and high gamma frequencies, and proved useful for spatially mapping the learned features by revealing the topography of the causal contributions of features in different frequency bands to the decoding decision. Our study thus shows how to design and train ConvNets to decode task-related information from the raw EEG without handcrafted features and highlights the potential of deep ConvNets combined with advanced visualization techniques for EEG-based brain mapping. Hum Brain Mapp 38:5391-5420, 2017. © 2017 Wiley Periodicals, Inc. © 2017 The Authors Human Brain Mapping Published by Wiley Periodicals, Inc.

Task- and self-related pathways to deep learning: the mediating role of achievement goals, classroom attentiveness, and group participation.

PubMed

Lau, Shun; Liem, Arief Darmanegara; Nie, Youyan

2008-12-01

The expectancy-value and achievement goal theories are arguably the two most dominant theories of achievement motivation in the contemporary literature. However, very few studies have examined how the constructs derived from both theories are related to deep learning. Moreover, although there is evidence demonstrating the links between achievement goals and deep learning, little research has examined the mediating processes involved. The aims of this research were to: (a) investigate the role of task- and self-related beliefs (task value and self-efficacy) as well as achievement goals in predicting deep learning in mathematics and (b) examine how classroom attentiveness and group participation mediated the relations between achievement goals and deep learning. The sample comprised 1,476 Grade-9 students from 39 schools in Singapore. Students' self-efficacy, task value, achievement goals, classroom attentiveness, group participation, and deep learning in mathematics were assessed by a self-reported questionnaire administered on-line. Structural equation modelling was performed to test the hypothesized model linking these variables. Task value was predictive of task-related achievement goals whereas self-efficacy was predictive of task-approach, performance-approach, and performance-avoidance goals. Achievement goals were found to fully mediate the relations between task value and self-efficacy on the one hand, and classroom attentiveness, group participation, and deep learning on the other. Classroom attentiveness and group participation partially mediated the relations between achievement goal adoption and deep learning. The findings suggest that (a) task- and self-related pathways are two possible routes through which students could be motivated to learn and (b) like task-approach goals, performance-approach goals could lead to adaptive processes and outcomes.

Music mnemonics aid Verbal Memory and Induce Learning – Related Brain Plasticity in Multiple Sclerosis

PubMed Central

Thaut, Michael H.; Peterson, David A.; McIntosh, Gerald C.; Hoemberg, Volker

2014-01-01

Recent research on music and brain function has suggested that the temporal pattern structure in music and rhythm can enhance cognitive functions. To further elucidate this question specifically for memory, we investigated if a musical template can enhance verbal learning in patients with multiple sclerosis (MS) and if music-assisted learning will also influence short-term, system-level brain plasticity. We measured systems-level brain activity with oscillatory network synchronization during music-assisted learning. Specifically, we measured the spectral power of 128-channel electroencephalogram (EEG) in alpha and beta frequency bands in 54 patients with MS. The study sample was randomly divided into two groups, either hearing a spoken or a musical (sung) presentation of Rey’s auditory verbal learning test. We defined the “learning-related synchronization” (LRS) as the percent change in EEG spectral power from the first time the word was presented to the average of the subsequent word encoding trials. LRS differed significantly between the music and the spoken conditions in low alpha and upper beta bands. Patients in the music condition showed overall better word memory and better word order memory and stronger bilateral frontal alpha LRS than patients in the spoken condition. The evidence suggests that a musical mnemonic recruits stronger oscillatory network synchronization in prefrontal areas in MS patients during word learning. It is suggested that the temporal structure implicit in musical stimuli enhances “deep encoding” during verbal learning and sharpens the timing of neural dynamics in brain networks degraded by demyelination in MS. PMID:24982626

Factors Contributing to Changes in a Deep Approach to Learning in Different Learning Environments

ERIC Educational Resources Information Center

Postareff, Liisa; Parpala, Anna; Lindblom-Ylänne, Sari

2015-01-01

The study explored factors explaining changes in a deep approach to learning. The data consisted of interviews with 12 students from four Bachelor-level courses representing different disciplines. We analysed and compared descriptions of students whose deep approach either increased, decreased or remained relatively unchanged during their courses.…

Deep learning aided decision support for pulmonary nodules diagnosing: a review.

PubMed

Yang, Yixin; Feng, Xiaoyi; Chi, Wenhao; Li, Zhengyang; Duan, Wenzhe; Liu, Haiping; Liang, Wenhua; Wang, Wei; Chen, Ping; He, Jianxing; Liu, Bo

2018-04-01

Deep learning techniques have recently emerged as promising decision supporting approaches to automatically analyze medical images for different clinical diagnosing purposes. Diagnosing of pulmonary nodules by using computer-assisted diagnosing has received considerable theoretical, computational, and empirical research work, and considerable methods have been developed for detection and classification of pulmonary nodules on different formats of images including chest radiographs, computed tomography (CT), and positron emission tomography in the past five decades. The recent remarkable and significant progress in deep learning for pulmonary nodules achieved in both academia and the industry has demonstrated that deep learning techniques seem to be promising alternative decision support schemes to effectively tackle the central issues in pulmonary nodules diagnosing, including feature extraction, nodule detection, false-positive reduction, and benign-malignant classification for the huge volume of chest scan data. The main goal of this investigation is to provide a comprehensive state-of-the-art review of the deep learning aided decision support for pulmonary nodules diagnosing. As far as the authors know, this is the first time that a review is devoted exclusively to deep learning techniques for pulmonary nodules diagnosing.

Application of Deep Learning in Automated Analysis of Molecular Images in Cancer: A Survey

PubMed Central

Xue, Yong; Chen, Shihui; Liu, Yong

2017-01-01

Molecular imaging enables the visualization and quantitative analysis of the alterations of biological procedures at molecular and/or cellular level, which is of great significance for early detection of cancer. In recent years, deep leaning has been widely used in medical imaging analysis, as it overcomes the limitations of visual assessment and traditional machine learning techniques by extracting hierarchical features with powerful representation capability. Research on cancer molecular images using deep learning techniques is also increasing dynamically. Hence, in this paper, we review the applications of deep learning in molecular imaging in terms of tumor lesion segmentation, tumor classification, and survival prediction. We also outline some future directions in which researchers may develop more powerful deep learning models for better performance in the applications in cancer molecular imaging. PMID:29114182

Enhancing SDO/HMI images using deep learning

NASA Astrophysics Data System (ADS)

Baso, C. J. Díaz; Ramos, A. Asensio

2018-06-01

Context. The Helioseismic and Magnetic Imager (HMI) provides continuum images and magnetograms with a cadence better than one per minute. It has been continuously observing the Sun 24 h a day for the past 7 yr. The trade-off between full disk observations and spatial resolution means that HMI is not adequate for analyzing the smallest-scale events in the solar atmosphere. Aims: Our aim is to develop a new method to enhance HMI data, simultaneously deconvolving and super-resolving images and magnetograms. The resulting images will mimic observations with a diffraction-limited telescope twice the diameter of HMI. Methods: Our method, which we call Enhance, is based on two deep, fully convolutional neural networks that input patches of HMI observations and output deconvolved and super-resolved data. The neural networks are trained on synthetic data obtained from simulations of the emergence of solar active regions. Results: We have obtained deconvolved and super-resolved HMI images. To solve this ill-defined problem with infinite solutions we have used a neural network approach to add prior information from the simulations. We test Enhance against Hinode data that has been degraded to a 28 cm diameter telescope showing very good consistency. The code is open source.

E pluribus unum: the potential of collaborative learning to enhance Microbiology teaching in higher education.

PubMed

Rutherford, Stephen

2015-12-01

Collaborative learning, where students work together towards a shared understanding of a concept, is a well-established pedagogy, and one which has great potential for higher education (HE). Through discussion and challenging each other's ideas, learners gain a richer appreciation for a subject than with solitary study or didactic teaching methods. However, collaborative learning does require some scaffolding by the teacher in order to be successful. Collaborative learning can be augmented by the use of Web 2.0 collaborative technologies, such as wikis, blogs and social media. This article reviews some of the uses of collaborative learning strategies in Microbiology teaching in HE. Despite the great potential of collaborative learning, evidence of its use in Microbiology teaching is, to date, limited. But the potential for collaborative learning approaches to develop self-regulated, deep learners is considerable, and so collaborative learning should be considered strongly as a viable pedagogy for HE. © FEMS 2015. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Developing Deep Learning Applications for Life Science and Pharma Industry.

PubMed

Siegismund, Daniel; Tolkachev, Vasily; Heyse, Stephan; Sick, Beate; Duerr, Oliver; Steigele, Stephan

2018-06-01

Deep Learning has boosted artificial intelligence over the past 5 years and is seen now as one of the major technological innovation areas, predicted to replace lots of repetitive, but complex tasks of human labor within the next decade. It is also expected to be 'game changing' for research activities in pharma and life sciences, where large sets of similar yet complex data samples are systematically analyzed. Deep learning is currently conquering formerly expert domains especially in areas requiring perception, previously not amenable to standard machine learning. A typical example is the automated analysis of images which are typically produced en-masse in many domains, e. g., in high-content screening or digital pathology. Deep learning enables to create competitive applications in so-far defined core domains of 'human intelligence'. Applications of artificial intelligence have been enabled in recent years by (i) the massive availability of data samples, collected in pharma driven drug programs (='big data') as well as (ii) deep learning algorithmic advancements and (iii) increase in compute power. Such applications are based on software frameworks with specific strengths and weaknesses. Here, we introduce typical applications and underlying frameworks for deep learning with a set of practical criteria for developing production ready solutions in life science and pharma research. Based on our own experience in successfully developing deep learning applications we provide suggestions and a baseline for selecting the most suited frameworks for a future-proof and cost-effective development. © Georg Thieme Verlag KG Stuttgart · New York.

A Deep Learning Approach to on-Node Sensor Data Analytics for Mobile or Wearable Devices.

PubMed

Ravi, Daniele; Wong, Charence; Lo, Benny; Yang, Guang-Zhong

2017-01-01

The increasing popularity of wearable devices in recent years means that a diverse range of physiological and functional data can now be captured continuously for applications in sports, wellbeing, and healthcare. This wealth of information requires efficient methods of classification and analysis where deep learning is a promising technique for large-scale data analytics. While deep learning has been successful in implementations that utilize high-performance computing platforms, its use on low-power wearable devices is limited by resource constraints. In this paper, we propose a deep learning methodology, which combines features learned from inertial sensor data together with complementary information from a set of shallow features to enable accurate and real-time activity classification. The design of this combined method aims to overcome some of the limitations present in a typical deep learning framework where on-node computation is required. To optimize the proposed method for real-time on-node computation, spectral domain preprocessing is used before the data are passed onto the deep learning framework. The classification accuracy of our proposed deep learning approach is evaluated against state-of-the-art methods using both laboratory and real world activity datasets. Our results show the validity of the approach on different human activity datasets, outperforming other methods, including the two methods used within our combined pipeline. We also demonstrate that the computation times for the proposed method are consistent with the constraints of real-time on-node processing on smartphones and a wearable sensor platform.

Robotic astrobiology - prospects for enhancing scientific productivity of mars rover missions

NASA Astrophysics Data System (ADS)

Ellery, A. A.

2018-07-01

Robotic astrobiology involves the remote projection of intelligent capabilities to planetary missions in the search for life, preferably with human-level intelligence. Planetary rovers would be true human surrogates capable of sophisticated decision-making to enhance their scientific productivity. We explore several key aspects of this capability: (i) visual texture analysis of rocks to enable their geological classification and so, astrobiological potential; (ii) serendipitous target acquisition whilst on the move; (iii) continuous extraction of regolith properties, including water ice whilst on the move; and (iv) deep learning-capable Bayesian net expert systems. Individually, these capabilities will provide enhanced scientific return for astrobiology missions, but together, they will provide full autonomous science capability.

Deep-learning derived features for lung nodule classification with limited datasets

NASA Astrophysics Data System (ADS)

Thammasorn, P.; Wu, W.; Pierce, L. A.; Pipavath, S. N.; Lampe, P. D.; Houghton, A. M.; Haynor, D. R.; Chaovalitwongse, W. A.; Kinahan, P. E.

2018-02-01

Only a few percent of indeterminate nodules found in lung CT images are cancer. However, enabling earlier diagnosis is important to avoid invasive procedures or long-time surveillance to those benign nodules. We are evaluating a classification framework using radiomics features derived with a machine learning approach from a small data set of indeterminate CT lung nodule images. We used a retrospective analysis of 194 cases with pulmonary nodules in the CT images with or without contrast enhancement from lung cancer screening clinics. The nodules were contoured by a radiologist and texture features of the lesion were calculated. In addition, sematic features describing shape were categorized. We also explored a Multiband network, a feature derivation path that uses a modified convolutional neural network (CNN) with a Triplet Network. This was trained to create discriminative feature representations useful for variable-sized nodule classification. The diagnostic accuracy was evaluated for multiple machine learning algorithms using texture, shape, and CNN features. In the CT contrast-enhanced group, the texture or semantic shape features yielded an overall diagnostic accuracy of 80%. Use of a standard deep learning network in the framework for feature derivation yielded features that substantially underperformed compared to texture and/or semantic features. However, the proposed Multiband approach of feature derivation produced results similar in diagnostic accuracy to the texture and semantic features. While the Multiband feature derivation approach did not outperform the texture and/or semantic features, its equivalent performance indicates promise for future improvements to increase diagnostic accuracy. Importantly, the Multiband approach adapts readily to different size lesions without interpolation, and performed well with relatively small amount of training data.

Deep Learning to Predict Falls in Older Adults Based on Daily-Life Trunk Accelerometry.

PubMed

Nait Aicha, Ahmed; Englebienne, Gwenn; van Schooten, Kimberley S; Pijnappels, Mirjam; Kröse, Ben

2018-05-22

Early detection of high fall risk is an essential component of fall prevention in older adults. Wearable sensors can provide valuable insight into daily-life activities; biomechanical features extracted from such inertial data have been shown to be of added value for the assessment of fall risk. Body-worn sensors such as accelerometers can provide valuable insight into fall risk. Currently, biomechanical features derived from accelerometer data are used for the assessment of fall risk. Here, we studied whether deep learning methods from machine learning are suited to automatically derive features from raw accelerometer data that assess fall risk. We used an existing dataset of 296 older adults. We compared the performance of three deep learning model architectures (convolutional neural network (CNN), long short-term memory (LSTM) and a combination of these two (ConvLSTM)) to each other and to a baseline model with biomechanical features on the same dataset. The results show that the deep learning models in a single-task learning mode are strong in recognition of identity of the subject, but that these models only slightly outperform the baseline method on fall risk assessment. When using multi-task learning, with gender and age as auxiliary tasks, deep learning models perform better. We also found that preprocessing of the data resulted in the best performance (AUC = 0.75). We conclude that deep learning models, and in particular multi-task learning, effectively assess fall risk on the basis of wearable sensor data.

Deep Learning to Predict Falls in Older Adults Based on Daily-Life Trunk Accelerometry

PubMed Central

Englebienne, Gwenn; Pijnappels, Mirjam

2018-01-01

Early detection of high fall risk is an essential component of fall prevention in older adults. Wearable sensors can provide valuable insight into daily-life activities; biomechanical features extracted from such inertial data have been shown to be of added value for the assessment of fall risk. Body-worn sensors such as accelerometers can provide valuable insight into fall risk. Currently, biomechanical features derived from accelerometer data are used for the assessment of fall risk. Here, we studied whether deep learning methods from machine learning are suited to automatically derive features from raw accelerometer data that assess fall risk. We used an existing dataset of 296 older adults. We compared the performance of three deep learning model architectures (convolutional neural network (CNN), long short-term memory (LSTM) and a combination of these two (ConvLSTM)) to each other and to a baseline model with biomechanical features on the same dataset. The results show that the deep learning models in a single-task learning mode are strong in recognition of identity of the subject, but that these models only slightly outperform the baseline method on fall risk assessment. When using multi-task learning, with gender and age as auxiliary tasks, deep learning models perform better. We also found that preprocessing of the data resulted in the best performance (AUC = 0.75). We conclude that deep learning models, and in particular multi-task learning, effectively assess fall risk on the basis of wearable sensor data. PMID:29786659

Preferences for Deep-Surface Learning: A Vocational Education Case Study Using a Multimedia Assessment Activity

ERIC Educational Resources Information Center

Hamm, Simon; Robertson, Ian

2010-01-01

This research tests the proposition that the integration of a multimedia assessment activity into a Diploma of Events Management program promotes a deep learning approach. Firstly, learners' preferences for deep or surface learning were evaluated using the revised two-factor Study Process Questionnaire. Secondly, after completion of an assessment…

Digitally Inspired Thinking: Can Social Media Lead to Deep Learning in Higher Education?

ERIC Educational Resources Information Center

Samuels-Peretz, Debbie; Dvorkin Camiel, Lana; Teeley, Karen; Banerjee, Gouri

2017-01-01

In this study, students from a variety of disciplines, who were enrolled in six courses that incorporate the use of social media, were surveyed to evaluate their perception of how the integration of social-media tools supports deep approaches to learning. Students reported that social media supports deep learning both directly and indirectly,…

Moving beyond the Deep and Surface Dichotomy; Using Q Methodology to Explore Students' Approaches to Studying

ERIC Educational Resources Information Center

Godor, Brian P.

2016-01-01

Student learning approaches research has been built upon the notions of deep and surface learning. Despite its status as part of the educational research canon, the dichotomy of deep/surface has been critiqued as constraining the debate surrounding student learning. Additionally, issues of content validity have been expressed concerning…

White blood cells identification system based on convolutional deep neural learning networks.

PubMed

Shahin, A I; Guo, Yanhui; Amin, K M; Sharawi, Amr A

2017-11-16

White blood cells (WBCs) differential counting yields valued information about human health and disease. The current developed automated cell morphology equipments perform differential count which is based on blood smear image analysis. Previous identification systems for WBCs consist of successive dependent stages; pre-processing, segmentation, feature extraction, feature selection, and classification. There is a real need to employ deep learning methodologies so that the performance of previous WBCs identification systems can be increased. Classifying small limited datasets through deep learning systems is a major challenge and should be investigated. In this paper, we propose a novel identification system for WBCs based on deep convolutional neural networks. Two methodologies based on transfer learning are followed: transfer learning based on deep activation features and fine-tuning of existed deep networks. Deep acrivation featues are extracted from several pre-trained networks and employed in a traditional identification system. Moreover, a novel end-to-end convolutional deep architecture called "WBCsNet" is proposed and built from scratch. Finally, a limited balanced WBCs dataset classification is performed through the WBCsNet as a pre-trained network. During our experiments, three different public WBCs datasets (2551 images) have been used which contain 5 healthy WBCs types. The overall system accuracy achieved by the proposed WBCsNet is (96.1%) which is more than different transfer learning approaches or even the previous traditional identification system. We also present features visualization for the WBCsNet activation which reflects higher response than the pre-trained activated one. a novel WBCs identification system based on deep learning theory is proposed and a high performance WBCsNet can be employed as a pre-trained network. Copyright © 2017. Published by Elsevier B.V.

Survey on deep learning for radiotherapy.

PubMed

Meyer, Philippe; Noblet, Vincent; Mazzara, Christophe; Lallement, Alex

2018-07-01

More than 50% of cancer patients are treated with radiotherapy, either exclusively or in combination with other methods. The planning and delivery of radiotherapy treatment is a complex process, but can now be greatly facilitated by artificial intelligence technology. Deep learning is the fastest-growing field in artificial intelligence and has been successfully used in recent years in many domains, including medicine. In this article, we first explain the concept of deep learning, addressing it in the broader context of machine learning. The most common network architectures are presented, with a more specific focus on convolutional neural networks. We then present a review of the published works on deep learning methods that can be applied to radiotherapy, which are classified into seven categories related to the patient workflow, and can provide some insights of potential future applications. We have attempted to make this paper accessible to both radiotherapy and deep learning communities, and hope that it will inspire new collaborations between these two communities to develop dedicated radiotherapy applications. Copyright © 2018 Elsevier Ltd. All rights reserved.

[Advantages and Application Prospects of Deep Learning in Image Recognition and Bone Age Assessment].

PubMed

Hu, T H; Wan, L; Liu, T A; Wang, M W; Chen, T; Wang, Y H

2017-12-01

Deep learning and neural network models have been new research directions and hot issues in the fields of machine learning and artificial intelligence in recent years. Deep learning has made a breakthrough in the applications of image and speech recognitions, and also has been extensively used in the fields of face recognition and information retrieval because of its special superiority. Bone X-ray images express different variations in black-white-gray gradations, which have image features of black and white contrasts and level differences. Based on these advantages of deep learning in image recognition, we combine it with the research of bone age assessment to provide basic datum for constructing a forensic automatic system of bone age assessment. This paper reviews the basic concept and network architectures of deep learning, and describes its recent research progress on image recognition in different research fields at home and abroad, and explores its advantages and application prospects in bone age assessment. Copyright© by the Editorial Department of Journal of Forensic Medicine.

Deep learning for healthcare applications based on physiological signals: A review.

PubMed

Faust, Oliver; Hagiwara, Yuki; Hong, Tan Jen; Lih, Oh Shu; Acharya, U Rajendra

2018-07-01

We have cast the net into the ocean of knowledge to retrieve the latest scientific research on deep learning methods for physiological signals. We found 53 research papers on this topic, published from 01.01.2008 to 31.12.2017. An initial bibliometric analysis shows that the reviewed papers focused on Electromyogram(EMG), Electroencephalogram(EEG), Electrocardiogram(ECG), and Electrooculogram(EOG). These four categories were used to structure the subsequent content review. During the content review, we understood that deep learning performs better for big and varied datasets than classic analysis and machine classification methods. Deep learning algorithms try to develop the model by using all the available input. This review paper depicts the application of various deep learning algorithms used till recently, but in future it will be used for more healthcare areas to improve the quality of diagnosis. Copyright © 2018 Elsevier B.V. All rights reserved.

Applications of Deep Learning in Biomedicine.

PubMed

Mamoshina, Polina; Vieira, Armando; Putin, Evgeny; Zhavoronkov, Alex

2016-05-02

Increases in throughput and installed base of biomedical research equipment led to a massive accumulation of -omics data known to be highly variable, high-dimensional, and sourced from multiple often incompatible data platforms. While this data may be useful for biomarker identification and drug discovery, the bulk of it remains underutilized. Deep neural networks (DNNs) are efficient algorithms based on the use of compositional layers of neurons, with advantages well matched to the challenges -omics data presents. While achieving state-of-the-art results and even surpassing human accuracy in many challenging tasks, the adoption of deep learning in biomedicine has been comparatively slow. Here, we discuss key features of deep learning that may give this approach an edge over other machine learning methods. We then consider limitations and review a number of applications of deep learning in biomedical studies demonstrating proof of concept and practical utility.

Assessing the Linguistic Productivity of Unsupervised Deep Neural Networks

DOE Office of Scientific and Technical Information (OSTI.GOV)

Phillips, Lawrence A.; Hodas, Nathan O.

Increasingly, cognitive scientists have demonstrated interest in applying tools from deep learning. One use for deep learning is in language acquisition where it is useful to know if a linguistic phenomenon can be learned through domain-general means. To assess whether unsupervised deep learning is appropriate, we first pose a smaller question: Can unsupervised neural networks apply linguistic rules productively, using them in novel situations. We draw from the literature on determiner/noun productivity by training an unsupervised, autoencoder network measuring its ability to combine nouns with determiners. Our simple autoencoder creates combinations it has not previously encountered, displaying a degree ofmore » overlap similar to actual children. While this preliminary work does not provide conclusive evidence for productivity, it warrants further investigation with more complex models. Further, this work helps lay the foundations for future collaboration between the deep learning and cognitive science communities.« less

Teaching for Deep Learning

ERIC Educational Resources Information Center

Smith, Tracy Wilson; Colby, Susan A.

2007-01-01

The authors have been engaged in research focused on students' depth of learning as well as teachers' efforts to foster deep learning. Findings from a study examining the teaching practices and student learning outcomes of sixty-four teachers in seventeen different states (Smith et al. 2005) indicated that most of the learning in these classrooms…

Stimulating Deep Learning Using Active Learning Techniques

ERIC Educational Resources Information Center

Yew, Tee Meng; Dawood, Fauziah K. P.; a/p S. Narayansany, Kannaki; a/p Palaniappa Manickam, M. Kamala; Jen, Leong Siok; Hoay, Kuan Chin

2016-01-01

When students and teachers behave in ways that reinforce learning as a spectator sport, the result can often be a classroom and overall learning environment that is mostly limited to transmission of information and rote learning rather than deep approaches towards meaningful construction and application of knowledge. A group of college instructors…

Deep learning improves prediction of CRISPR-Cpf1 guide RNA activity.

PubMed

Kim, Hui Kwon; Min, Seonwoo; Song, Myungjae; Jung, Soobin; Choi, Jae Woo; Kim, Younggwang; Lee, Sangeun; Yoon, Sungroh; Kim, Hyongbum Henry

2018-03-01

We present two algorithms to predict the activity of AsCpf1 guide RNAs. Indel frequencies for 15,000 target sequences were used in a deep-learning framework based on a convolutional neural network to train Seq-deepCpf1. We then incorporated chromatin accessibility information to create the better-performing DeepCpf1 algorithm for cell lines for which such information is available and show that both algorithms outperform previous machine learning algorithms on our own and published data sets.

Using Deep Learning Algorithm to Enhance Image-review Software for Surveillance Cameras

DOE Office of Scientific and Technical Information (OSTI.GOV)

Cui, Yonggang; Thomas, Maikael A.

We propose the development of proven deep learning algorithms to flag objects and events of interest in Next Generation Surveillance System (NGSS) surveillance to make IAEA image review more efficient. Video surveillance is one of the core monitoring technologies used by the IAEA Department of Safeguards when implementing safeguards at nuclear facilities worldwide. The current image review software GARS has limited automated functions, such as scene-change detection, black image detection and missing scene analysis, but struggles with highly cluttered backgrounds. A cutting-edge algorithm to be developed in this project will enable efficient and effective searches in images and video streamsmore » by identifying and tracking safeguards relevant objects and detect anomalies in their vicinity. In this project, we will develop the algorithm, test it with the IAEA surveillance cameras and data sets collected at simulated nuclear facilities at BNL and SNL, and implement it in a software program for potential integration into the IAEA’s IRAP (Integrated Review and Analysis Program).« less

A deep learning framework for financial time series using stacked autoencoders and long-short term memory.

PubMed

Bao, Wei; Yue, Jun; Rao, Yulei

2017-01-01

The application of deep learning approaches to finance has received a great deal of attention from both investors and researchers. This study presents a novel deep learning framework where wavelet transforms (WT), stacked autoencoders (SAEs) and long-short term memory (LSTM) are combined for stock price forecasting. The SAEs for hierarchically extracted deep features is introduced into stock price forecasting for the first time. The deep learning framework comprises three stages. First, the stock price time series is decomposed by WT to eliminate noise. Second, SAEs is applied to generate deep high-level features for predicting the stock price. Third, high-level denoising features are fed into LSTM to forecast the next day's closing price. Six market indices and their corresponding index futures are chosen to examine the performance of the proposed model. Results show that the proposed model outperforms other similar models in both predictive accuracy and profitability performance.

Teaching as if your life depends on it: Environmental studies as a vehicle for societal and educational transformation

NASA Astrophysics Data System (ADS)

Giuliano, Jackie Alan

1998-11-01

This work presents a process for teaching environmental studies that is based on active engagement and participation with the world around us. In particular, the importance of recognizing our intimate connection to the natural world is stressed as an effective tool to learn about humans' role in the environment. Understanding our place in the natural world may be a pivotal awareness that must be developed if we are to heal the many wounds we are experiencing today. This work contains approaches to teaching that are based on critical thinking, problem solving, and nonlinear, non-patriarchal approaches to thinking, reasoning, and learning. With these tools, a learner is challenged to think and to understand diverse cultural, social, and intellectual perspectives and to perceive the natural world as an intimate and integral part of our lives. To develop this Deep Teaching Process principles were drawn from many elements including deep ecology, ecofeminism, despairwork, spiritual ecology, bioregionalism, critical thinking, movement therapy, and the author's own teaching experience with learners of all ages. The need for a deep teaching process is demonstrated through a discussion of a number of the environmental challenges we face today and how they affect a learner's perceptions. Two key items are vital to this process. First, 54 experiential learning experiences are presented that the author has developed or adapted to enhance the teaching of our relationship to the natural world. These experiences move the body and activate the creative impulses. Secondly, the author has developed workbooks for each class he has designed that provide foundational notes for each course. These workbooks insure that the student is present for the experience and not immersed in taking notes. The deep teaching process is a process to reawaken our senses. A reawakening of the senses and an intimate awareness of our connections to the natural world and the web of life may be the primary goal of any deep environmental studies educator.

Comparison of Deep Learning With Multiple Machine Learning Methods and Metrics Using Diverse Drug Discovery Data Sets.

PubMed

Korotcov, Alexandru; Tkachenko, Valery; Russo, Daniel P; Ekins, Sean

2017-12-04

Machine learning methods have been applied to many data sets in pharmaceutical research for several decades. The relative ease and availability of fingerprint type molecular descriptors paired with Bayesian methods resulted in the widespread use of this approach for a diverse array of end points relevant to drug discovery. Deep learning is the latest machine learning algorithm attracting attention for many of pharmaceutical applications from docking to virtual screening. Deep learning is based on an artificial neural network with multiple hidden layers and has found considerable traction for many artificial intelligence applications. We have previously suggested the need for a comparison of different machine learning methods with deep learning across an array of varying data sets that is applicable to pharmaceutical research. End points relevant to pharmaceutical research include absorption, distribution, metabolism, excretion, and toxicity (ADME/Tox) properties, as well as activity against pathogens and drug discovery data sets. In this study, we have used data sets for solubility, probe-likeness, hERG, KCNQ1, bubonic plague, Chagas, tuberculosis, and malaria to compare different machine learning methods using FCFP6 fingerprints. These data sets represent whole cell screens, individual proteins, physicochemical properties as well as a data set with a complex end point. Our aim was to assess whether deep learning offered any improvement in testing when assessed using an array of metrics including AUC, F1 score, Cohen's kappa, Matthews correlation coefficient and others. Based on ranked normalized scores for the metrics or data sets Deep Neural Networks (DNN) ranked higher than SVM, which in turn was ranked higher than all the other machine learning methods. Visualizing these properties for training and test sets using radar type plots indicates when models are inferior or perhaps over trained. These results also suggest the need for assessing deep learning further using multiple metrics with much larger scale comparisons, prospective testing as well as assessment of different fingerprints and DNN architectures beyond those used.

A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction

PubMed Central

Spencer, Matt; Eickholt, Jesse; Cheng, Jianlin

2014-01-01

Ab initio protein secondary structure (SS) predictions are utilized to generate tertiary structure predictions, which are increasingly demanded due to the rapid discovery of proteins. Although recent developments have slightly exceeded previous methods of SS prediction, accuracy has stagnated around 80% and many wonder if prediction cannot be advanced beyond this ceiling. Disciplines that have traditionally employed neural networks are experimenting with novel deep learning techniques in attempts to stimulate progress. Since neural networks have historically played an important role in SS prediction, we wanted to determine whether deep learning could contribute to the advancement of this field as well. We developed an SS predictor that makes use of the position-specific scoring matrix generated by PSI-BLAST and deep learning network architectures, which we call DNSS. Graphical processing units and CUDA software optimize the deep network architecture and efficiently train the deep networks. Optimal parameters for the training process were determined, and a workflow comprising three separately trained deep networks was constructed in order to make refined predictions. This deep learning network approach was used to predict SS for a fully independent test data set of 198 proteins, achieving a Q3 accuracy of 80.7% and a Sov accuracy of 74.2%. PMID:25750595

A Deep Learning Network Approach to ab initio Protein Secondary Structure Prediction.

PubMed

Spencer, Matt; Eickholt, Jesse; Jianlin Cheng

2015-01-01

Ab initio protein secondary structure (SS) predictions are utilized to generate tertiary structure predictions, which are increasingly demanded due to the rapid discovery of proteins. Although recent developments have slightly exceeded previous methods of SS prediction, accuracy has stagnated around 80 percent and many wonder if prediction cannot be advanced beyond this ceiling. Disciplines that have traditionally employed neural networks are experimenting with novel deep learning techniques in attempts to stimulate progress. Since neural networks have historically played an important role in SS prediction, we wanted to determine whether deep learning could contribute to the advancement of this field as well. We developed an SS predictor that makes use of the position-specific scoring matrix generated by PSI-BLAST and deep learning network architectures, which we call DNSS. Graphical processing units and CUDA software optimize the deep network architecture and efficiently train the deep networks. Optimal parameters for the training process were determined, and a workflow comprising three separately trained deep networks was constructed in order to make refined predictions. This deep learning network approach was used to predict SS for a fully independent test dataset of 198 proteins, achieving a Q3 accuracy of 80.7 percent and a Sov accuracy of 74.2 percent.

DeepNeuron: an open deep learning toolbox for neuron tracing.

PubMed

Zhou, Zhi; Kuo, Hsien-Chi; Peng, Hanchuan; Long, Fuhui

2018-06-06

Reconstructing three-dimensional (3D) morphology of neurons is essential for understanding brain structures and functions. Over the past decades, a number of neuron tracing tools including manual, semiautomatic, and fully automatic approaches have been developed to extract and analyze 3D neuronal structures. Nevertheless, most of them were developed based on coding certain rules to extract and connect structural components of a neuron, showing limited performance on complicated neuron morphology. Recently, deep learning outperforms many other machine learning methods in a wide range of image analysis and computer vision tasks. Here we developed a new Open Source toolbox, DeepNeuron, which uses deep learning networks to learn features and rules from data and trace neuron morphology in light microscopy images. DeepNeuron provides a family of modules to solve basic yet challenging problems in neuron tracing. These problems include but not limited to: (1) detecting neuron signal under different image conditions, (2) connecting neuronal signals into tree(s), (3) pruning and refining tree morphology, (4) quantifying the quality of morphology, and (5) classifying dendrites and axons in real time. We have tested DeepNeuron using light microscopy images including bright-field and confocal images of human and mouse brain, on which DeepNeuron demonstrates robustness and accuracy in neuron tracing.

Opening up the blackbox: an interpretable deep neural network-based classifier for cell-type specific enhancer predictions.

PubMed

Kim, Seong Gon; Theera-Ampornpunt, Nawanol; Fang, Chih-Hao; Harwani, Mrudul; Grama, Ananth; Chaterji, Somali

2016-08-01

Gene expression is mediated by specialized cis-regulatory modules (CRMs), the most prominent of which are called enhancers. Early experiments indicated that enhancers located far from the gene promoters are often responsible for mediating gene transcription. Knowing their properties, regulatory activity, and genomic targets is crucial to the functional understanding of cellular events, ranging from cellular homeostasis to differentiation. Recent genome-wide investigation of epigenomic marks has indicated that enhancer elements could be enriched for certain epigenomic marks, such as, combinatorial patterns of histone modifications. Our efforts in this paper are motivated by these recent advances in epigenomic profiling methods, which have uncovered enhancer-associated chromatin features in different cell types and organisms. Specifically, in this paper, we use recent state-of-the-art Deep Learning methods and develop a deep neural network (DNN)-based architecture, called EP-DNN, to predict the presence and types of enhancers in the human genome. It uses as features, the expression levels of the histone modifications at the peaks of the functional sites as well as in its adjacent regions. We apply EP-DNN to four different cell types: H1, IMR90, HepG2, and HeLa S3. We train EP-DNN using p300 binding sites as enhancers, and TSS and random non-DHS sites as non-enhancers. We perform EP-DNN predictions to quantify the validation rate for different levels of confidence in the predictions and also perform comparisons against two state-of-the-art computational models for enhancer predictions, DEEP-ENCODE and RFECS. We find that EP-DNN has superior accuracy and takes less time to make predictions. Next, we develop methods to make EP-DNN interpretable by computing the importance of each input feature in the classification task. This analysis indicates that the important histone modifications were distinct for different cell types, with some overlaps, e.g., H3K27ac was important in cell type H1 but less so in HeLa S3, while H3K4me1 was relatively important in all four cell types. We finally use the feature importance analysis to reduce the number of input features needed to train the DNN, thus reducing training time, which is often the computational bottleneck in the use of a DNN. In this paper, we developed EP-DNN, which has high accuracy of prediction, with validation rates above 90 % for the operational region of enhancer prediction for all four cell lines that we studied, outperforming DEEP-ENCODE and RFECS. Then, we developed a method to analyze a trained DNN and determine which histone modifications are important, and within that, which features proximal or distal to the enhancer site, are important.

Clinical Named Entity Recognition Using Deep Learning Models.

PubMed

Wu, Yonghui; Jiang, Min; Xu, Jun; Zhi, Degui; Xu, Hua

2017-01-01

Clinical Named Entity Recognition (NER) is a critical natural language processing (NLP) task to extract important concepts (named entities) from clinical narratives. Researchers have extensively investigated machine learning models for clinical NER. Recently, there have been increasing efforts to apply deep learning models to improve the performance of current clinical NER systems. This study examined two popular deep learning architectures, the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN), to extract concepts from clinical texts. We compared the two deep neural network architectures with three baseline Conditional Random Fields (CRFs) models and two state-of-the-art clinical NER systems using the i2b2 2010 clinical concept extraction corpus. The evaluation results showed that the RNN model trained with the word embeddings achieved a new state-of-the- art performance (a strict F1 score of 85.94%) for the defined clinical NER task, outperforming the best-reported system that used both manually defined and unsupervised learning features. This study demonstrates the advantage of using deep neural network architectures for clinical concept extraction, including distributed feature representation, automatic feature learning, and long-term dependencies capture. This is one of the first studies to compare the two widely used deep learning models and demonstrate the superior performance of the RNN model for clinical NER.

Clinical Named Entity Recognition Using Deep Learning Models

PubMed Central

Wu, Yonghui; Jiang, Min; Xu, Jun; Zhi, Degui; Xu, Hua

2017-01-01

Clinical Named Entity Recognition (NER) is a critical natural language processing (NLP) task to extract important concepts (named entities) from clinical narratives. Researchers have extensively investigated machine learning models for clinical NER. Recently, there have been increasing efforts to apply deep learning models to improve the performance of current clinical NER systems. This study examined two popular deep learning architectures, the Convolutional Neural Network (CNN) and the Recurrent Neural Network (RNN), to extract concepts from clinical texts. We compared the two deep neural network architectures with three baseline Conditional Random Fields (CRFs) models and two state-of-the-art clinical NER systems using the i2b2 2010 clinical concept extraction corpus. The evaluation results showed that the RNN model trained with the word embeddings achieved a new state-of-the- art performance (a strict F1 score of 85.94%) for the defined clinical NER task, outperforming the best-reported system that used both manually defined and unsupervised learning features. This study demonstrates the advantage of using deep neural network architectures for clinical concept extraction, including distributed feature representation, automatic feature learning, and long-term dependencies capture. This is one of the first studies to compare the two widely used deep learning models and demonstrate the superior performance of the RNN model for clinical NER. PMID:29854252

Adaptive template generation for amyloid PET using a deep learning approach.

PubMed

Kang, Seung Kwan; Seo, Seongho; Shin, Seong A; Byun, Min Soo; Lee, Dong Young; Kim, Yu Kyeong; Lee, Dong Soo; Lee, Jae Sung

2018-05-11

Accurate spatial normalization (SN) of amyloid positron emission tomography (PET) images for Alzheimer's disease assessment without coregistered anatomical magnetic resonance imaging (MRI) of the same individual is technically challenging. In this study, we applied deep neural networks to generate individually adaptive PET templates for robust and accurate SN of amyloid PET without using matched 3D MR images. Using 681 pairs of simultaneously acquired 11 C-PIB PET and T1-weighted 3D MRI scans of AD, MCI, and cognitively normal subjects, we trained and tested two deep neural networks [convolutional auto-encoder (CAE) and generative adversarial network (GAN)] that produce adaptive best PET templates. More specifically, the networks were trained using 685,100 pieces of augmented data generated by rotating 527 randomly selected datasets and validated using 154 datasets. The input to the supervised neural networks was the 3D PET volume in native space and the label was the spatially normalized 3D PET image using the transformation parameters obtained from MRI-based SN. The proposed deep learning approach significantly enhanced the quantitative accuracy of MRI-less amyloid PET assessment by reducing the SN error observed when an average amyloid PET template is used. Given an input image, the trained deep neural networks rapidly provide individually adaptive 3D PET templates without any discontinuity between the slices (in 0.02 s). As the proposed method does not require 3D MRI for the SN of PET images, it has great potential for use in routine analysis of amyloid PET images in clinical practice and research. © 2018 Wiley Periodicals, Inc.

Deep learning in pharmacogenomics: from gene regulation to patient stratification.

PubMed

Kalinin, Alexandr A; Higgins, Gerald A; Reamaroon, Narathip; Soroushmehr, Sayedmohammadreza; Allyn-Feuer, Ari; Dinov, Ivo D; Najarian, Kayvan; Athey, Brian D

2018-05-01

This Perspective provides examples of current and future applications of deep learning in pharmacogenomics, including: identification of novel regulatory variants located in noncoding domains of the genome and their function as applied to pharmacoepigenomics; patient stratification from medical records; and the mechanistic prediction of drug response, targets and their interactions. Deep learning encapsulates a family of machine learning algorithms that has transformed many important subfields of artificial intelligence over the last decade, and has demonstrated breakthrough performance improvements on a wide range of tasks in biomedicine. We anticipate that in the future, deep learning will be widely used to predict personalized drug response and optimize medication selection and dosing, using knowledge extracted from large and complex molecular, epidemiological, clinical and demographic datasets.

Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis

NASA Astrophysics Data System (ADS)

Chernoded, Andrey; Dudko, Lev; Myagkov, Igor; Volkov, Petr

2017-10-01

Most of the modern analyses in high energy physics use signal-versus-background classification techniques of machine learning methods and neural networks in particular. Deep learning neural network is the most promising modern technique to separate signal and background and now days can be widely and successfully implemented as a part of physical analysis. In this article we compare Deep learning and Bayesian neural networks application as a classifiers in an instance of top quark analysis.

BCDForest: a boosting cascade deep forest model towards the classification of cancer subtypes based on gene expression data.

PubMed

Guo, Yang; Liu, Shuhui; Li, Zhanhuai; Shang, Xuequn

2018-04-11

The classification of cancer subtypes is of great importance to cancer disease diagnosis and therapy. Many supervised learning approaches have been applied to cancer subtype classification in the past few years, especially of deep learning based approaches. Recently, the deep forest model has been proposed as an alternative of deep neural networks to learn hyper-representations by using cascade ensemble decision trees. It has been proved that the deep forest model has competitive or even better performance than deep neural networks in some extent. However, the standard deep forest model may face overfitting and ensemble diversity challenges when dealing with small sample size and high-dimensional biology data. In this paper, we propose a deep learning model, so-called BCDForest, to address cancer subtype classification on small-scale biology datasets, which can be viewed as a modification of the standard deep forest model. The BCDForest distinguishes from the standard deep forest model with the following two main contributions: First, a named multi-class-grained scanning method is proposed to train multiple binary classifiers to encourage diversity of ensemble. Meanwhile, the fitting quality of each classifier is considered in representation learning. Second, we propose a boosting strategy to emphasize more important features in cascade forests, thus to propagate the benefits of discriminative features among cascade layers to improve the classification performance. Systematic comparison experiments on both microarray and RNA-Seq gene expression datasets demonstrate that our method consistently outperforms the state-of-the-art methods in application of cancer subtype classification. The multi-class-grained scanning and boosting strategy in our model provide an effective solution to ease the overfitting challenge and improve the robustness of deep forest model working on small-scale data. Our model provides a useful approach to the classification of cancer subtypes by using deep learning on high-dimensional and small-scale biology data.

The Influence of Parents and Teachers on the Deep Learning Approach of Pupils in Norwegian Upper-Secondary Schools

ERIC Educational Resources Information Center

Elstad, Eyvind; Christophersen, Knut-Andreas; Turmo, Are

2012-01-01

Introduction: The purpose of this article was to explore the influence of parents and teachers on the deep learning approach of pupils by estimating the strength of the relationships between these factors and the motivation, volition and deep learning approach of Norwegian 16-year-olds. Method: Structural equation modeling for cross-sectional…

The Use of Deep Learning Strategies in Online Business Courses to Impact Student Retention

ERIC Educational Resources Information Center

DeLotell, Pam Jones; Millam, Loretta A.; Reinhardt, Michelle M.

2010-01-01

Interest, application and understanding--these are key elements in successful online classroom experiences and all part of what is commonly referred to as deep learning. Deep learning occurs when students are able to connect with course topics, find value in them and see how to apply them to real-world situations. Asynchronous discussion forums in…

Deep Unfolding for Topic Models.

PubMed

Chien, Jen-Tzung; Lee, Chao-Hsi

2018-02-01

Deep unfolding provides an approach to integrate the probabilistic generative models and the deterministic neural networks. Such an approach is benefited by deep representation, easy interpretation, flexible learning and stochastic modeling. This study develops the unsupervised and supervised learning of deep unfolded topic models for document representation and classification. Conventionally, the unsupervised and supervised topic models are inferred via the variational inference algorithm where the model parameters are estimated by maximizing the lower bound of logarithm of marginal likelihood using input documents without and with class labels, respectively. The representation capability or classification accuracy is constrained by the variational lower bound and the tied model parameters across inference procedure. This paper aims to relax these constraints by directly maximizing the end performance criterion and continuously untying the parameters in learning process via deep unfolding inference (DUI). The inference procedure is treated as the layer-wise learning in a deep neural network. The end performance is iteratively improved by using the estimated topic parameters according to the exponentiated updates. Deep learning of topic models is therefore implemented through a back-propagation procedure. Experimental results show the merits of DUI with increasing number of layers compared with variational inference in unsupervised as well as supervised topic models.

Using deep learning in image hyper spectral segmentation, classification, and detection

NASA Astrophysics Data System (ADS)

Zhao, Xiuying; Su, Zhenyu

2018-02-01

Recent years have shown that deep learning neural networks are a valuable tool in the field of computer vision. Deep learning method can be used in applications like remote sensing such as Land cover Classification, Detection of Vehicle in Satellite Images, Hyper spectral Image classification. This paper addresses the use of the deep learning artificial neural network in Satellite image segmentation. Image segmentation plays an important role in image processing. The hue of the remote sensing image often has a large hue difference, which will result in the poor display of the images in the VR environment. Image segmentation is a pre processing technique applied to the original images and splits the image into many parts which have different hue to unify the color. Several computational models based on supervised, unsupervised, parametric, probabilistic region based image segmentation techniques have been proposed. Recently, one of the machine learning technique known as, deep learning with convolution neural network has been widely used for development of efficient and automatic image segmentation models. In this paper, we focus on study of deep neural convolution network and its variants for automatic image segmentation rather than traditional image segmentation strategies.

Deep learning aided decision support for pulmonary nodules diagnosing: a review

PubMed Central

Yang, Yixin; Feng, Xiaoyi; Chi, Wenhao; Li, Zhengyang; Duan, Wenzhe; Liu, Haiping; Liang, Wenhua; Wang, Wei; Chen, Ping

2018-01-01

Deep learning techniques have recently emerged as promising decision supporting approaches to automatically analyze medical images for different clinical diagnosing purposes. Diagnosing of pulmonary nodules by using computer-assisted diagnosing has received considerable theoretical, computational, and empirical research work, and considerable methods have been developed for detection and classification of pulmonary nodules on different formats of images including chest radiographs, computed tomography (CT), and positron emission tomography in the past five decades. The recent remarkable and significant progress in deep learning for pulmonary nodules achieved in both academia and the industry has demonstrated that deep learning techniques seem to be promising alternative decision support schemes to effectively tackle the central issues in pulmonary nodules diagnosing, including feature extraction, nodule detection, false-positive reduction, and benign-malignant classification for the huge volume of chest scan data. The main goal of this investigation is to provide a comprehensive state-of-the-art review of the deep learning aided decision support for pulmonary nodules diagnosing. As far as the authors know, this is the first time that a review is devoted exclusively to deep learning techniques for pulmonary nodules diagnosing. PMID:29780633

Deep Learning for Prediction of Obstructive Disease From Fast Myocardial Perfusion SPECT: A Multicenter Study.

PubMed

Betancur, Julian; Commandeur, Frederic; Motlagh, Mahsaw; Sharir, Tali; Einstein, Andrew J; Bokhari, Sabahat; Fish, Mathews B; Ruddy, Terrence D; Kaufmann, Philipp; Sinusas, Albert J; Miller, Edward J; Bateman, Timothy M; Dorbala, Sharmila; Di Carli, Marcelo; Germano, Guido; Otaki, Yuka; Tamarappoo, Balaji K; Dey, Damini; Berman, Daniel S; Slomka, Piotr J

2018-03-12

The study evaluated the automatic prediction of obstructive disease from myocardial perfusion imaging (MPI) by deep learning as compared with total perfusion deficit (TPD). Deep convolutional neural networks trained with a large multicenter population may provide improved prediction of per-patient and per-vessel coronary artery disease from single-photon emission computed tomography MPI. A total of 1,638 patients (67% men) without known coronary artery disease, undergoing stress 99m Tc-sestamibi or tetrofosmin MPI with new generation solid-state scanners in 9 different sites, with invasive coronary angiography performed within 6 months of MPI, were studied. Obstructive disease was defined as ≥70% narrowing of coronary arteries (≥50% for left main artery). Left ventricular myocardium was segmented using clinical nuclear cardiology software and verified by an expert reader. Stress TPD was computed using sex- and camera-specific normal limits. Deep learning was trained using raw and quantitative polar maps and evaluated for prediction of obstructive stenosis in a stratified 10-fold cross-validation procedure. A total of 1,018 (62%) patients and 1,797 of 4,914 (37%) arteries had obstructive disease. Area under the receiver-operating characteristic curve for disease prediction by deep learning was higher than for TPD (per patient: 0.80 vs. 0.78; per vessel: 0.76 vs. 0.73: p < 0.01). With deep learning threshold set to the same specificity as TPD, per-patient sensitivity improved from 79.8% (TPD) to 82.3% (deep learning) (p < 0.05), and per-vessel sensitivity improved from 64.4% (TPD) to 69.8% (deep learning) (p < 0.01). Deep learning has the potential to improve automatic interpretation of MPI as compared with current clinical methods. Copyright © 2018 American College of Cardiology Foundation. Published by Elsevier Inc. All rights reserved.

Intelligent Detection of Structure from Remote Sensing Images Based on Deep Learning Method

NASA Astrophysics Data System (ADS)

Xin, L.

2018-04-01

Utilizing high-resolution remote sensing images for earth observation has become the common method of land use monitoring. It requires great human participation when dealing with traditional image interpretation, which is inefficient and difficult to guarantee the accuracy. At present, the artificial intelligent method such as deep learning has a large number of advantages in the aspect of image recognition. By means of a large amount of remote sensing image samples and deep neural network models, we can rapidly decipher the objects of interest such as buildings, etc. Whether in terms of efficiency or accuracy, deep learning method is more preponderant. This paper explains the research of deep learning method by a great mount of remote sensing image samples and verifies the feasibility of building extraction via experiments.

Dental students' perception of their approaches to learning in a PBL programme.

PubMed

Haghparast, H; Ghorbani, A; Rohlin, M

2017-08-01

To compare dental students' perceptions of their learning approaches between different years of a problem-based learning (PBL) programme. The hypothesis was that in a comparison between senior and junior students, the senior students would perceive themselves as having a higher level of deep learning approach and a lower level of surface learning approach than junior students would. This hypothesis was based on the fact that senior students have longer experience of a student-centred educational context, which is supposed to underpin student learning. Students of three cohorts (first year, third year and fifth year) of a PBL-based dental programme were asked to respond to a questionnaire (R-SPQ-2F) developed to analyse students' learning approaches, that is deep approach and surface approach, using four subscales including deep strategy, surface strategy, deep motive and surface motive. The results of the three cohorts were compared using a one-way analysis of variance (ANOVA). A P-value was set at <0.05 for statistical significance. The fifth-year students demonstrated a lower surface approach than the first-year students (P = 0.020). There was a significant decrease in surface strategy from the first to the fifth year (P = 0.003). No differences were found concerning deep approach or its subscales (deep strategy and deep motive) between the mean scores of the three cohorts. The results did not show the expected increased depth in learning approaches over the programme years. © 2016 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

New Techniques for Deep Learning with Geospatial Data using TensorFlow, Earth Engine, and Google Cloud Platform

NASA Astrophysics Data System (ADS)

Hancher, M.

2017-12-01

Recent years have seen promising results from many research teams applying deep learning techniques to geospatial data processing. In that same timeframe, TensorFlow has emerged as the most popular framework for deep learning in general, and Google has assembled petabytes of Earth observation data from a wide variety of sources and made them available in analysis-ready form in the cloud through Google Earth Engine. Nevertheless, developing and applying deep learning to geospatial data at scale has been somewhat cumbersome to date. We present a new set of tools and techniques that simplify this process. Our approach combines the strengths of several underlying tools: TensorFlow for its expressive deep learning framework; Earth Engine for data management, preprocessing, postprocessing, and visualization; and other tools in Google Cloud Platform to train TensorFlow models at scale, perform additional custom parallel data processing, and drive the entire process from a single familiar Python development environment. These tools can be used to easily apply standard deep neural networks, convolutional neural networks, and other custom model architectures to a variety of geospatial data structures. We discuss our experiences applying these and related tools to a range of machine learning problems, including classic problems like cloud detection, building detection, land cover classification, as well as more novel problems like illegal fishing detection. Our improved tools will make it easier for geospatial data scientists to apply modern deep learning techniques to their own problems, and will also make it easier for machine learning researchers to advance the state of the art of those techniques.

Latent feature representation with stacked auto-encoder for AD/MCI diagnosis

PubMed Central

Lee, Seong-Whan

2014-01-01

Recently, there have been great interests for computer-aided diagnosis of Alzheimer’s disease (AD) and its prodromal stage, mild cognitive impairment (MCI). Unlike the previous methods that considered simple low-level features such as gray matter tissue volumes from MRI, and mean signal intensities from PET, in this paper, we propose a deep learning-based latent feature representation with a stacked auto-encoder (SAE). We believe that there exist latent non-linear complicated patterns inherent in the low-level features such as relations among features. Combining the latent information with the original features helps build a robust model in AD/MCI classification, with high diagnostic accuracy. Furthermore, thanks to the unsupervised characteristic of the pre-training in deep learning, we can benefit from the target-unrelated samples to initialize parameters of SAE, thus finding optimal parameters in fine-tuning with the target-related samples, and further enhancing the classification performances across four binary classification problems: AD vs. healthy normal control (HC), MCI vs. HC, AD vs. MCI, and MCI converter (MCI-C) vs. MCI non-converter (MCI-NC). In our experiments on ADNI dataset, we validated the effectiveness of the proposed method, showing the accuracies of 98.8, 90.7, 83.7, and 83.3 % for AD/HC, MCI/HC, AD/MCI, and MCI-C/MCI-NC classification, respectively. We believe that deep learning can shed new light on the neuroimaging data analysis, and our work presented the applicability of this method to brain disease diagnosis. PMID:24363140

A hybrid deep learning approach to predict malignancy of breast lesions using mammograms

NASA Astrophysics Data System (ADS)

Wang, Yunzhi; Heidari, Morteza; Mirniaharikandehei, Seyedehnafiseh; Gong, Jing; Qian, Wei; Qiu, Yuchen; Zheng, Bin

2018-03-01

Applying deep learning technology to medical imaging informatics field has been recently attracting extensive research interest. However, the limited medical image dataset size often reduces performance and robustness of the deep learning based computer-aided detection and/or diagnosis (CAD) schemes. In attempt to address this technical challenge, this study aims to develop and evaluate a new hybrid deep learning based CAD approach to predict likelihood of a breast lesion detected on mammogram being malignant. In this approach, a deep Convolutional Neural Network (CNN) was firstly pre-trained using the ImageNet dataset and serve as a feature extractor. A pseudo-color Region of Interest (ROI) method was used to generate ROIs with RGB channels from the mammographic images as the input to the pre-trained deep network. The transferred CNN features from different layers of the CNN were then obtained and a linear support vector machine (SVM) was trained for the prediction task. By applying to a dataset involving 301 suspicious breast lesions and using a leave-one-case-out validation method, the areas under the ROC curves (AUC) = 0.762 and 0.792 using the traditional CAD scheme and the proposed deep learning based CAD scheme, respectively. An ensemble classifier that combines the classification scores generated by the two schemes yielded an improved AUC value of 0.813. The study results demonstrated feasibility and potentially improved performance of applying a new hybrid deep learning approach to develop CAD scheme using a relatively small dataset of medical images.

The effects of deep network topology on mortality prediction.

PubMed

Hao Du; Ghassemi, Mohammad M; Mengling Feng

2016-08-01

Deep learning has achieved remarkable results in the areas of computer vision, speech recognition, natural language processing and most recently, even playing Go. The application of deep-learning to problems in healthcare, however, has gained attention only in recent years, and it's ultimate place at the bedside remains a topic of skeptical discussion. While there is a growing academic interest in the application of Machine Learning (ML) techniques to clinical problems, many in the clinical community see little incentive to upgrade from simpler methods, such as logistic regression, to deep learning. Logistic regression, after all, provides odds ratios, p-values and confidence intervals that allow for ease of interpretation, while deep nets are often seen as `black-boxes' which are difficult to understand and, as of yet, have not demonstrated performance levels far exceeding their simpler counterparts. If deep learning is to ever take a place at the bedside, it will require studies which (1) showcase the performance of deep-learning methods relative to other approaches and (2) interpret the relationships between network structure, model performance, features and outcomes. We have chosen these two requirements as the goal of this study. In our investigation, we utilized a publicly available EMR dataset of over 32,000 intensive care unit patients and trained a Deep Belief Network (DBN) to predict patient mortality at discharge. Utilizing an evolutionary algorithm, we demonstrate automated topology selection for DBNs. We demonstrate that with the correct topology selection, DBNs can achieve better prediction performance compared to several bench-marking methods.

Deep Unsupervised Learning on a Desktop PC: A Primer for Cognitive Scientists.

PubMed

Testolin, Alberto; Stoianov, Ivilin; De Filippo De Grazia, Michele; Zorzi, Marco

2013-01-01

Deep belief networks hold great promise for the simulation of human cognition because they show how structured and abstract representations may emerge from probabilistic unsupervised learning. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. However, learning in deep networks typically requires big datasets and it can involve millions of connection weights, which implies that simulations on standard computers are unfeasible. Developing realistic, medium-to-large-scale learning models of cognition would therefore seem to require expertise in programing parallel-computing hardware, and this might explain why the use of this promising approach is still largely confined to the machine learning community. Here we show how simulations of deep unsupervised learning can be easily performed on a desktop PC by exploiting the processors of low cost graphic cards (graphic processor units) without any specific programing effort, thanks to the use of high-level programming routines (available in MATLAB or Python). We also show that even an entry-level graphic card can outperform a small high-performance computing cluster in terms of learning time and with no loss of learning quality. We therefore conclude that graphic card implementations pave the way for a widespread use of deep learning among cognitive scientists for modeling cognition and behavior.

Deep Unsupervised Learning on a Desktop PC: A Primer for Cognitive Scientists

PubMed Central

Testolin, Alberto; Stoianov, Ivilin; De Filippo De Grazia, Michele; Zorzi, Marco

2013-01-01

Deep belief networks hold great promise for the simulation of human cognition because they show how structured and abstract representations may emerge from probabilistic unsupervised learning. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. However, learning in deep networks typically requires big datasets and it can involve millions of connection weights, which implies that simulations on standard computers are unfeasible. Developing realistic, medium-to-large-scale learning models of cognition would therefore seem to require expertise in programing parallel-computing hardware, and this might explain why the use of this promising approach is still largely confined to the machine learning community. Here we show how simulations of deep unsupervised learning can be easily performed on a desktop PC by exploiting the processors of low cost graphic cards (graphic processor units) without any specific programing effort, thanks to the use of high-level programming routines (available in MATLAB or Python). We also show that even an entry-level graphic card can outperform a small high-performance computing cluster in terms of learning time and with no loss of learning quality. We therefore conclude that graphic card implementations pave the way for a widespread use of deep learning among cognitive scientists for modeling cognition and behavior. PMID:23653617

Is Multitask Deep Learning Practical for Pharma?

PubMed

Ramsundar, Bharath; Liu, Bowen; Wu, Zhenqin; Verras, Andreas; Tudor, Matthew; Sheridan, Robert P; Pande, Vijay

2017-08-28

Multitask deep learning has emerged as a powerful tool for computational drug discovery. However, despite a number of preliminary studies, multitask deep networks have yet to be widely deployed in the pharmaceutical and biotech industries. This lack of acceptance stems from both software difficulties and lack of understanding of the robustness of multitask deep networks. Our work aims to resolve both of these barriers to adoption. We introduce a high-quality open-source implementation of multitask deep networks as part of the DeepChem open-source platform. Our implementation enables simple python scripts to construct, fit, and evaluate sophisticated deep models. We use our implementation to analyze the performance of multitask deep networks and related deep models on four collections of pharmaceutical data (three of which have not previously been analyzed in the literature). We split these data sets into train/valid/test using time and neighbor splits to test multitask deep learning performance under challenging conditions. Our results demonstrate that multitask deep networks are surprisingly robust and can offer strong improvement over random forests. Our analysis and open-source implementation in DeepChem provide an argument that multitask deep networks are ready for widespread use in commercial drug discovery.

Active appearance model and deep learning for more accurate prostate segmentation on MRI

NASA Astrophysics Data System (ADS)

Cheng, Ruida; Roth, Holger R.; Lu, Le; Wang, Shijun; Turkbey, Baris; Gandler, William; McCreedy, Evan S.; Agarwal, Harsh K.; Choyke, Peter; Summers, Ronald M.; McAuliffe, Matthew J.

2016-03-01

Prostate segmentation on 3D MR images is a challenging task due to image artifacts, large inter-patient prostate shape and texture variability, and lack of a clear prostate boundary specifically at apex and base levels. We propose a supervised machine learning model that combines atlas based Active Appearance Model (AAM) with a Deep Learning model to segment the prostate on MR images. The performance of the segmentation method is evaluated on 20 unseen MR image datasets. The proposed method combining AAM and Deep Learning achieves a mean Dice Similarity Coefficient (DSC) of 0.925 for whole 3D MR images of the prostate using axial cross-sections. The proposed model utilizes the adaptive atlas-based AAM model and Deep Learning to achieve significant segmentation accuracy.

Simulation of noisy dynamical system by Deep Learning

NASA Astrophysics Data System (ADS)

Yeo, Kyongmin

2017-11-01

Deep learning has attracted huge attention due to its powerful representation capability. However, most of the studies on deep learning have been focused on visual analytics or language modeling and the capability of the deep learning in modeling dynamical systems is not well understood. In this study, we use a recurrent neural network to model noisy nonlinear dynamical systems. In particular, we use a long short-term memory (LSTM) network, which constructs internal nonlinear dynamics systems. We propose a cross-entropy loss with spatial ridge regularization to learn a non-stationary conditional probability distribution from a noisy nonlinear dynamical system. A Monte Carlo procedure to perform time-marching simulations by using the LSTM is presented. The behavior of the LSTM is studied by using noisy, forced Van der Pol oscillator and Ikeda equation.

A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery.

PubMed

Liu, Yan; Stojadinovic, Strahinja; Hrycushko, Brian; Wardak, Zabi; Lau, Steven; Lu, Weiguo; Yan, Yulong; Jiang, Steve B; Zhen, Xin; Timmerman, Robert; Nedzi, Lucien; Gu, Xuejun

2017-01-01

Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs) of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases.

Deep learning of support vector machines with class probability output networks.

PubMed

Kim, Sangwook; Yu, Zhibin; Kil, Rhee Man; Lee, Minho

2015-04-01

Deep learning methods endeavor to learn features automatically at multiple levels and allow systems to learn complex functions mapping from the input space to the output space for the given data. The ability to learn powerful features automatically is increasingly important as the volume of data and range of applications of machine learning methods continues to grow. This paper proposes a new deep architecture that uses support vector machines (SVMs) with class probability output networks (CPONs) to provide better generalization power for pattern classification problems. As a result, deep features are extracted without additional feature engineering steps, using multiple layers of the SVM classifiers with CPONs. The proposed structure closely approaches the ideal Bayes classifier as the number of layers increases. Using a simulation of classification problems, the effectiveness of the proposed method is demonstrated. Copyright © 2014 Elsevier Ltd. All rights reserved.

Diverse assessment and active student engagement sustain deep learning: A comparative study of outcomes in two parallel introductory biochemistry courses.

PubMed

Bevan, Samantha J; Chan, Cecilia W L; Tanner, Julian A

2014-01-01

Although there is increasing evidence for a relationship between courses that emphasize student engagement and achievement of student deep learning, there is a paucity of quantitative comparative studies in a biochemistry and molecular biology context. Here, we present a pedagogical study in two contrasting parallel biochemistry introductory courses to compare student surface and deep learning. Surface and deep learning were measured quantitatively by a study process questionnaire at the start and end of the semester, and qualitatively by questionnaires and interviews with students. In the traditional lecture/examination based course, there was a dramatic shift to surface learning approaches through the semester. In the course that emphasized student engagement and adopted multiple forms of assessment, a preference for deep learning was sustained with only a small reduction through the semester. Such evidence for the benefits of implementing student engagement and more diverse non-examination based assessment has important implications for the design, delivery, and renewal of introductory courses in biochemistry and molecular biology. © 2014 The International Union of Biochemistry and Molecular Biology.

Airline Passenger Profiling Based on Fuzzy Deep Machine Learning.

PubMed

Zheng, Yu-Jun; Sheng, Wei-Guo; Sun, Xing-Ming; Chen, Sheng-Yong

2017-12-01

Passenger profiling plays a vital part of commercial aviation security, but classical methods become very inefficient in handling the rapidly increasing amounts of electronic records. This paper proposes a deep learning approach to passenger profiling. The center of our approach is a Pythagorean fuzzy deep Boltzmann machine (PFDBM), whose parameters are expressed by Pythagorean fuzzy numbers such that each neuron can learn how a feature affects the production of the correct output from both the positive and negative sides. We propose a hybrid algorithm combining a gradient-based method and an evolutionary algorithm for training the PFDBM. Based on the novel learning model, we develop a deep neural network (DNN) for classifying normal passengers and potential attackers, and further develop an integrated DNN for identifying group attackers whose individual features are insufficient to reveal the abnormality. Experiments on data sets from Air China show that our approach provides much higher learning ability and classification accuracy than existing profilers. It is expected that the fuzzy deep learning approach can be adapted for a variety of complex pattern analysis tasks.

Using deep learning for content-based medical image retrieval

NASA Astrophysics Data System (ADS)

Sun, Qinpei; Yang, Yuanyuan; Sun, Jianyong; Yang, Zhiming; Zhang, Jianguo

2017-03-01

Content-Based medical image retrieval (CBMIR) is been highly active research area from past few years. The retrieval performance of a CBMIR system crucially depends on the feature representation, which have been extensively studied by researchers for decades. Although a variety of techniques have been proposed, it remains one of the most challenging problems in current CBMIR research, which is mainly due to the well-known "semantic gap" issue that exists between low-level image pixels captured by machines and high-level semantic concepts perceived by human[1]. Recent years have witnessed some important advances of new techniques in machine learning. One important breakthrough technique is known as "deep learning". Unlike conventional machine learning methods that are often using "shallow" architectures, deep learning mimics the human brain that is organized in a deep architecture and processes information through multiple stages of transformation and representation. This means that we do not need to spend enormous energy to extract features manually. In this presentation, we propose a novel framework which uses deep learning to retrieval the medical image to improve the accuracy and speed of a CBIR in integrated RIS/PACS.

Deep Convolutional Extreme Learning Machine and Its Application in Handwritten Digit Classification

PubMed Central

Yang, Xinyi

2016-01-01

In recent years, some deep learning methods have been developed and applied to image classification applications, such as convolutional neuron network (CNN) and deep belief network (DBN). However they are suffering from some problems like local minima, slow convergence rate, and intensive human intervention. In this paper, we propose a rapid learning method, namely, deep convolutional extreme learning machine (DC-ELM), which combines the power of CNN and fast training of ELM. It uses multiple alternate convolution layers and pooling layers to effectively abstract high level features from input images. Then the abstracted features are fed to an ELM classifier, which leads to better generalization performance with faster learning speed. DC-ELM also introduces stochastic pooling in the last hidden layer to reduce dimensionality of features greatly, thus saving much training time and computation resources. We systematically evaluated the performance of DC-ELM on two handwritten digit data sets: MNIST and USPS. Experimental results show that our method achieved better testing accuracy with significantly shorter training time in comparison with deep learning methods and other ELM methods. PMID:27610128

Deep Convolutional Extreme Learning Machine and Its Application in Handwritten Digit Classification.

PubMed

Pang, Shan; Yang, Xinyi

2016-01-01

In recent years, some deep learning methods have been developed and applied to image classification applications, such as convolutional neuron network (CNN) and deep belief network (DBN). However they are suffering from some problems like local minima, slow convergence rate, and intensive human intervention. In this paper, we propose a rapid learning method, namely, deep convolutional extreme learning machine (DC-ELM), which combines the power of CNN and fast training of ELM. It uses multiple alternate convolution layers and pooling layers to effectively abstract high level features from input images. Then the abstracted features are fed to an ELM classifier, which leads to better generalization performance with faster learning speed. DC-ELM also introduces stochastic pooling in the last hidden layer to reduce dimensionality of features greatly, thus saving much training time and computation resources. We systematically evaluated the performance of DC-ELM on two handwritten digit data sets: MNIST and USPS. Experimental results show that our method achieved better testing accuracy with significantly shorter training time in comparison with deep learning methods and other ELM methods.

Deep learning

NASA Astrophysics Data System (ADS)

Lecun, Yann; Bengio, Yoshua; Hinton, Geoffrey

2015-05-01

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

A survey on deep learning in medical image analysis.

PubMed

Litjens, Geert; Kooi, Thijs; Bejnordi, Babak Ehteshami; Setio, Arnaud Arindra Adiyoso; Ciompi, Francesco; Ghafoorian, Mohsen; van der Laak, Jeroen A W M; van Ginneken, Bram; Sánchez, Clara I

2017-12-01

Deep learning algorithms, in particular convolutional networks, have rapidly become a methodology of choice for analyzing medical images. This paper reviews the major deep learning concepts pertinent to medical image analysis and summarizes over 300 contributions to the field, most of which appeared in the last year. We survey the use of deep learning for image classification, object detection, segmentation, registration, and other tasks. Concise overviews are provided of studies per application area: neuro, retinal, pulmonary, digital pathology, breast, cardiac, abdominal, musculoskeletal. We end with a summary of the current state-of-the-art, a critical discussion of open challenges and directions for future research. Copyright © 2017 Elsevier B.V. All rights reserved.

Deep learning.

PubMed

LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey

2015-05-28

Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

Using Student-Centred Learning Environments to Stimulate Deep Approaches to Learning: Factors Encouraging or Discouraging Their Effectiveness

ERIC Educational Resources Information Center

Baeten, Marlies; Kyndt, Eva; Struyven, Katrien; Dochy, Filip

2010-01-01

This review outlines encouraging and discouraging factors in stimulating the adoption of deep approaches to learning in student-centred learning environments. Both encouraging and discouraging factors can be situated in the context of the learning environment, in students' perceptions of that context and in characteristics of the students…

Understanding Cognitive Presence in an Online and Blended Community of Inquiry: Assessing Outcomes and Processes for Deep Approaches to Learning

ERIC Educational Resources Information Center

Akyol, Zehra; Garrison, D. Randy

2011-01-01

This paper focuses on deep and meaningful learning approaches and outcomes associated with online and blended communities of inquiry. Applying mixed methodology for the research design, the study used transcript analysis, learning outcomes, perceived learning, satisfaction, and interviews to assess learning processes and outcomes. The findings for…

MusiteDeep: a deep-learning framework for general and kinase-specific phosphorylation site prediction.

PubMed

Wang, Duolin; Zeng, Shuai; Xu, Chunhui; Qiu, Wangren; Liang, Yanchun; Joshi, Trupti; Xu, Dong

2017-12-15

Computational methods for phosphorylation site prediction play important roles in protein function studies and experimental design. Most existing methods are based on feature extraction, which may result in incomplete or biased features. Deep learning as the cutting-edge machine learning method has the ability to automatically discover complex representations of phosphorylation patterns from the raw sequences, and hence it provides a powerful tool for improvement of phosphorylation site prediction. We present MusiteDeep, the first deep-learning framework for predicting general and kinase-specific phosphorylation sites. MusiteDeep takes raw sequence data as input and uses convolutional neural networks with a novel two-dimensional attention mechanism. It achieves over a 50% relative improvement in the area under the precision-recall curve in general phosphorylation site prediction and obtains competitive results in kinase-specific prediction compared to other well-known tools on the benchmark data. MusiteDeep is provided as an open-source tool available at https://github.com/duolinwang/MusiteDeep. xudong@missouri.edu. Supplementary data are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Teaching Real-World Applications of Business Statistics Using Communication to Scaffold Learning

ERIC Educational Resources Information Center

Green, Gareth P.; Jones, Stacey; Bean, John C.

2015-01-01

Our assessment research suggests that quantitative business courses that rely primarily on algorithmic problem solving may not produce the deep learning required for addressing real-world business problems. This article illustrates a strategy, supported by recent learning theory, for promoting deep learning by moving students gradually from…

Integration of adaptive guided filtering, deep feature learning, and edge-detection techniques for hyperspectral image classification

NASA Astrophysics Data System (ADS)

Wan, Xiaoqing; Zhao, Chunhui; Gao, Bing

2017-11-01

The integration of an edge-preserving filtering technique in the classification of a hyperspectral image (HSI) has been proven effective in enhancing classification performance. This paper proposes an ensemble strategy for HSI classification using an edge-preserving filter along with a deep learning model and edge detection. First, an adaptive guided filter is applied to the original HSI to reduce the noise in degraded images and to extract powerful spectral-spatial features. Second, the extracted features are fed as input to a stacked sparse autoencoder to adaptively exploit more invariant and deep feature representations; then, a random forest classifier is applied to fine-tune the entire pretrained network and determine the classification output. Third, a Prewitt compass operator is further performed on the HSI to extract the edges of the first principal component after dimension reduction. Moreover, the regional growth rule is applied to the resulting edge logical image to determine the local region for each unlabeled pixel. Finally, the categories of the corresponding neighborhood samples are determined in the original classification map; then, the major voting mechanism is implemented to generate the final output. Extensive experiments proved that the proposed method achieves competitive performance compared with several traditional approaches.

Understanding social collaboration between actors and technology in an automated and digitised deep mining environment.

PubMed

Sanda, M-A; Johansson, J; Johansson, B; Abrahamsson, L

2011-10-01

The purpose of this article is to develop knowledge and learning on the best way to automate organisational activities in deep mines that could lead to the creation of harmony between the human, technical and the social system, towards increased productivity. The findings showed that though the introduction of high-level technological tools in the work environment disrupted the social relations developed over time amongst the employees in most situations, the technological tools themselves became substitute social collaborative partners to the employees. It is concluded that, in developing a digitised mining production system, knowledge of the social collaboration between the humans (miners) and the technology they use for their work must be developed. By implication, knowledge of the human's subject-oriented and object-oriented activities should be considered as an important integral resource for developing a better technological, organisational and human interactive subsystem when designing the intelligent automation and digitisation systems for deep mines. STATEMENT OF RELEVANCE: This study focused on understanding the social collaboration between humans and the technologies they use to work in underground mines. The learning provides an added knowledge in designing technologies and work organisations that could better enhance the human-technology interactive and collaborative system in the automation and digitisation of underground mines.

Modeling language and cognition with deep unsupervised learning: a tutorial overview

PubMed Central

Zorzi, Marco; Testolin, Alberto; Stoianov, Ivilin P.

2013-01-01

Deep unsupervised learning in stochastic recurrent neural networks with many layers of hidden units is a recent breakthrough in neural computation research. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. In this article we discuss the theoretical foundations of this approach and we review key issues related to training, testing and analysis of deep networks for modeling language and cognitive processing. The classic letter and word perception problem of McClelland and Rumelhart (1981) is used as a tutorial example to illustrate how structured and abstract representations may emerge from deep generative learning. We argue that the focus on deep architectures and generative (rather than discriminative) learning represents a crucial step forward for the connectionist modeling enterprise, because it offers a more plausible model of cortical learning as well as a way to bridge the gap between emergentist connectionist models and structured Bayesian models of cognition. PMID:23970869

Modeling language and cognition with deep unsupervised learning: a tutorial overview.

PubMed

Zorzi, Marco; Testolin, Alberto; Stoianov, Ivilin P

2013-01-01

Deep unsupervised learning in stochastic recurrent neural networks with many layers of hidden units is a recent breakthrough in neural computation research. These networks build a hierarchy of progressively more complex distributed representations of the sensory data by fitting a hierarchical generative model. In this article we discuss the theoretical foundations of this approach and we review key issues related to training, testing and analysis of deep networks for modeling language and cognitive processing. The classic letter and word perception problem of McClelland and Rumelhart (1981) is used as a tutorial example to illustrate how structured and abstract representations may emerge from deep generative learning. We argue that the focus on deep architectures and generative (rather than discriminative) learning represents a crucial step forward for the connectionist modeling enterprise, because it offers a more plausible model of cortical learning as well as a way to bridge the gap between emergentist connectionist models and structured Bayesian models of cognition.

Action-Driven Visual Object Tracking With Deep Reinforcement Learning.

PubMed

Yun, Sangdoo; Choi, Jongwon; Yoo, Youngjoon; Yun, Kimin; Choi, Jin Young

2018-06-01

In this paper, we propose an efficient visual tracker, which directly captures a bounding box containing the target object in a video by means of sequential actions learned using deep neural networks. The proposed deep neural network to control tracking actions is pretrained using various training video sequences and fine-tuned during actual tracking for online adaptation to a change of target and background. The pretraining is done by utilizing deep reinforcement learning (RL) as well as supervised learning. The use of RL enables even partially labeled data to be successfully utilized for semisupervised learning. Through the evaluation of the object tracking benchmark data set, the proposed tracker is validated to achieve a competitive performance at three times the speed of existing deep network-based trackers. The fast version of the proposed method, which operates in real time on graphics processing unit, outperforms the state-of-the-art real-time trackers with an accuracy improvement of more than 8%.

Sublayer-Specific Coding Dynamics during Spatial Navigation and Learning in Hippocampal Area CA1.

PubMed

Danielson, Nathan B; Zaremba, Jeffrey D; Kaifosh, Patrick; Bowler, John; Ladow, Max; Losonczy, Attila

2016-08-03

The mammalian hippocampus is critical for spatial information processing and episodic memory. Its primary output cells, CA1 pyramidal cells (CA1 PCs), vary in genetics, morphology, connectivity, and electrophysiological properties. It is therefore possible that distinct CA1 PC subpopulations encode different features of the environment and differentially contribute to learning. To test this hypothesis, we optically monitored activity in deep and superficial CA1 PCs segregated along the radial axis of the mouse hippocampus and assessed the relationship between sublayer dynamics and learning. Superficial place maps were more stable than deep during head-fixed exploration. Deep maps, however, were preferentially stabilized during goal-oriented learning, and representation of the reward zone by deep cells predicted task performance. These findings demonstrate that superficial CA1 PCs provide a more stable map of an environment, while their counterparts in the deep sublayer provide a more flexible representation that is shaped by learning about salient features in the environment. VIDEO ABSTRACT. Copyright © 2016 Elsevier Inc. All rights reserved.

Efficient collective swimming by harnessing vortices through deep reinforcement learning.

PubMed

Verma, Siddhartha; Novati, Guido; Koumoutsakos, Petros

2018-06-05

Fish in schooling formations navigate complex flow fields replete with mechanical energy in the vortex wakes of their companions. Their schooling behavior has been associated with evolutionary advantages including energy savings, yet the underlying physical mechanisms remain unknown. We show that fish can improve their sustained propulsive efficiency by placing themselves in appropriate locations in the wake of other swimmers and intercepting judiciously their shed vortices. This swimming strategy leads to collective energy savings and is revealed through a combination of high-fidelity flow simulations with a deep reinforcement learning (RL) algorithm. The RL algorithm relies on a policy defined by deep, recurrent neural nets, with long-short-term memory cells, that are essential for capturing the unsteadiness of the two-way interactions between the fish and the vortical flow field. Surprisingly, we find that swimming in-line with a leader is not associated with energetic benefits for the follower. Instead, "smart swimmer(s)" place themselves at off-center positions, with respect to the axis of the leader(s) and deform their body to synchronize with the momentum of the oncoming vortices, thus enhancing their swimming efficiency at no cost to the leader(s). The results confirm that fish may harvest energy deposited in vortices and support the conjecture that swimming in formation is energetically advantageous. Moreover, this study demonstrates that deep RL can produce navigation algorithms for complex unsteady and vortical flow fields, with promising implications for energy savings in autonomous robotic swarms.

The Use of Deep and Surface Learning Strategies among Students Learning English as a Foreign Language in an Internet Environment

ERIC Educational Resources Information Center

Aharony, Noa

2006-01-01

Background: The learning context is learning English in an Internet environment. The examination of this learning process was based on the Biggs and Moore's teaching-learning model (Biggs & Moore, 1993). Aim: The research aims to explore the use of the deep and surface strategies in an Internet environment among EFL students who come from…

A deep learning framework for financial time series using stacked autoencoders and long-short term memory

PubMed Central

Bao, Wei; Rao, Yulei

2017-01-01

The application of deep learning approaches to finance has received a great deal of attention from both investors and researchers. This study presents a novel deep learning framework where wavelet transforms (WT), stacked autoencoders (SAEs) and long-short term memory (LSTM) are combined for stock price forecasting. The SAEs for hierarchically extracted deep features is introduced into stock price forecasting for the first time. The deep learning framework comprises three stages. First, the stock price time series is decomposed by WT to eliminate noise. Second, SAEs is applied to generate deep high-level features for predicting the stock price. Third, high-level denoising features are fed into LSTM to forecast the next day’s closing price. Six market indices and their corresponding index futures are chosen to examine the performance of the proposed model. Results show that the proposed model outperforms other similar models in both predictive accuracy and profitability performance. PMID:28708865

Computer aided lung cancer diagnosis with deep learning algorithms

NASA Astrophysics Data System (ADS)

Sun, Wenqing; Zheng, Bin; Qian, Wei

2016-03-01

Deep learning is considered as a popular and powerful method in pattern recognition and classification. However, there are not many deep structured applications used in medical imaging diagnosis area, because large dataset is not always available for medical images. In this study we tested the feasibility of using deep learning algorithms for lung cancer diagnosis with the cases from Lung Image Database Consortium (LIDC) database. The nodules on each computed tomography (CT) slice were segmented according to marks provided by the radiologists. After down sampling and rotating we acquired 174412 samples with 52 by 52 pixel each and the corresponding truth files. Three deep learning algorithms were designed and implemented, including Convolutional Neural Network (CNN), Deep Belief Networks (DBNs), Stacked Denoising Autoencoder (SDAE). To compare the performance of deep learning algorithms with traditional computer aided diagnosis (CADx) system, we designed a scheme with 28 image features and support vector machine. The accuracies of CNN, DBNs, and SDAE are 0.7976, 0.8119, and 0.7929, respectively; the accuracy of our designed traditional CADx is 0.7940, which is slightly lower than CNN and DBNs. We also noticed that the mislabeled nodules using DBNs are 4% larger than using traditional CADx, this might be resulting from down sampling process lost some size information of the nodules.

Learning approach among health sciences students in a medical college in Nepal: a cross-sectional study.

PubMed

Shah, Dev Kumar; Yadav, Ram Lochan; Sharma, Deepak; Yadav, Prakash Kumar; Sapkota, Niraj Khatri; Jha, Rajesh Kumar; Islam, Md Nazrul

2016-01-01

Many factors shape the quality of learning. The intrinsically motivated students adopt a deep approach to learning, while students who fear failure in assessments adopt a surface approach to learning. In the area of health science education in Nepal, there is still a lack of studies on learning approach that can be used to transform the students to become better learners and improve the effectiveness of teaching. Therefore, we aimed to explore the learning approaches among medical, dental, and nursing students of Chitwan Medical College, Nepal using Biggs's Revised Two-Factor Study Process Questionnaire (R-SPQ-2F) after testing its reliability. R-SPQ-2F containing 20 items represented two main scales of learning approaches, deep and surface, with four subscales: deep motive, deep strategy, surface motive, and surface strategy. Each subscale had five items and each item was rated on a 5-point Likert scale. The data were analyzed using Student's t-test and analysis of variance. Reliability of the administered questionnaire was checked using Cronbach's alpha. The Cronbach's alpha value (0.6) for 20 items of R-SPQ-2F was found to be acceptable for its use. The participants predominantly had a deep approach to learning regardless of their age and sex (deep: 32.62±6.33 versus surface: 25.14±6.81, P<0.001). The level of deep approach among medical students (33.26±6.40) was significantly higher than among dental (31.71±6.51) and nursing (31.36±4.72) students. In comparison to first-year students, deep approach among second-year medical (34.63±6.51 to 31.73±5.93; P<0.001) and dental (33.47±6.73 to 29.09±5.62; P=0.002) students was found to be significantly decreased. On the other hand, surface approach significantly increased (25.55±8.19 to 29.34±6.25; P=0.023) among second-year dental students compared to first-year dental students. Medical students were found to adopt a deeper approach to learning than dental and nursing students. However, irrespective of disciplines and personal characteristics of participants, the primarily deep learning approach was found to be shifting progressively toward a surface approach after completion of an academic year, which should be avoided.

Deep learning guided stroke management: a review of clinical applications.

PubMed

Feng, Rui; Badgeley, Marcus; Mocco, J; Oermann, Eric K

2018-04-01

Stroke is a leading cause of long-term disability, and outcome is directly related to timely intervention. Not all patients benefit from rapid intervention, however. Thus a significant amount of attention has been paid to using neuroimaging to assess potential benefit by identifying areas of ischemia that have not yet experienced cellular death. The perfusion-diffusion mismatch, is used as a simple metric for potential benefit with timely intervention, yet penumbral patterns provide an inaccurate predictor of clinical outcome. Machine learning research in the form of deep learning (artificial intelligence) techniques using deep neural networks (DNNs) excel at working with complex inputs. The key areas where deep learning may be imminently applied to stroke management are image segmentation, automated featurization (radiomics), and multimodal prognostication. The application of convolutional neural networks, the family of DNN architectures designed to work with images, to stroke imaging data is a perfect match between a mature deep learning technique and a data type that is naturally suited to benefit from deep learning's strengths. These powerful tools have opened up exciting opportunities for data-driven stroke management for acute intervention and for guiding prognosis. Deep learning techniques are useful for the speed and power of results they can deliver and will become an increasingly standard tool in the modern stroke specialist's arsenal for delivering personalized medicine to patients with ischemic stroke. © Article author(s) (or their employer(s) unless otherwise stated in the text of the article) 2018. All rights reserved. No commercial use is permitted unless otherwise expressly granted.

Fifty years of computer analysis in chest imaging: rule-based, machine learning, deep learning.

PubMed

van Ginneken, Bram

2017-03-01

Half a century ago, the term "computer-aided diagnosis" (CAD) was introduced in the scientific literature. Pulmonary imaging, with chest radiography and computed tomography, has always been one of the focus areas in this field. In this study, I describe how machine learning became the dominant technology for tackling CAD in the lungs, generally producing better results than do classical rule-based approaches, and how the field is now rapidly changing: in the last few years, we have seen how even better results can be obtained with deep learning. The key differences among rule-based processing, machine learning, and deep learning are summarized and illustrated for various applications of CAD in the chest.

Quantum neuromorphic hardware for quantum artificial intelligence

NASA Astrophysics Data System (ADS)

Prati, Enrico

2017-08-01

The development of machine learning methods based on deep learning boosted the field of artificial intelligence towards unprecedented achievements and application in several fields. Such prominent results were made in parallel with the first successful demonstrations of fault tolerant hardware for quantum information processing. To which extent deep learning can take advantage of the existence of a hardware based on qubits behaving as a universal quantum computer is an open question under investigation. Here I review the convergence between the two fields towards implementation of advanced quantum algorithms, including quantum deep learning.

A Comparative Study of Learning Strategies Used by Romanian and Hungarian Preuniversity Students in Science Learning

ERIC Educational Resources Information Center

Lingvay, Mónika; Timofte, Roxana S.; Ciascai, Liliana; Predescu, Constantin

2015-01-01

Development of pupils' deep learning approach is an important goal of education nowadays, considering that a deep learning approach is mediating conceptual understanding and transfer. Different performance at PISA tests of Romanian and Hungarian pupils cause us to commence a study for the analysis of learning approaches employed by these pupils.…

Making Information Systems Less Scrugged: Reflecting on the Processes of Change in Teaching and Learning

ERIC Educational Resources Information Center

Houghton, Luke; Ruth, Alison

2010-01-01

Deep and shallow learner approaches are useful for different purposes. Shallow learning can be good where fact memorization is appropriate, learning how to swim or play the guitar for example. Deep learning is much more appropriate when the learning material present involves going beyond simple facts and into what lies below the surface. When…

Is the University System in Australia Producing Deep Thinkers?

ERIC Educational Resources Information Center

Lake, Warren W.; Boyd, William E.

2015-01-01

Teaching and learning research since the 1980s has established a trend in students' learning approach tendencies, characterised by decreasing surface learning and increasing deep learning with increasing age. This is an important trend in higher education, especially at a time of increasing numbers of older students: are we graduating more deep…

How Enterprise Education Can Promote Deep Learning to Improve Student Employability

ERIC Educational Resources Information Center

Moon, Rob; Curtis, Vic; Dupernex, Simon

2013-01-01

This paper focuses on identifying the approaches students take to their learning, with particular regard to issues of enterprise, entrepreneurship and innovation when comparing the traditional lecture format to a more applied, practice-based case study format. The notions of deep and surface learning are used to explain student learning. More…

Emotion and the Internet: A Model of Learning

ERIC Educational Resources Information Center

Tran, Thuhang T.; Ward, Cheryl B.

2005-01-01

This conceptual paper examines the link between emotion and surface-deep learning in the context of the international business curriculum. We propose that 1) emotion and learning have a curvilinear relationship, and 2) the reflective abilities and attitude transformations related to deep-level learning can only arise if the student is emotionally…

Changing Students' Approaches to Learning: A Two-Year Study within a University Teacher Training Course

ERIC Educational Resources Information Center

Gijbels, David; Coertjens, Liesje; Vanthournout, Gert; Struyf, Elke; Van Petegem, Peter

2009-01-01

Inciting a deep approach to learning in students is difficult. The present research poses two questions: can a constructivist learning-assessment environment change students' approaches towards a more deep approach? What effect does additional feedback have on the changes in learning approaches? Two cohorts of students completed questionnaires…

A deep learning method for lincRNA detection using auto-encoder algorithm.

PubMed

Yu, Ning; Yu, Zeng; Pan, Yi

2017-12-06

RNA sequencing technique (RNA-seq) enables scientists to develop novel data-driven methods for discovering more unidentified lincRNAs. Meantime, knowledge-based technologies are experiencing a potential revolution ignited by the new deep learning methods. By scanning the newly found data set from RNA-seq, scientists have found that: (1) the expression of lincRNAs appears to be regulated, that is, the relevance exists along the DNA sequences; (2) lincRNAs contain some conversed patterns/motifs tethered together by non-conserved regions. The two evidences give the reasoning for adopting knowledge-based deep learning methods in lincRNA detection. Similar to coding region transcription, non-coding regions are split at transcriptional sites. However, regulatory RNAs rather than message RNAs are generated. That is, the transcribed RNAs participate the biological process as regulatory units instead of generating proteins. Identifying these transcriptional regions from non-coding regions is the first step towards lincRNA recognition. The auto-encoder method achieves 100% and 92.4% prediction accuracy on transcription sites over the putative data sets. The experimental results also show the excellent performance of predictive deep neural network on the lincRNA data sets compared with support vector machine and traditional neural network. In addition, it is validated through the newly discovered lincRNA data set and one unreported transcription site is found by feeding the whole annotated sequences through the deep learning machine, which indicates that deep learning method has the extensive ability for lincRNA prediction. The transcriptional sequences of lincRNAs are collected from the annotated human DNA genome data. Subsequently, a two-layer deep neural network is developed for the lincRNA detection, which adopts the auto-encoder algorithm and utilizes different encoding schemes to obtain the best performance over intergenic DNA sequence data. Driven by those newly annotated lincRNA data, deep learning methods based on auto-encoder algorithm can exert their capability in knowledge learning in order to capture the useful features and the information correlation along DNA genome sequences for lincRNA detection. As our knowledge, this is the first application to adopt the deep learning techniques for identifying lincRNA transcription sequences.

Students' Approaches to Learning in Problem-Based Learning: Taking into Account Professional Behavior in the Tutorial Groups, Self-Study Time, and Different Assessment Aspects

ERIC Educational Resources Information Center

Loyens, Sofie M. M.; Gijbels, David; Coertjens, Liesje; Cote, Daniel J.

2013-01-01

Problem-based learning (PBL) represents a major development in higher educational practice and is believed to promote deep learning in students. However, empirical findings on the promotion of deep learning in PBL remain unclear. The aim of the present study is to investigate the relationships between students' approaches to learning (SAL) and…

Twelve tips for facilitating Millennials' learning.

PubMed

Roberts, David H; Newman, Lori R; Schwartzstein, Richard M

2012-01-01

The current, so-called "Millennial" generation of learners is frequently characterized as having deep understanding of, and appreciation for, technology and social connectedness. This generation of learners has also been molded by a unique set of cultural influences that are essential for medical educators to consider in all aspects of their teaching, including curriculum design, student assessment, and interactions between faculty and learners.  The following tips outline an approach to facilitating learning of our current generation of medical trainees.  The method is based on the available literature and the authors' experiences with Millennial Learners in medical training.  The 12 tips provide detailed approaches and specific strategies for understanding and engaging Millennial Learners and enhancing their learning.  With an increased understanding of the characteristics of the current generation of medical trainees, faculty will be better able to facilitate learning and optimize interactions with Millennial Learners.

Iterative deep convolutional encoder-decoder network for medical image segmentation.

PubMed

Jung Uk Kim; Hak Gu Kim; Yong Man Ro

2017-07-01

In this paper, we propose a novel medical image segmentation using iterative deep learning framework. We have combined an iterative learning approach and an encoder-decoder network to improve segmentation results, which enables to precisely localize the regions of interest (ROIs) including complex shapes or detailed textures of medical images in an iterative manner. The proposed iterative deep convolutional encoder-decoder network consists of two main paths: convolutional encoder path and convolutional decoder path with iterative learning. Experimental results show that the proposed iterative deep learning framework is able to yield excellent medical image segmentation performances for various medical images. The effectiveness of the proposed method has been proved by comparing with other state-of-the-art medical image segmentation methods.

Deep ECGNet: An Optimal Deep Learning Framework for Monitoring Mental Stress Using Ultra Short-Term ECG Signals.

PubMed

Hwang, Bosun; You, Jiwoo; Vaessen, Thomas; Myin-Germeys, Inez; Park, Cheolsoo; Zhang, Byoung-Tak

2018-02-08

Stress recognition using electrocardiogram (ECG) signals requires the intractable long-term heart rate variability (HRV) parameter extraction process. This study proposes a novel deep learning framework to recognize the stressful states, the Deep ECGNet, using ultra short-term raw ECG signals without any feature engineering methods. The Deep ECGNet was developed through various experiments and analysis of ECG waveforms. We proposed the optimal recurrent and convolutional neural networks architecture, and also the optimal convolution filter length (related to the P, Q, R, S, and T wave durations of ECG) and pooling length (related to the heart beat period) based on the optimization experiments and analysis on the waveform characteristics of ECG signals. The experiments were also conducted with conventional methods using HRV parameters and frequency features as a benchmark test. The data used in this study were obtained from Kwangwoon University in Korea (13 subjects, Case 1) and KU Leuven University in Belgium (9 subjects, Case 2). Experiments were designed according to various experimental protocols to elicit stressful conditions. The proposed framework to recognize stress conditions, the Deep ECGNet, outperformed the conventional approaches with the highest accuracy of 87.39% for Case 1 and 73.96% for Case 2, respectively, that is, 16.22% and 10.98% improvements compared with those of the conventional HRV method. We proposed an optimal deep learning architecture and its parameters for stress recognition, and the theoretical consideration on how to design the deep learning structure based on the periodic patterns of the raw ECG data. Experimental results in this study have proved that the proposed deep learning model, the Deep ECGNet, is an optimal structure to recognize the stress conditions using ultra short-term ECG data.

Learning better deep features for the prediction of occult invasive disease in ductal carcinoma in situ through transfer learning

NASA Astrophysics Data System (ADS)

Shi, Bibo; Hou, Rui; Mazurowski, Maciej A.; Grimm, Lars J.; Ren, Yinhao; Marks, Jeffrey R.; King, Lorraine M.; Maley, Carlo C.; Hwang, E. Shelley; Lo, Joseph Y.

2018-02-01

Purpose: To determine whether domain transfer learning can improve the performance of deep features extracted from digital mammograms using a pre-trained deep convolutional neural network (CNN) in the prediction of occult invasive disease for patients with ductal carcinoma in situ (DCIS) on core needle biopsy. Method: In this study, we collected digital mammography magnification views for 140 patients with DCIS at biopsy, 35 of which were subsequently upstaged to invasive cancer. We utilized a deep CNN model that was pre-trained on two natural image data sets (ImageNet and DTD) and one mammographic data set (INbreast) as the feature extractor, hypothesizing that these data sets are increasingly more similar to our target task and will lead to better representations of deep features to describe DCIS lesions. Through a statistical pooling strategy, three sets of deep features were extracted using the CNNs at different levels of convolutional layers from the lesion areas. A logistic regression classifier was then trained to predict which tumors contain occult invasive disease. The generalization performance was assessed and compared using repeated random sub-sampling validation and receiver operating characteristic (ROC) curve analysis. Result: The best performance of deep features was from CNN model pre-trained on INbreast, and the proposed classifier using this set of deep features was able to achieve a median classification performance of ROC-AUC equal to 0.75, which is significantly better (p<=0.05) than the performance of deep features extracted using ImageNet data set (ROCAUC = 0.68). Conclusion: Transfer learning is helpful for learning a better representation of deep features, and improves the prediction of occult invasive disease in DCIS.

Wishart Deep Stacking Network for Fast POLSAR Image Classification.

PubMed

Jiao, Licheng; Liu, Fang

2016-05-11

Inspired by the popular deep learning architecture - Deep Stacking Network (DSN), a specific deep model for polarimetric synthetic aperture radar (POLSAR) image classification is proposed in this paper, which is named as Wishart Deep Stacking Network (W-DSN). First of all, a fast implementation of Wishart distance is achieved by a special linear transformation, which speeds up the classification of POLSAR image and makes it possible to use this polarimetric information in the following Neural Network (NN). Then a single-hidden-layer neural network based on the fast Wishart distance is defined for POLSAR image classification, which is named as Wishart Network (WN) and improves the classification accuracy. Finally, a multi-layer neural network is formed by stacking WNs, which is in fact the proposed deep learning architecture W-DSN for POLSAR image classification and improves the classification accuracy further. In addition, the structure of WN can be expanded in a straightforward way by adding hidden units if necessary, as well as the structure of the W-DSN. As a preliminary exploration on formulating specific deep learning architecture for POLSAR image classification, the proposed methods may establish a simple but clever connection between POLSAR image interpretation and deep learning. The experiment results tested on real POLSAR image show that the fast implementation of Wishart distance is very efficient (a POLSAR image with 768000 pixels can be classified in 0.53s), and both the single-hidden-layer architecture WN and the deep learning architecture W-DSN for POLSAR image classification perform well and work efficiently.

Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding.

PubMed

Min, Xu; Zeng, Wanwen; Chen, Ning; Chen, Ting; Jiang, Rui

2017-07-15

Experimental techniques for measuring chromatin accessibility are expensive and time consuming, appealing for the development of computational approaches to predict open chromatin regions from DNA sequences. Along this direction, existing methods fall into two classes: one based on handcrafted k -mer features and the other based on convolutional neural networks. Although both categories have shown good performance in specific applications thus far, there still lacks a comprehensive framework to integrate useful k -mer co-occurrence information with recent advances in deep learning. We fill this gap by addressing the problem of chromatin accessibility prediction with a convolutional Long Short-Term Memory (LSTM) network with k -mer embedding. We first split DNA sequences into k -mers and pre-train k -mer embedding vectors based on the co-occurrence matrix of k -mers by using an unsupervised representation learning approach. We then construct a supervised deep learning architecture comprised of an embedding layer, three convolutional layers and a Bidirectional LSTM (BLSTM) layer for feature learning and classification. We demonstrate that our method gains high-quality fixed-length features from variable-length sequences and consistently outperforms baseline methods. We show that k -mer embedding can effectively enhance model performance by exploring different embedding strategies. We also prove the efficacy of both the convolution and the BLSTM layers by comparing two variations of the network architecture. We confirm the robustness of our model to hyper-parameters by performing sensitivity analysis. We hope our method can eventually reinforce our understanding of employing deep learning in genomic studies and shed light on research regarding mechanisms of chromatin accessibility. The source code can be downloaded from https://github.com/minxueric/ismb2017_lstm . tingchen@tsinghua.edu.cn or ruijiang@tsinghua.edu.cn. Supplementary materials are available at Bioinformatics online. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Chromatin accessibility prediction via convolutional long short-term memory networks with k-mer embedding

PubMed Central

Min, Xu; Zeng, Wanwen; Chen, Ning; Chen, Ting; Jiang, Rui

2017-01-01

Abstract Motivation: Experimental techniques for measuring chromatin accessibility are expensive and time consuming, appealing for the development of computational approaches to predict open chromatin regions from DNA sequences. Along this direction, existing methods fall into two classes: one based on handcrafted k-mer features and the other based on convolutional neural networks. Although both categories have shown good performance in specific applications thus far, there still lacks a comprehensive framework to integrate useful k-mer co-occurrence information with recent advances in deep learning. Results: We fill this gap by addressing the problem of chromatin accessibility prediction with a convolutional Long Short-Term Memory (LSTM) network with k-mer embedding. We first split DNA sequences into k-mers and pre-train k-mer embedding vectors based on the co-occurrence matrix of k-mers by using an unsupervised representation learning approach. We then construct a supervised deep learning architecture comprised of an embedding layer, three convolutional layers and a Bidirectional LSTM (BLSTM) layer for feature learning and classification. We demonstrate that our method gains high-quality fixed-length features from variable-length sequences and consistently outperforms baseline methods. We show that k-mer embedding can effectively enhance model performance by exploring different embedding strategies. We also prove the efficacy of both the convolution and the BLSTM layers by comparing two variations of the network architecture. We confirm the robustness of our model to hyper-parameters by performing sensitivity analysis. We hope our method can eventually reinforce our understanding of employing deep learning in genomic studies and shed light on research regarding mechanisms of chromatin accessibility. Availability and implementation: The source code can be downloaded from https://github.com/minxueric/ismb2017_lstm. Contact: tingchen@tsinghua.edu.cn or ruijiang@tsinghua.edu.cn Supplementary information: Supplementary materials are available at Bioinformatics online. PMID:28881969

Deep generative learning for automated EHR diagnosis of traditional Chinese medicine.

PubMed

Liang, Zhaohui; Liu, Jun; Ou, Aihua; Zhang, Honglai; Li, Ziping; Huang, Jimmy Xiangji

2018-05-04

Computer-aided medical decision-making (CAMDM) is the method to utilize massive EMR data as both empirical and evidence support for the decision procedure of healthcare activities. Well-developed information infrastructure, such as hospital information systems and disease surveillance systems, provides abundant data for CAMDM. However, the complexity of EMR data with abstract medical knowledge makes the conventional model incompetent for the analysis. Thus a deep belief networks (DBN) based model is proposed to simulate the information analysis and decision-making procedure in medical practice. The purpose of this paper is to evaluate a deep learning architecture as an effective solution for CAMDM. A two-step model is applied in our study. At the first step, an optimized seven-layer deep belief network (DBN) is applied as an unsupervised learning algorithm to perform model training to acquire feature representation. Then a support vector machine model is adopted to DBN at the second step of the supervised learning. There are two data sets used in the experiments. One is a plain text data set indexed by medical experts. The other is a structured dataset on primary hypertension. The data are randomly divided to generate the training set for the unsupervised learning and the testing set for the supervised learning. The model performance is evaluated by the statistics of mean and variance, the average precision and coverage on the data sets. Two conventional shallow models (support vector machine / SVM and decision tree / DT) are applied as the comparisons to show the superiority of our proposed approach. The deep learning (DBN + SVM) model outperforms simple SVM and DT on two data sets in terms of all the evaluation measures, which confirms our motivation that the deep model is good at capturing the key features with less dependence when the index is built up by manpower. Our study shows the two-step deep learning model achieves high performance for medical information retrieval over the conventional shallow models. It is able to capture the features of both plain text and the highly-structured database of EMR data. The performance of the deep model is superior to the conventional shallow learning models such as SVM and DT. It is an appropriate knowledge-learning model for information retrieval of EMR system. Therefore, deep learning provides a good solution to improve the performance of CAMDM systems. Copyright © 2018. Published by Elsevier B.V.

Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set.

PubMed

Lenselink, Eelke B; Ten Dijke, Niels; Bongers, Brandon; Papadatos, George; van Vlijmen, Herman W T; Kowalczyk, Wojtek; IJzerman, Adriaan P; van Westen, Gerard J P

2017-08-14

The increase of publicly available bioactivity data in recent years has fueled and catalyzed research in chemogenomics, data mining, and modeling approaches. As a direct result, over the past few years a multitude of different methods have been reported and evaluated, such as target fishing, nearest neighbor similarity-based methods, and Quantitative Structure Activity Relationship (QSAR)-based protocols. However, such studies are typically conducted on different datasets, using different validation strategies, and different metrics. In this study, different methods were compared using one single standardized dataset obtained from ChEMBL, which is made available to the public, using standardized metrics (BEDROC and Matthews Correlation Coefficient). Specifically, the performance of Naïve Bayes, Random Forests, Support Vector Machines, Logistic Regression, and Deep Neural Networks was assessed using QSAR and proteochemometric (PCM) methods. All methods were validated using both a random split validation and a temporal validation, with the latter being a more realistic benchmark of expected prospective execution. Deep Neural Networks are the top performing classifiers, highlighting the added value of Deep Neural Networks over other more conventional methods. Moreover, the best method ('DNN_PCM') performed significantly better at almost one standard deviation higher than the mean performance. Furthermore, Multi-task and PCM implementations were shown to improve performance over single task Deep Neural Networks. Conversely, target prediction performed almost two standard deviations under the mean performance. Random Forests, Support Vector Machines, and Logistic Regression performed around mean performance. Finally, using an ensemble of DNNs, alongside additional tuning, enhanced the relative performance by another 27% (compared with unoptimized 'DNN_PCM'). Here, a standardized set to test and evaluate different machine learning algorithms in the context of multi-task learning is offered by providing the data and the protocols. Graphical Abstract .

A comparative study of two prediction models for brain tumor progression

NASA Astrophysics Data System (ADS)

Zhou, Deqi; Tran, Loc; Wang, Jihong; Li, Jiang

2015-03-01

MR diffusion tensor imaging (DTI) technique together with traditional T1 or T2 weighted MRI scans supplies rich information sources for brain cancer diagnoses. These images form large-scale, high-dimensional data sets. Due to the fact that significant correlations exist among these images, we assume low-dimensional geometry data structures (manifolds) are embedded in the high-dimensional space. Those manifolds might be hidden from radiologists because it is challenging for human experts to interpret high-dimensional data. Identification of the manifold is a critical step for successfully analyzing multimodal MR images. We have developed various manifold learning algorithms (Tran et al. 2011; Tran et al. 2013) for medical image analysis. This paper presents a comparative study of an incremental manifold learning scheme (Tran. et al. 2013) versus the deep learning model (Hinton et al. 2006) in the application of brain tumor progression prediction. The incremental manifold learning is a variant of manifold learning algorithm to handle large-scale datasets in which a representative subset of original data is sampled first to construct a manifold skeleton and remaining data points are then inserted into the skeleton by following their local geometry. The incremental manifold learning algorithm aims at mitigating the computational burden associated with traditional manifold learning methods for large-scale datasets. Deep learning is a recently developed multilayer perceptron model that has achieved start-of-the-art performances in many applications. A recent technique named "Dropout" can further boost the deep model by preventing weight coadaptation to avoid over-fitting (Hinton et al. 2012). We applied the two models on multiple MRI scans from four brain tumor patients to predict tumor progression and compared the performances of the two models in terms of average prediction accuracy, sensitivity, specificity and precision. The quantitative performance metrics were calculated as average over the four patients. Experimental results show that both the manifold learning and deep neural network models produced better results compared to using raw data and principle component analysis (PCA), and the deep learning model is a better method than manifold learning on this data set. The averaged sensitivity and specificity by deep learning are comparable with these by the manifold learning approach while its precision is considerably higher. This means that the predicted abnormal points by deep learning are more likely to correspond to the actual progression region.

Evaluation of Deep Learning Based Stereo Matching Methods: from Ground to Aerial Images

NASA Astrophysics Data System (ADS)

Liu, J.; Ji, S.; Zhang, C.; Qin, Z.

2018-05-01

Dense stereo matching has been extensively studied in photogrammetry and computer vision. In this paper we evaluate the application of deep learning based stereo methods, which were raised from 2016 and rapidly spread, on aerial stereos other than ground images that are commonly used in computer vision community. Two popular methods are evaluated. One learns matching cost with a convolutional neural network (known as MC-CNN); the other produces a disparity map in an end-to-end manner by utilizing both geometry and context (known as GC-net). First, we evaluate the performance of the deep learning based methods for aerial stereo images by a direct model reuse. The models pre-trained on KITTI 2012, KITTI 2015 and Driving datasets separately, are directly applied to three aerial datasets. We also give the results of direct training on target aerial datasets. Second, the deep learning based methods are compared to the classic stereo matching method, Semi-Global Matching(SGM), and a photogrammetric software, SURE, on the same aerial datasets. Third, transfer learning strategy is introduced to aerial image matching based on the assumption of a few target samples available for model fine tuning. It experimentally proved that the conventional methods and the deep learning based methods performed similarly, and the latter had greater potential to be explored.

Deep Learning for Automated Extraction of Primary Sites From Cancer Pathology Reports.

PubMed

Qiu, John X; Yoon, Hong-Jun; Fearn, Paul A; Tourassi, Georgia D

2018-01-01

Pathology reports are a primary source of information for cancer registries which process high volumes of free-text reports annually. Information extraction and coding is a manual, labor-intensive process. In this study, we investigated deep learning and a convolutional neural network (CNN), for extracting ICD-O-3 topographic codes from a corpus of breast and lung cancer pathology reports. We performed two experiments, using a CNN and a more conventional term frequency vector approach, to assess the effects of class prevalence and inter-class transfer learning. The experiments were based on a set of 942 pathology reports with human expert annotations as the gold standard. CNN performance was compared against a more conventional term frequency vector space approach. We observed that the deep learning models consistently outperformed the conventional approaches in the class prevalence experiment, resulting in micro- and macro-F score increases of up to 0.132 and 0.226, respectively, when class labels were well populated. Specifically, the best performing CNN achieved a micro-F score of 0.722 over 12 ICD-O-3 topography codes. Transfer learning provided a consistent but modest performance boost for the deep learning methods but trends were contingent on the CNN method and cancer site. These encouraging results demonstrate the potential of deep learning for automated abstraction of pathology reports.

A Deep Learning Approach for Fault Diagnosis of Induction Motors in Manufacturing

NASA Astrophysics Data System (ADS)

Shao, Si-Yu; Sun, Wen-Jun; Yan, Ru-Qiang; Wang, Peng; Gao, Robert X.

2017-11-01

Extracting features from original signals is a key procedure for traditional fault diagnosis of induction motors, as it directly influences the performance of fault recognition. However, high quality features need expert knowledge and human intervention. In this paper, a deep learning approach based on deep belief networks (DBN) is developed to learn features from frequency distribution of vibration signals with the purpose of characterizing working status of induction motors. It combines feature extraction procedure with classification task together to achieve automated and intelligent fault diagnosis. The DBN model is built by stacking multiple-units of restricted Boltzmann machine (RBM), and is trained using layer-by-layer pre-training algorithm. Compared with traditional diagnostic approaches where feature extraction is needed, the presented approach has the ability of learning hierarchical representations, which are suitable for fault classification, directly from frequency distribution of the measurement data. The structure of the DBN model is investigated as the scale and depth of the DBN architecture directly affect its classification performance. Experimental study conducted on a machine fault simulator verifies the effectiveness of the deep learning approach for fault diagnosis of induction motors. This research proposes an intelligent diagnosis method for induction motor which utilizes deep learning model to automatically learn features from sensor data and realize working status recognition.

The cerebellum: a neuronal learning machine?

NASA Technical Reports Server (NTRS)

Raymond, J. L.; Lisberger, S. G.; Mauk, M. D.

1996-01-01

Comparison of two seemingly quite different behaviors yields a surprisingly consistent picture of the role of the cerebellum in motor learning. Behavioral and physiological data about classical conditioning of the eyelid response and motor learning in the vestibulo-ocular reflex suggests that (i) plasticity is distributed between the cerebellar cortex and the deep cerebellar nuclei; (ii) the cerebellar cortex plays a special role in learning the timing of movement; and (iii) the cerebellar cortex guides learning in the deep nuclei, which may allow learning to be transferred from the cortex to the deep nuclei. Because many of the similarities in the data from the two systems typify general features of cerebellar organization, the cerebellar mechanisms of learning in these two systems may represent principles that apply to many motor systems.

A Multiobjective Sparse Feature Learning Model for Deep Neural Networks.

PubMed

Gong, Maoguo; Liu, Jia; Li, Hao; Cai, Qing; Su, Linzhi

2015-12-01

Hierarchical deep neural networks are currently popular learning models for imitating the hierarchical architecture of human brain. Single-layer feature extractors are the bricks to build deep networks. Sparse feature learning models are popular models that can learn useful representations. But most of those models need a user-defined constant to control the sparsity of representations. In this paper, we propose a multiobjective sparse feature learning model based on the autoencoder. The parameters of the model are learnt by optimizing two objectives, reconstruction error and the sparsity of hidden units simultaneously to find a reasonable compromise between them automatically. We design a multiobjective induced learning procedure for this model based on a multiobjective evolutionary algorithm. In the experiments, we demonstrate that the learning procedure is effective, and the proposed multiobjective model can learn useful sparse features.

Sentiment analysis: a comparison of deep learning neural network algorithm with SVM and naϊve Bayes for Indonesian text

NASA Astrophysics Data System (ADS)

Calvin Frans Mariel, Wahyu; Mariyah, Siti; Pramana, Setia

2018-03-01

Deep learning is a new era of machine learning techniques that essentially imitate the structure and function of the human brain. It is a development of deeper Artificial Neural Network (ANN) that uses more than one hidden layer. Deep Learning Neural Network has a great ability on recognizing patterns from various data types such as picture, audio, text, and many more. In this paper, the authors tries to measure that algorithm’s ability by applying it into the text classification. The classification task herein is done by considering the content of sentiment in a text which is also called as sentiment analysis. By using several combinations of text preprocessing and feature extraction techniques, we aim to compare the precise modelling results of Deep Learning Neural Network with the other two commonly used algorithms, the Naϊve Bayes and Support Vector Machine (SVM). This algorithm comparison uses Indonesian text data with balanced and unbalanced sentiment composition. Based on the experimental simulation, Deep Learning Neural Network clearly outperforms the Naϊve Bayes and SVM and offers a better F-1 Score while for the best feature extraction technique which improves that modelling result is Bigram.

De novo peptide sequencing by deep learning

PubMed Central

Tran, Ngoc Hieu; Zhang, Xianglilan; Xin, Lei; Shan, Baozhen; Li, Ming

2017-01-01

De novo peptide sequencing from tandem MS data is the key technology in proteomics for the characterization of proteins, especially for new sequences, such as mAbs. In this study, we propose a deep neural network model, DeepNovo, for de novo peptide sequencing. DeepNovo architecture combines recent advances in convolutional neural networks and recurrent neural networks to learn features of tandem mass spectra, fragment ions, and sequence patterns of peptides. The networks are further integrated with local dynamic programming to solve the complex optimization task of de novo sequencing. We evaluated the method on a wide variety of species and found that DeepNovo considerably outperformed state of the art methods, achieving 7.7–22.9% higher accuracy at the amino acid level and 38.1–64.0% higher accuracy at the peptide level. We further used DeepNovo to automatically reconstruct the complete sequences of antibody light and heavy chains of mouse, achieving 97.5–100% coverage and 97.2–99.5% accuracy, without assisting databases. Moreover, DeepNovo is retrainable to adapt to any sources of data and provides a complete end-to-end training and prediction solution to the de novo sequencing problem. Not only does our study extend the deep learning revolution to a new field, but it also shows an innovative approach in solving optimization problems by using deep learning and dynamic programming. PMID:28720701

Four Major South Korea's Rivers Using Deep Learning Models.

PubMed

Lee, Sangmok; Lee, Donghyun

2018-06-24

Harmful algal blooms are an annual phenomenon that cause environmental damage, economic losses, and disease outbreaks. A fundamental solution to this problem is still lacking, thus, the best option for counteracting the effects of algal blooms is to improve advance warnings (predictions). However, existing physical prediction models have difficulties setting a clear coefficient indicating the relationship between each factor when predicting algal blooms, and many variable data sources are required for the analysis. These limitations are accompanied by high time and economic costs. Meanwhile, artificial intelligence and deep learning methods have become increasingly common in scientific research; attempts to apply the long short-term memory (LSTM) model to environmental research problems are increasing because the LSTM model exhibits good performance for time-series data prediction. However, few studies have applied deep learning models or LSTM to algal bloom prediction, especially in South Korea, where algal blooms occur annually. Therefore, we employed the LSTM model for algal bloom prediction in four major rivers of South Korea. We conducted short-term (one week) predictions by employing regression analysis and deep learning techniques on a newly constructed water quality and quantity dataset drawn from 16 dammed pools on the rivers. Three deep learning models (multilayer perceptron, MLP; recurrent neural network, RNN; and long short-term memory, LSTM) were used to predict chlorophyll-a, a recognized proxy for algal activity. The results were compared to those from OLS (ordinary least square) regression analysis and actual data based on the root mean square error (RSME). The LSTM model showed the highest prediction rate for harmful algal blooms and all deep learning models out-performed the OLS regression analysis. Our results reveal the potential for predicting algal blooms using LSTM and deep learning.

[Deep learning and neuronal networks in ophthalmology : Applications in the field of optical coherence tomography].

PubMed

Treder, M; Eter, N

2018-04-19

Deep learning is increasingly becoming the focus of various imaging methods in medicine. Due to the large number of different imaging modalities, ophthalmology is particularly suitable for this field of application. This article gives a general overview on the topic of deep learning and its current applications in the field of optical coherence tomography. For the benefit of the reader it focuses on the clinical rather than the technical aspects.

Saliency U-Net: A regional saliency map-driven hybrid deep learning network for anomaly segmentation

NASA Astrophysics Data System (ADS)

Karargyros, Alex; Syeda-Mahmood, Tanveer

2018-02-01

Deep learning networks are gaining popularity in many medical image analysis tasks due to their generalized ability to automatically extract relevant features from raw images. However, this can make the learning problem unnecessarily harder requiring network architectures of high complexity. In case of anomaly detection, in particular, there is often sufficient regional difference between the anomaly and the surrounding parenchyma that could be easily highlighted through bottom-up saliency operators. In this paper we propose a new hybrid deep learning network using a combination of raw image and such regional maps to more accurately learn the anomalies using simpler network architectures. Specifically, we modify a deep learning network called U-Net using both the raw and pre-segmented images as input to produce joint encoding (contraction) and expansion paths (decoding) in the U-Net. We present results of successfully delineating subdural and epidural hematomas in brain CT imaging and liver hemangioma in abdominal CT images using such network.

Towards Scalable Deep Learning via I/O Analysis and Optimization

DOE Office of Scientific and Technical Information (OSTI.GOV)

Pumma, Sarunya; Si, Min; Feng, Wu-Chun

Deep learning systems have been growing in prominence as a way to automatically characterize objects, trends, and anomalies. Given the importance of deep learning systems, researchers have been investigating techniques to optimize such systems. An area of particular interest has been using large supercomputing systems to quickly generate effective deep learning networks: a phase often referred to as “training” of the deep learning neural network. As we scale existing deep learning frameworks—such as Caffe—on these large supercomputing systems, we notice that the parallelism can help improve the computation tremendously, leaving data I/O as the major bottleneck limiting the overall systemmore » scalability. In this paper, we first present a detailed analysis of the performance bottlenecks of Caffe on large supercomputing systems. Our analysis shows that the I/O subsystem of Caffe—LMDB—relies on memory-mapped I/O to access its database, which can be highly inefficient on large-scale systems because of its interaction with the process scheduling system and the network-based parallel filesystem. Based on this analysis, we then present LMDBIO, our optimized I/O plugin for Caffe that takes into account the data access pattern of Caffe in order to vastly improve I/O performance. Our experimental results show that LMDBIO can improve the overall execution time of Caffe by nearly 20-fold in some cases.« less

A theory of local learning, the learning channel, and the optimality of backpropagation.

PubMed

Baldi, Pierre; Sadowski, Peter

2016-11-01

In a physical neural system, where storage and processing are intimately intertwined, the rules for adjusting the synaptic weights can only depend on variables that are available locally, such as the activity of the pre- and post-synaptic neurons, resulting in local learning rules. A systematic framework for studying the space of local learning rules is obtained by first specifying the nature of the local variables, and then the functional form that ties them together into each learning rule. Such a framework enables also the systematic discovery of new learning rules and exploration of relationships between learning rules and group symmetries. We study polynomial local learning rules stratified by their degree and analyze their behavior and capabilities in both linear and non-linear units and networks. Stacking local learning rules in deep feedforward networks leads to deep local learning. While deep local learning can learn interesting representations, it cannot learn complex input-output functions, even when targets are available for the top layer. Learning complex input-output functions requires local deep learning where target information is communicated to the deep layers through a backward learning channel. The nature of the communicated information about the targets and the structure of the learning channel partition the space of learning algorithms. For any learning algorithm, the capacity of the learning channel can be defined as the number of bits provided about the error gradient per weight, divided by the number of required operations per weight. We estimate the capacity associated with several learning algorithms and show that backpropagation outperforms them by simultaneously maximizing the information rate and minimizing the computational cost. This result is also shown to be true for recurrent networks, by unfolding them in time. The theory clarifies the concept of Hebbian learning, establishes the power and limitations of local learning rules, introduces the learning channel which enables a formal analysis of the optimality of backpropagation, and explains the sparsity of the space of learning rules discovered so far. Copyright © 2016 Elsevier Ltd. All rights reserved.

Learning and cognitive styles in web-based learning: theory, evidence, and application.

PubMed

Cook, David A

2005-03-01

Cognitive and learning styles (CLS) have long been investigated as a basis to adapt instruction and enhance learning. Web-based learning (WBL) can reach large, heterogenous audiences, and adaptation to CLS may increase its effectiveness. Adaptation is only useful if some learners (with a defined trait) do better with one method and other learners (with a complementary trait) do better with another method (aptitude-treatment interaction). A comprehensive search of health professions education literature found 12 articles on CLS in computer-assisted learning and WBL. Because so few reports were found, research from non-medical education was also included. Among all the reports, four CLS predominated. Each CLS construct was used to predict relationships between CLS and WBL. Evidence was then reviewed to support or refute these predictions. The wholist-analytic construct shows consistent aptitude-treatment interactions consonant with predictions (wholists need structure, a broad-before-deep approach, and social interaction, while analytics need less structure and a deep-before-broad approach). Limited evidence for the active-reflective construct suggests aptitude-treatment interaction, with active learners doing better with interactive learning and reflective learners doing better with methods to promote reflection. As predicted, no consistent interaction between the concrete-abstract construct and computer format was found, but one study suggests that there is interaction with instructional method. Contrary to predictions, no interaction was found for the verbal-imager construct. Teachers developing WBL activities should consider assessing and adapting to accommodate learners defined by the wholist-analytic and active-reflective constructs. Other adaptations should be considered experimental. Further WBL research could clarify the feasibility and effectiveness of assessing and adapting to CLS.

Deep learning for classification of islanding and grid disturbance based on multi-resolution singular spectrum entropy

NASA Astrophysics Data System (ADS)

Li, Tie; He, Xiaoyang; Tang, Junci; Zeng, Hui; Zhou, Chunying; Zhang, Nan; Liu, Hui; Lu, Zhuoxin; Kong, Xiangrui; Yan, Zheng

2018-02-01

Forasmuch as the distinguishment of islanding is easy to be interfered by grid disturbance, island detection device may make misjudgment thus causing the consequence of photovoltaic out of service. The detection device must provide with the ability to differ islanding from grid disturbance. In this paper, the concept of deep learning is introduced into classification of islanding and grid disturbance for the first time. A novel deep learning framework is proposed to detect and classify islanding or grid disturbance. The framework is a hybrid of wavelet transformation, multi-resolution singular spectrum entropy, and deep learning architecture. As a signal processing method after wavelet transformation, multi-resolution singular spectrum entropy combines multi-resolution analysis and spectrum analysis with entropy as output, from which we can extract the intrinsic different features between islanding and grid disturbance. With the features extracted, deep learning is utilized to classify islanding and grid disturbance. Simulation results indicate that the method can achieve its goal while being highly accurate, so the photovoltaic system mistakenly withdrawing from power grids can be avoided.

Discrimination of Breast Cancer with Microcalcifications on Mammography by Deep Learning.

PubMed

Wang, Jinhua; Yang, Xi; Cai, Hongmin; Tan, Wanchang; Jin, Cangzheng; Li, Li

2016-06-07

Microcalcification is an effective indicator of early breast cancer. To improve the diagnostic accuracy of microcalcifications, this study evaluates the performance of deep learning-based models on large datasets for its discrimination. A semi-automated segmentation method was used to characterize all microcalcifications. A discrimination classifier model was constructed to assess the accuracies of microcalcifications and breast masses, either in isolation or combination, for classifying breast lesions. Performances were compared to benchmark models. Our deep learning model achieved a discriminative accuracy of 87.3% if microcalcifications were characterized alone, compared to 85.8% with a support vector machine. The accuracies were 61.3% for both methods with masses alone and improved to 89.7% and 85.8% after the combined analysis with microcalcifications. Image segmentation with our deep learning model yielded 15, 26 and 41 features for the three scenarios, respectively. Overall, deep learning based on large datasets was superior to standard methods for the discrimination of microcalcifications. Accuracy was increased by adopting a combinatorial approach to detect microcalcifications and masses simultaneously. This may have clinical value for early detection and treatment of breast cancer.

Discrimination of Breast Cancer with Microcalcifications on Mammography by Deep Learning

PubMed Central

Wang, Jinhua; Yang, Xi; Cai, Hongmin; Tan, Wanchang; Jin, Cangzheng; Li, Li

2016-01-01

Microcalcification is an effective indicator of early breast cancer. To improve the diagnostic accuracy of microcalcifications, this study evaluates the performance of deep learning-based models on large datasets for its discrimination. A semi-automated segmentation method was used to characterize all microcalcifications. A discrimination classifier model was constructed to assess the accuracies of microcalcifications and breast masses, either in isolation or combination, for classifying breast lesions. Performances were compared to benchmark models. Our deep learning model achieved a discriminative accuracy of 87.3% if microcalcifications were characterized alone, compared to 85.8% with a support vector machine. The accuracies were 61.3% for both methods with masses alone and improved to 89.7% and 85.8% after the combined analysis with microcalcifications. Image segmentation with our deep learning model yielded 15, 26 and 41 features for the three scenarios, respectively. Overall, deep learning based on large datasets was superior to standard methods for the discrimination of microcalcifications. Accuracy was increased by adopting a combinatorial approach to detect microcalcifications and masses simultaneously. This may have clinical value for early detection and treatment of breast cancer. PMID:27273294

Deep machine learning provides state-of-the-art performance in image-based plant phenotyping.

PubMed

Pound, Michael P; Atkinson, Jonathan A; Townsend, Alexandra J; Wilson, Michael H; Griffiths, Marcus; Jackson, Aaron S; Bulat, Adrian; Tzimiropoulos, Georgios; Wells, Darren M; Murchie, Erik H; Pridmore, Tony P; French, Andrew P

2017-10-01

In plant phenotyping, it has become important to be able to measure many features on large image sets in order to aid genetic discovery. The size of the datasets, now often captured robotically, often precludes manual inspection, hence the motivation for finding a fully automated approach. Deep learning is an emerging field that promises unparalleled results on many data analysis problems. Building on artificial neural networks, deep approaches have many more hidden layers in the network, and hence have greater discriminative and predictive power. We demonstrate the use of such approaches as part of a plant phenotyping pipeline. We show the success offered by such techniques when applied to the challenging problem of image-based plant phenotyping and demonstrate state-of-the-art results (>97% accuracy) for root and shoot feature identification and localization. We use fully automated trait identification using deep learning to identify quantitative trait loci in root architecture datasets. The majority (12 out of 14) of manually identified quantitative trait loci were also discovered using our automated approach based on deep learning detection to locate plant features. We have shown deep learning-based phenotyping to have very good detection and localization accuracy in validation and testing image sets. We have shown that such features can be used to derive meaningful biological traits, which in turn can be used in quantitative trait loci discovery pipelines. This process can be completely automated. We predict a paradigm shift in image-based phenotyping bought about by such deep learning approaches, given sufficient training sets. © The Authors 2017. Published by Oxford University Press.

A Case Study on Sepsis Using PubMed and Deep Learning for Ontology Learning.

PubMed

Arguello Casteleiro, Mercedes; Maseda Fernandez, Diego; Demetriou, George; Read, Warren; Fernandez Prieto, Maria Jesus; Des Diz, Julio; Nenadic, Goran; Keane, John; Stevens, Robert

2017-01-01

We investigate the application of distributional semantics models for facilitating unsupervised extraction of biomedical terms from unannotated corpora. Term extraction is used as the first step of an ontology learning process that aims to (semi-)automatic annotation of biomedical concepts and relations from more than 300K PubMed titles and abstracts. We experimented with both traditional distributional semantics methods such as Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA) as well as the neural language models CBOW and Skip-gram from Deep Learning. The evaluation conducted concentrates on sepsis, a major life-threatening condition, and shows that Deep Learning models outperform LSA and LDA with much higher precision.

Reinforced dynamics for enhanced sampling in large atomic and molecular systems

NASA Astrophysics Data System (ADS)

Zhang, Linfeng; Wang, Han; E, Weinan

2018-03-01

A new approach for efficiently exploring the configuration space and computing the free energy of large atomic and molecular systems is proposed, motivated by an analogy with reinforcement learning. There are two major components in this new approach. Like metadynamics, it allows for an efficient exploration of the configuration space by adding an adaptively computed biasing potential to the original dynamics. Like deep reinforcement learning, this biasing potential is trained on the fly using deep neural networks, with data collected judiciously from the exploration and an uncertainty indicator from the neural network model playing the role of the reward function. Parameterization using neural networks makes it feasible to handle cases with a large set of collective variables. This has the potential advantage that selecting precisely the right set of collective variables has now become less critical for capturing the structural transformations of the system. The method is illustrated by studying the full-atom explicit solvent models of alanine dipeptide and tripeptide, as well as the system of a polyalanine-10 molecule with 20 collective variables.

Adaptive nodes enrich nonlinear cooperative learning beyond traditional adaptation by links.

PubMed

Sardi, Shira; Vardi, Roni; Goldental, Amir; Sheinin, Anton; Uzan, Herut; Kanter, Ido

2018-03-23

Physical models typically assume time-independent interactions, whereas neural networks and machine learning incorporate interactions that function as adjustable parameters. Here we demonstrate a new type of abundant cooperative nonlinear dynamics where learning is attributed solely to the nodes, instead of the network links which their number is significantly larger. The nodal, neuronal, fast adaptation follows its relative anisotropic (dendritic) input timings, as indicated experimentally, similarly to the slow learning mechanism currently attributed to the links, synapses. It represents a non-local learning rule, where effectively many incoming links to a node concurrently undergo the same adaptation. The network dynamics is now counterintuitively governed by the weak links, which previously were assumed to be insignificant. This cooperative nonlinear dynamic adaptation presents a self-controlled mechanism to prevent divergence or vanishing of the learning parameters, as opposed to learning by links, and also supports self-oscillations of the effective learning parameters. It hints on a hierarchical computational complexity of nodes, following their number of anisotropic inputs and opens new horizons for advanced deep learning algorithms and artificial intelligence based applications, as well as a new mechanism for enhanced and fast learning by neural networks.

Empowering Prospective Teachers to Become Active Sense-Makers: Multimodal Modeling of the Seasons

NASA Astrophysics Data System (ADS)

Kim, Mi Song

2015-10-01

Situating science concepts in concrete and authentic contexts, using information and communications technologies, including multimodal modeling tools, is important for promoting the development of higher-order thinking skills in learners. However, teachers often struggle to integrate emergent multimodal models into a technology-rich informal learning environment. Our design-based research co-designs and develops engaging, immersive, and interactive informal learning activities called "Embodied Modeling-Mediated Activities" (EMMA) to support not only Singaporean learners' deep learning of astronomy but also the capacity of teachers. As part of the research on EMMA, this case study describes two prospective teachers' co-design processes involving multimodal models for teaching and learning the concept of the seasons in a technology-rich informal learning setting. Our study uncovers four prominent themes emerging from our data concerning the contextualized nature of learning and teaching involving multimodal models in informal learning contexts: (1) promoting communication and emerging questions, (2) offering affordances through limitations, (3) explaining one concept involving multiple concepts, and (4) integrating teaching and learning experiences. This study has an implication for the development of a pedagogical framework for teaching and learning in technology-enhanced learning environments—that is empowering teachers to become active sense-makers using multimodal models.

Exploring the Function Space of Deep-Learning Machines

NASA Astrophysics Data System (ADS)

Li, Bo; Saad, David

2018-06-01

The function space of deep-learning machines is investigated by studying growth in the entropy of functions of a given error with respect to a reference function, realized by a deep-learning machine. Using physics-inspired methods we study both sparsely and densely connected architectures to discover a layerwise convergence of candidate functions, marked by a corresponding reduction in entropy when approaching the reference function, gain insight into the importance of having a large number of layers, and observe phase transitions as the error increases.

The Effects of Deep Approaches to Learning on Students' Need for Cognition over Four Years of College

ERIC Educational Resources Information Center

Wang, Jui-Sheng

2013-01-01

This study examines the effect of deep approaches to learning on development of the inclination to inquire and lifelong learning over four years, as an essential graduated outcome that helps students face the challenges of a complex and rapidly changing world. Despite the importance of the inclination to inquire and lifelong learning, some…

Plant Species Identification by Bi-channel Deep Convolutional Networks

NASA Astrophysics Data System (ADS)

He, Guiqing; Xia, Zhaoqiang; Zhang, Qiqi; Zhang, Haixi; Fan, Jianping

2018-04-01

Plant species identification achieves much attention recently as it has potential application in the environmental protection and human life. Although deep learning techniques can be directly applied for plant species identification, it still needs to be designed for this specific task to obtain the state-of-art performance. In this paper, a bi-channel deep learning framework is developed for identifying plant species. In the framework, two different sub-networks are fine-tuned over their pretrained models respectively. And then a stacking layer is used to fuse the output of two different sub-networks. We construct a plant dataset of Orchidaceae family for algorithm evaluation. Our experimental results have demonstrated that our bi-channel deep network can achieve very competitive performance on accuracy rates compared to the existing deep learning algorithm.

NiftyNet: a deep-learning platform for medical imaging.

PubMed

Gibson, Eli; Li, Wenqi; Sudre, Carole; Fidon, Lucas; Shakir, Dzhoshkun I; Wang, Guotai; Eaton-Rosen, Zach; Gray, Robert; Doel, Tom; Hu, Yipeng; Whyntie, Tom; Nachev, Parashkev; Modat, Marc; Barratt, Dean C; Ourselin, Sébastien; Cardoso, M Jorge; Vercauteren, Tom

2018-05-01

Medical image analysis and computer-assisted intervention problems are increasingly being addressed with deep-learning-based solutions. Established deep-learning platforms are flexible but do not provide specific functionality for medical image analysis and adapting them for this domain of application requires substantial implementation effort. Consequently, there has been substantial duplication of effort and incompatible infrastructure developed across many research groups. This work presents the open-source NiftyNet platform for deep learning in medical imaging. The ambition of NiftyNet is to accelerate and simplify the development of these solutions, and to provide a common mechanism for disseminating research outputs for the community to use, adapt and build upon. The NiftyNet infrastructure provides a modular deep-learning pipeline for a range of medical imaging applications including segmentation, regression, image generation and representation learning applications. Components of the NiftyNet pipeline including data loading, data augmentation, network architectures, loss functions and evaluation metrics are tailored to, and take advantage of, the idiosyncracies of medical image analysis and computer-assisted intervention. NiftyNet is built on the TensorFlow framework and supports features such as TensorBoard visualization of 2D and 3D images and computational graphs by default. We present three illustrative medical image analysis applications built using NiftyNet infrastructure: (1) segmentation of multiple abdominal organs from computed tomography; (2) image regression to predict computed tomography attenuation maps from brain magnetic resonance images; and (3) generation of simulated ultrasound images for specified anatomical poses. The NiftyNet infrastructure enables researchers to rapidly develop and distribute deep learning solutions for segmentation, regression, image generation and representation learning applications, or extend the platform to new applications. Copyright © 2018 The Authors. Published by Elsevier B.V. All rights reserved.

Goal Orientation, Deep Learning, and Sustainable Feedback in Higher Business Education

ERIC Educational Resources Information Center

Geitz, Gerry; Brinke, Desirée Joosten-ten; Kirschner, Paul A.

2015-01-01

Relations between and changeability of goal orientation and learning behavior have been studied in several domains and contexts. To alter the adopted goal orientation into a mastery orientation and increase a concomitant deep learning in international business students, a sustainable feedback intervention study was carried out. Sustainable…

Theoretical Explanation for Success of Deep-Level-Learning Study Tours

ERIC Educational Resources Information Center

Bergsteiner, Harald; Avery, Gayle C.

2008-01-01

Study tours can help internationalize curricula and prepare students for global workplaces. We examine benefits of tours providing deep-level learning experiences rather than industrial tourism using five main theoretical frameworks to highlight the diverse learning benefits associated with intensive study tours in particular. Relevant theoretical…

ACTIVIS: Visual Exploration of Industry-Scale Deep Neural Network Models.

PubMed

Kahng, Minsuk; Andrews, Pierre Y; Kalro, Aditya; Polo Chau, Duen Horng

2017-08-30

While deep learning models have achieved state-of-the-art accuracies for many prediction tasks, understanding these models remains a challenge. Despite the recent interest in developing visual tools to help users interpret deep learning models, the complexity and wide variety of models deployed in industry, and the large-scale datasets that they used, pose unique design challenges that are inadequately addressed by existing work. Through participatory design sessions with over 15 researchers and engineers at Facebook, we have developed, deployed, and iteratively improved ACTIVIS, an interactive visualization system for interpreting large-scale deep learning models and results. By tightly integrating multiple coordinated views, such as a computation graph overview of the model architecture, and a neuron activation view for pattern discovery and comparison, users can explore complex deep neural network models at both the instance- and subset-level. ACTIVIS has been deployed on Facebook's machine learning platform. We present case studies with Facebook researchers and engineers, and usage scenarios of how ACTIVIS may work with different models.

Jet-images — deep learning edition

DOE PAGES

de Oliveira, Luke; Kagan, Michael; Mackey, Lester; ...

2016-07-13

Building on the notion of a particle physics detector as a camera and the collimated streams of high energy particles, or jets, it measures as an image, we investigate the potential of machine learning techniques based on deep learning architectures to identify highly boosted W bosons. Modern deep learning algorithms trained on jet images can out-perform standard physically-motivated feature driven approaches to jet tagging. We develop techniques for visualizing how these features are learned by the network and what additional information is used to improve performance. Finally, this interplay between physically-motivated feature driven tools and supervised learning algorithms is generalmore » and can be used to significantly increase the sensitivity to discover new particles and new forces, and gain a deeper understanding of the physics within jets.« less

Jet-images — deep learning edition

DOE Office of Scientific and Technical Information (OSTI.GOV)

de Oliveira, Luke; Kagan, Michael; Mackey, Lester

Building on the notion of a particle physics detector as a camera and the collimated streams of high energy particles, or jets, it measures as an image, we investigate the potential of machine learning techniques based on deep learning architectures to identify highly boosted W bosons. Modern deep learning algorithms trained on jet images can out-perform standard physically-motivated feature driven approaches to jet tagging. We develop techniques for visualizing how these features are learned by the network and what additional information is used to improve performance. Finally, this interplay between physically-motivated feature driven tools and supervised learning algorithms is generalmore » and can be used to significantly increase the sensitivity to discover new particles and new forces, and gain a deeper understanding of the physics within jets.« less

Deep Processing Strategies and Critical Thinking: Developmental Trajectories Using Latent Growth Analyses

ERIC Educational Resources Information Center

Phan, Huy P.

2011-01-01

The author explored the developmental courses of deep learning approach and critical thinking over a 2-year period. Latent growth curve modeling (LGM) procedures were used to test and trace the trajectories of both theoretical frameworks over time. Participants were 264 (119 women, 145 men) university undergraduates. The Deep Learning subscale of…

Breast cancer molecular subtype classification using deep features: preliminary results

NASA Astrophysics Data System (ADS)

Zhu, Zhe; Albadawy, Ehab; Saha, Ashirbani; Zhang, Jun; Harowicz, Michael R.; Mazurowski, Maciej A.

2018-02-01

Radiogenomics is a field of investigation that attempts to examine the relationship between imaging characteris- tics of cancerous lesions and their genomic composition. This could offer a noninvasive alternative to establishing genomic characteristics of tumors and aid cancer treatment planning. While deep learning has shown its supe- riority in many detection and classification tasks, breast cancer radiogenomic data suffers from a very limited number of training examples, which renders the training of the neural network for this problem directly and with no pretraining a very difficult task. In this study, we investigated an alternative deep learning approach referred to as deep features or off-the-shelf network approach to classify breast cancer molecular subtypes using breast dynamic contrast enhanced MRIs. We used the feature maps of different convolution layers and fully connected layers as features and trained support vector machines using these features for prediction. For the feature maps that have multiple layers, max-pooling was performed along each channel. We focused on distinguishing the Luminal A subtype from other subtypes. To evaluate the models, 10 fold cross-validation was performed and the final AUC was obtained by averaging the performance of all the folds. The highest average AUC obtained was 0.64 (0.95 CI: 0.57-0.71), using the feature maps of the last fully connected layer. This indicates the promise of using this approach to predict the breast cancer molecular subtypes. Since the best performance appears in the last fully connected layer, it also implies that breast cancer molecular subtypes may relate to high level image features

What makes deeply encoded items memorable? Insights into the levels of processing framework from neuroimaging and neuromodulation.

PubMed

Galli, Giulia

2014-01-01

When we form new memories, their mnestic fate largely depends upon the cognitive operations set in train during encoding. A typical observation in experimental as well as everyday life settings is that if we learn an item using semantic or "deep" operations, such as attending to its meaning, memory will be better than if we learn the same item using more "shallow" operations, such as attending to its structural features. In the psychological literature, this phenomenon has been conceptualized within the "levels of processing" framework and has been consistently replicated since its original proposal by Craik and Lockhart in 1972. However, the exact mechanisms underlying the memory advantage for deeply encoded items are not yet entirely understood. A cognitive neuroscience perspective can add to this field by clarifying the nature of the processes involved in effective deep and shallow encoding and how they are instantiated in the brain, but so far there has been little work to systematically integrate findings from the literature. This work aims to fill this gap by reviewing, first, some of the key neuroimaging findings on the neural correlates of deep and shallow episodic encoding and second, emerging evidence from studies using neuromodulatory approaches such as psychopharmacology and non-invasive brain stimulation. Taken together, these studies help further our understanding of levels of processing. In addition, by showing that deep encoding can be modulated by acting upon specific brain regions or systems, the reviewed studies pave the way for selective enhancements of episodic encoding processes.

DeepPicker: A deep learning approach for fully automated particle picking in cryo-EM.

PubMed

Wang, Feng; Gong, Huichao; Liu, Gaochao; Li, Meijing; Yan, Chuangye; Xia, Tian; Li, Xueming; Zeng, Jianyang

2016-09-01

Particle picking is a time-consuming step in single-particle analysis and often requires significant interventions from users, which has become a bottleneck for future automated electron cryo-microscopy (cryo-EM). Here we report a deep learning framework, called DeepPicker, to address this problem and fill the current gaps toward a fully automated cryo-EM pipeline. DeepPicker employs a novel cross-molecule training strategy to capture common features of particles from previously-analyzed micrographs, and thus does not require any human intervention during particle picking. Tests on the recently-published cryo-EM data of three complexes have demonstrated that our deep learning based scheme can successfully accomplish the human-level particle picking process and identify a sufficient number of particles that are comparable to those picked manually by human experts. These results indicate that DeepPicker can provide a practically useful tool to significantly reduce the time and manual effort spent in single-particle analysis and thus greatly facilitate high-resolution cryo-EM structure determination. DeepPicker is released as an open-source program, which can be downloaded from https://github.com/nejyeah/DeepPicker-python. Copyright © 2016 Elsevier Inc. All rights reserved.

Deep learning for healthcare: review, opportunities and challenges.

PubMed

Miotto, Riccardo; Wang, Fei; Wang, Shuang; Jiang, Xiaoqian; Dudley, Joel T

2017-05-06

Gaining knowledge and actionable insights from complex, high-dimensional and heterogeneous biomedical data remains a key challenge in transforming health care. Various types of data have been emerging in modern biomedical research, including electronic health records, imaging, -omics, sensor data and text, which are complex, heterogeneous, poorly annotated and generally unstructured. Traditional data mining and statistical learning approaches typically need to first perform feature engineering to obtain effective and more robust features from those data, and then build prediction or clustering models on top of them. There are lots of challenges on both steps in a scenario of complicated data and lacking of sufficient domain knowledge. The latest advances in deep learning technologies provide new effective paradigms to obtain end-to-end learning models from complex data. In this article, we review the recent literature on applying deep learning technologies to advance the health care domain. Based on the analyzed work, we suggest that deep learning approaches could be the vehicle for translating big biomedical data into improved human health. However, we also note limitations and needs for improved methods development and applications, especially in terms of ease-of-understanding for domain experts and citizen scientists. We discuss such challenges and suggest developing holistic and meaningful interpretable architectures to bridge deep learning models and human interpretability. © The Author 2017. Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Deep Learning for Automated Extraction of Primary Sites from Cancer Pathology Reports

DOE PAGES

Qiu, John; Yoon, Hong-Jun; Fearn, Paul A.; ...

2017-05-03

Pathology reports are a primary source of information for cancer registries which process high volumes of free-text reports annually. Information extraction and coding is a manual, labor-intensive process. Here in this study we investigated deep learning and a convolutional neural network (CNN), for extracting ICDO- 3 topographic codes from a corpus of breast and lung cancer pathology reports. We performed two experiments, using a CNN and a more conventional term frequency vector approach, to assess the effects of class prevalence and inter-class transfer learning. The experiments were based on a set of 942 pathology reports with human expert annotations asmore » the gold standard. CNN performance was compared against a more conventional term frequency vector space approach. We observed that the deep learning models consistently outperformed the conventional approaches in the class prevalence experiment, resulting in micro and macro-F score increases of up to 0.132 and 0.226 respectively when class labels were well populated. Specifically, the best performing CNN achieved a micro-F score of 0.722 over 12 ICD-O-3 topography codes. Transfer learning provided a consistent but modest performance boost for the deep learning methods but trends were contingent on CNN method and cancer site. Finally, these encouraging results demonstrate the potential of deep learning for automated abstraction of pathology reports.« less

Deep Learning for Automated Extraction of Primary Sites from Cancer Pathology Reports

DOE Office of Scientific and Technical Information (OSTI.GOV)

Qiu, John; Yoon, Hong-Jun; Fearn, Paul A.

Pathology reports are a primary source of information for cancer registries which process high volumes of free-text reports annually. Information extraction and coding is a manual, labor-intensive process. Here in this study we investigated deep learning and a convolutional neural network (CNN), for extracting ICDO- 3 topographic codes from a corpus of breast and lung cancer pathology reports. We performed two experiments, using a CNN and a more conventional term frequency vector approach, to assess the effects of class prevalence and inter-class transfer learning. The experiments were based on a set of 942 pathology reports with human expert annotations asmore » the gold standard. CNN performance was compared against a more conventional term frequency vector space approach. We observed that the deep learning models consistently outperformed the conventional approaches in the class prevalence experiment, resulting in micro and macro-F score increases of up to 0.132 and 0.226 respectively when class labels were well populated. Specifically, the best performing CNN achieved a micro-F score of 0.722 over 12 ICD-O-3 topography codes. Transfer learning provided a consistent but modest performance boost for the deep learning methods but trends were contingent on CNN method and cancer site. Finally, these encouraging results demonstrate the potential of deep learning for automated abstraction of pathology reports.« less

Deep facial analysis: A new phase I epilepsy evaluation using computer vision.

PubMed

Ahmedt-Aristizabal, David; Fookes, Clinton; Nguyen, Kien; Denman, Simon; Sridharan, Sridha; Dionisio, Sasha

2018-05-01

Semiology observation and characterization play a major role in the presurgical evaluation of epilepsy. However, the interpretation of patient movements has subjective and intrinsic challenges. In this paper, we develop approaches to attempt to automatically extract and classify semiological patterns from facial expressions. We address limitations of existing computer-based analytical approaches of epilepsy monitoring, where facial movements have largely been ignored. This is an area that has seen limited advances in the literature. Inspired by recent advances in deep learning, we propose two deep learning models, landmark-based and region-based, to quantitatively identify changes in facial semiology in patients with mesial temporal lobe epilepsy (MTLE) from spontaneous expressions during phase I monitoring. A dataset has been collected from the Mater Advanced Epilepsy Unit (Brisbane, Australia) and is used to evaluate our proposed approach. Our experiments show that a landmark-based approach achieves promising results in analyzing facial semiology, where movements can be effectively marked and tracked when there is a frontal face on visualization. However, the region-based counterpart with spatiotemporal features achieves more accurate results when confronted with extreme head positions. A multifold cross-validation of the region-based approach exhibited an average test accuracy of 95.19% and an average AUC of 0.98 of the ROC curve. Conversely, a leave-one-subject-out cross-validation scheme for the same approach reveals a reduction in accuracy for the model as it is affected by data limitations and achieves an average test accuracy of 50.85%. Overall, the proposed deep learning models have shown promise in quantifying ictal facial movements in patients with MTLE. In turn, this may serve to enhance the automated presurgical epilepsy evaluation by allowing for standardization, mitigating bias, and assessing key features. The computer-aided diagnosis may help to support clinical decision-making and prevent erroneous localization and surgery. Copyright © 2018 Elsevier Inc. All rights reserved.

A deep learning-based multi-model ensemble method for cancer prediction.

PubMed

Xiao, Yawen; Wu, Jun; Lin, Zongli; Zhao, Xiaodong

2018-01-01

Cancer is a complex worldwide health problem associated with high mortality. With the rapid development of the high-throughput sequencing technology and the application of various machine learning methods that have emerged in recent years, progress in cancer prediction has been increasingly made based on gene expression, providing insight into effective and accurate treatment decision making. Thus, developing machine learning methods, which can successfully distinguish cancer patients from healthy persons, is of great current interest. However, among the classification methods applied to cancer prediction so far, no one method outperforms all the others. In this paper, we demonstrate a new strategy, which applies deep learning to an ensemble approach that incorporates multiple different machine learning models. We supply informative gene data selected by differential gene expression analysis to five different classification models. Then, a deep learning method is employed to ensemble the outputs of the five classifiers. The proposed deep learning-based multi-model ensemble method was tested on three public RNA-seq data sets of three kinds of cancers, Lung Adenocarcinoma, Stomach Adenocarcinoma and Breast Invasive Carcinoma. The test results indicate that it increases the prediction accuracy of cancer for all the tested RNA-seq data sets as compared to using a single classifier or the majority voting algorithm. By taking full advantage of different classifiers, the proposed deep learning-based multi-model ensemble method is shown to be accurate and effective for cancer prediction. Copyright © 2017 Elsevier B.V. All rights reserved.

Deep learning with non-medical training used for chest pathology identification

NASA Astrophysics Data System (ADS)

Bar, Yaniv; Diamant, Idit; Wolf, Lior; Greenspan, Hayit

2015-03-01

In this work, we examine the strength of deep learning approaches for pathology detection in chest radiograph data. Convolutional neural networks (CNN) deep architecture classification approaches have gained popularity due to their ability to learn mid and high level image representations. We explore the ability of a CNN to identify different types of pathologies in chest x-ray images. Moreover, since very large training sets are generally not available in the medical domain, we explore the feasibility of using a deep learning approach based on non-medical learning. We tested our algorithm on a dataset of 93 images. We use a CNN that was trained with ImageNet, a well-known large scale nonmedical image database. The best performance was achieved using a combination of features extracted from the CNN and a set of low-level features. We obtained an area under curve (AUC) of 0.93 for Right Pleural Effusion detection, 0.89 for Enlarged heart detection and 0.79 for classification between healthy and abnormal chest x-ray, where all pathologies are combined into one large class. This is a first-of-its-kind experiment that shows that deep learning with large scale non-medical image databases may be sufficient for general medical image recognition tasks.

An Advanced Deep Learning Approach for Ki-67 Stained Hotspot Detection and Proliferation Rate Scoring for Prognostic Evaluation of Breast Cancer.

PubMed

Saha, Monjoy; Chakraborty, Chandan; Arun, Indu; Ahmed, Rosina; Chatterjee, Sanjoy

2017-06-12

Being a non-histone protein, Ki-67 is one of the essential biomarkers for the immunohistochemical assessment of proliferation rate in breast cancer screening and grading. The Ki-67 signature is always sensitive to radiotherapy and chemotherapy. Due to random morphological, color and intensity variations of cell nuclei (immunopositive and immunonegative), manual/subjective assessment of Ki-67 scoring is error-prone and time-consuming. Hence, several machine learning approaches have been reported; nevertheless, none of them had worked on deep learning based hotspots detection and proliferation scoring. In this article, we suggest an advanced deep learning model for computerized recognition of candidate hotspots and subsequent proliferation rate scoring by quantifying Ki-67 appearance in breast cancer immunohistochemical images. Unlike existing Ki-67 scoring techniques, our methodology uses Gamma mixture model (GMM) with Expectation-Maximization for seed point detection and patch selection and deep learning, comprises with decision layer, for hotspots detection and proliferation scoring. Experimental results provide 93% precision, 0.88% recall and 0.91% F-score value. The model performance has also been compared with the pathologists' manual annotations and recently published articles. In future, the proposed deep learning framework will be highly reliable and beneficial to the junior and senior pathologists for fast and efficient Ki-67 scoring.

Deep learning for tumor classification in imaging mass spectrometry.

PubMed

Behrmann, Jens; Etmann, Christian; Boskamp, Tobias; Casadonte, Rita; Kriegsmann, Jörg; Maaß, Peter

2018-04-01

Tumor classification using imaging mass spectrometry (IMS) data has a high potential for future applications in pathology. Due to the complexity and size of the data, automated feature extraction and classification steps are required to fully process the data. Since mass spectra exhibit certain structural similarities to image data, deep learning may offer a promising strategy for classification of IMS data as it has been successfully applied to image classification. Methodologically, we propose an adapted architecture based on deep convolutional networks to handle the characteristics of mass spectrometry data, as well as a strategy to interpret the learned model in the spectral domain based on a sensitivity analysis. The proposed methods are evaluated on two algorithmically challenging tumor classification tasks and compared to a baseline approach. Competitiveness of the proposed methods is shown on both tasks by studying the performance via cross-validation. Moreover, the learned models are analyzed by the proposed sensitivity analysis revealing biologically plausible effects as well as confounding factors of the considered tasks. Thus, this study may serve as a starting point for further development of deep learning approaches in IMS classification tasks. https://gitlab.informatik.uni-bremen.de/digipath/Deep_Learning_for_Tumor_Classification_in_IMS. jbehrmann@uni-bremen.de or christianetmann@uni-bremen.de. Supplementary data are available at Bioinformatics online.

Deep learning methods to guide CT image reconstruction and reduce metal artifacts

NASA Astrophysics Data System (ADS)

Gjesteby, Lars; Yang, Qingsong; Xi, Yan; Zhou, Ye; Zhang, Junping; Wang, Ge

2017-03-01

The rapidly-rising field of machine learning, including deep learning, has inspired applications across many disciplines. In medical imaging, deep learning has been primarily used for image processing and analysis. In this paper, we integrate a convolutional neural network (CNN) into the computed tomography (CT) image reconstruction process. Our first task is to monitor the quality of CT images during iterative reconstruction and decide when to stop the process according to an intelligent numerical observer instead of using a traditional stopping rule, such as a fixed error threshold or a maximum number of iterations. After training on ground truth images, the CNN was successful in guiding an iterative reconstruction process to yield high-quality images. Our second task is to improve a sinogram to correct for artifacts caused by metal objects. A large number of interpolation and normalization-based schemes were introduced for metal artifact reduction (MAR) over the past four decades. The NMAR algorithm is considered a state-of-the-art method, although residual errors often remain in the reconstructed images, especially in cases of multiple metal objects. Here we merge NMAR with deep learning in the projection domain to achieve additional correction in critical image regions. Our results indicate that deep learning can be a viable tool to address CT reconstruction challenges.

A novel application of deep learning for single-lead ECG classification.

PubMed

Mathews, Sherin M; Kambhamettu, Chandra; Barner, Kenneth E

2018-06-04

Detecting and classifying cardiac arrhythmias is critical to the diagnosis of patients with cardiac abnormalities. In this paper, a novel approach based on deep learning methodology is proposed for the classification of single-lead electrocardiogram (ECG) signals. We demonstrate the application of the Restricted Boltzmann Machine (RBM) and deep belief networks (DBN) for ECG classification following detection of ventricular and supraventricular heartbeats using single-lead ECG. The effectiveness of this proposed algorithm is illustrated using real ECG signals from the widely-used MIT-BIH database. Simulation results demonstrate that with a suitable choice of parameters, RBM and DBN can achieve high average recognition accuracies of ventricular ectopic beats (93.63%) and of supraventricular ectopic beats (95.57%) at a low sampling rate of 114 Hz. Experimental results indicate that classifiers built into this deep learning-based framework achieved state-of-the art performance models at lower sampling rates and simple features when compared to traditional methods. Further, employing features extracted at a sampling rate of 114 Hz when combined with deep learning provided enough discriminatory power for the classification task. This performance is comparable to that of traditional methods and uses a much lower sampling rate and simpler features. Thus, our proposed deep neural network algorithm demonstrates that deep learning-based methods offer accurate ECG classification and could potentially be extended to other physiological signal classifications, such as those in arterial blood pressure (ABP), nerve conduction (EMG), and heart rate variability (HRV) studies. Copyright © 2018. Published by Elsevier Ltd.

Automatic detection of hemorrhagic pericardial effusion on PMCT using deep learning - a feasibility study.

PubMed

Ebert, Lars C; Heimer, Jakob; Schweitzer, Wolf; Sieberth, Till; Leipner, Anja; Thali, Michael; Ampanozi, Garyfalia

2017-12-01

Post mortem computed tomography (PMCT) can be used as a triage tool to better identify cases with a possibly non-natural cause of death, especially when high caseloads make it impossible to perform autopsies on all cases. Substantial data can be generated by modern medical scanners, especially in a forensic setting where the entire body is documented at high resolution. A solution for the resulting issues could be the use of deep learning techniques for automatic analysis of radiological images. In this article, we wanted to test the feasibility of such methods for forensic imaging by hypothesizing that deep learning methods can detect and segment a hemopericardium in PMCT. For deep learning image analysis software, we used the ViDi Suite 2.0. We retrospectively selected 28 cases with, and 24 cases without, hemopericardium. Based on these data, we trained two separate deep learning networks. The first one classified images into hemopericardium/not hemopericardium, and the second one segmented the blood content. We randomly selected 50% of the data for training and 50% for validation. This process was repeated 20 times. The best performing classification network classified all cases of hemopericardium from the validation images correctly with only a few false positives. The best performing segmentation network would tend to underestimate the amount of blood in the pericardium, which is the case for most networks. This is the first study that shows that deep learning has potential for automated image analysis of radiological images in forensic medicine.

Deep Learning Accurately Predicts Estrogen Receptor Status in Breast Cancer Metabolomics Data.

PubMed

Alakwaa, Fadhl M; Chaudhary, Kumardeep; Garmire, Lana X

2018-01-05

Metabolomics holds the promise as a new technology to diagnose highly heterogeneous diseases. Conventionally, metabolomics data analysis for diagnosis is done using various statistical and machine learning based classification methods. However, it remains unknown if deep neural network, a class of increasingly popular machine learning methods, is suitable to classify metabolomics data. Here we use a cohort of 271 breast cancer tissues, 204 positive estrogen receptor (ER+), and 67 negative estrogen receptor (ER-) to test the accuracies of feed-forward networks, a deep learning (DL) framework, as well as six widely used machine learning models, namely random forest (RF), support vector machines (SVM), recursive partitioning and regression trees (RPART), linear discriminant analysis (LDA), prediction analysis for microarrays (PAM), and generalized boosted models (GBM). DL framework has the highest area under the curve (AUC) of 0.93 in classifying ER+/ER- patients, compared to the other six machine learning algorithms. Furthermore, the biological interpretation of the first hidden layer reveals eight commonly enriched significant metabolomics pathways (adjusted P-value <0.05) that cannot be discovered by other machine learning methods. Among them, protein digestion and absorption and ATP-binding cassette (ABC) transporters pathways are also confirmed in integrated analysis between metabolomics and gene expression data in these samples. In summary, deep learning method shows advantages for metabolomics based breast cancer ER status classification, with both the highest prediction accuracy (AUC = 0.93) and better revelation of disease biology. We encourage the adoption of feed-forward networks based deep learning method in the metabolomics research community for classification.

Analysis of the load on the knee joint and vertebral column with changes in squatting depth and weight load.

PubMed

Hartmann, Hagen; Wirth, Klaus; Klusemann, Markus

2013-10-01

It has been suggested that deep squats could cause an increased injury risk of the lumbar spine and the knee joints. Avoiding deep flexion has been recommended to minimize the magnitude of knee-joint forces. Unfortunately this suggestion has not taken the influence of the wrapping effect, functional adaptations and soft tissue contact between the back of thigh and calf into account. The aim of this literature review is to assess whether squats with less knee flexion (half/quarter squats) are safer on the musculoskeletal system than deep squats. A search of relevant scientific publications was conducted between March 2011 and January 2013 using PubMed. Over 164 articles were included in the review. There are no realistic estimations of knee-joint forces for knee-flexion angles beyond 50° in the deep squat. Based on biomechanical calculations and measurements of cadaver knee joints, the highest retropatellar compressive forces and stresses can be seen at 90°. With increasing flexion, the wrapping effect contributes to an enhanced load distribution and enhanced force transfer with lower retropatellar compressive forces. Additionally, with further flexion of the knee joint a cranial displacement of facet contact areas with continuous enlargement of the retropatellar articulating surface occurs. Both lead to lower retropatellar compressive stresses. Menisci and cartilage, ligaments and bones are susceptible to anabolic metabolic processes and functional structural adaptations in response to increased activity and mechanical influences. Concerns about degenerative changes of the tendofemoral complex and the apparent higher risk for chondromalacia, osteoarthritis, and osteochondritis in deep squats are unfounded. With the same load configuration as in the deep squat, half and quarter squat training with comparatively supra-maximal loads will favour degenerative changes in the knee joints and spinal joints in the long term. Provided that technique is learned accurately under expert supervision and with progressive training loads, the deep squat presents an effective training exercise for protection against injuries and strengthening of the lower extremity. Contrary to commonly voiced concern, deep squats do not contribute increased risk of injury to passive tissues.

Deep Restricted Kernel Machines Using Conjugate Feature Duality.

PubMed

Suykens, Johan A K

2017-08-01

The aim of this letter is to propose a theory of deep restricted kernel machines offering new foundations for deep learning with kernel machines. From the viewpoint of deep learning, it is partially related to restricted Boltzmann machines, which are characterized by visible and hidden units in a bipartite graph without hidden-to-hidden connections and deep learning extensions as deep belief networks and deep Boltzmann machines. From the viewpoint of kernel machines, it includes least squares support vector machines for classification and regression, kernel principal component analysis (PCA), matrix singular value decomposition, and Parzen-type models. A key element is to first characterize these kernel machines in terms of so-called conjugate feature duality, yielding a representation with visible and hidden units. It is shown how this is related to the energy form in restricted Boltzmann machines, with continuous variables in a nonprobabilistic setting. In this new framework of so-called restricted kernel machine (RKM) representations, the dual variables correspond to hidden features. Deep RKM are obtained by coupling the RKMs. The method is illustrated for deep RKM, consisting of three levels with a least squares support vector machine regression level and two kernel PCA levels. In its primal form also deep feedforward neural networks can be trained within this framework.

Distributed Cerebellar Motor Learning: A Spike-Timing-Dependent Plasticity Model

PubMed Central

Luque, Niceto R.; Garrido, Jesús A.; Naveros, Francisco; Carrillo, Richard R.; D'Angelo, Egidio; Ros, Eduardo

2016-01-01

Deep cerebellar nuclei neurons receive both inhibitory (GABAergic) synaptic currents from Purkinje cells (within the cerebellar cortex) and excitatory (glutamatergic) synaptic currents from mossy fibers. Those two deep cerebellar nucleus inputs are thought to be also adaptive, embedding interesting properties in the framework of accurate movements. We show that distributed spike-timing-dependent plasticity mechanisms (STDP) located at different cerebellar sites (parallel fibers to Purkinje cells, mossy fibers to deep cerebellar nucleus cells, and Purkinje cells to deep cerebellar nucleus cells) in close-loop simulations provide an explanation for the complex learning properties of the cerebellum in motor learning. Concretely, we propose a new mechanistic cerebellar spiking model. In this new model, deep cerebellar nuclei embed a dual functionality: deep cerebellar nuclei acting as a gain adaptation mechanism and as a facilitator for the slow memory consolidation at mossy fibers to deep cerebellar nucleus synapses. Equipping the cerebellum with excitatory (e-STDP) and inhibitory (i-STDP) mechanisms at deep cerebellar nuclei afferents allows the accommodation of synaptic memories that were formed at parallel fibers to Purkinje cells synapses and then transferred to mossy fibers to deep cerebellar nucleus synapses. These adaptive mechanisms also contribute to modulate the deep-cerebellar-nucleus-output firing rate (output gain modulation toward optimizing its working range). PMID:26973504

Research on Daily Objects Detection Based on Deep Neural Network

NASA Astrophysics Data System (ADS)

Ding, Sheng; Zhao, Kun

2018-03-01

With the rapid development of deep learning, great breakthroughs have been made in the field of object detection. In this article, the deep learning algorithm is applied to the detection of daily objects, and some progress has been made in this direction. Compared with traditional object detection methods, the daily objects detection method based on deep learning is faster and more accurate. The main research work of this article: 1. collect a small data set of daily objects; 2. in the TensorFlow framework to build different models of object detection, and use this data set training model; 3. the training process and effect of the model are improved by fine-tuning the model parameters.

Surface, Deep, and Transfer? Considering the Role of Content Literacy Instructional Strategies

ERIC Educational Resources Information Center

Frey, Nancy; Fisher, Douglas; Hattie, John

2017-01-01

This article provides an organizational review of content literacy instructional strategies to forward a claim that some strategies work better for surface learning, whereas others are more effective for deep learning and still others for transfer learning. The authors argue that the failure to adopt content literacy strategies by disciplinary…

The Experience of Deep Learning by Accounting Students

ERIC Educational Resources Information Center

Turner, Martin; Baskerville, Rachel

2013-01-01

This study examines how to support accounting students to experience deep learning. A sample of 81 students in a third-year undergraduate accounting course was studied employing a phenomenographic research approach, using ten assessed learning tasks for each student (as well as a focus group and student surveys) to measure their experience of how…

Measuring Deep, Reflective Comprehension and Learning Strategies: Challenges and Successes

ERIC Educational Resources Information Center

McNamara, Danielle S.

2011-01-01

There is a heightened understanding that metacognition and strategy use are crucial to deep, long-lasting comprehension and learning, but their assessment is challenging. First, students' judgments of what their abilities and habits and measurements of their performance often do not match. Second, students tend to learn and comprehend differently…

What Can Be Learned from a Laboratory Model of Conceptual Change? Descriptive Findings and Methodological Issues

ERIC Educational Resources Information Center

Ohlsson, Stellan; Cosejo, David G.

2014-01-01

The problem of how people process novel and unexpected information--"deep learning" (Ohlsson in "Deep learning: how the mind overrides experience." Cambridge University Press, New York, 2011)--is central to several fields of research, including creativity, belief revision, and conceptual change. Researchers have not converged…

Getting Inside Knowledge: The Application of Entwistle's Model of Surface/Deep Processing in Producing Open Learning Materials.

ERIC Educational Resources Information Center

Evans, Barbara; Honour, Leslie

1997-01-01

Reports on a study that required student teachers training in business education to produce open learning materials on intercultural communication. Analysis of stages and responses to this assignment revealed a distinction between "deep" and "surface" learning. Includes charts delineating the characteristics of these two types…

A Critical Comparison of Transformation and Deep Approach Theories of Learning

ERIC Educational Resources Information Center

Howie, Peter; Bagnall, Richard

2015-01-01

This paper reports a critical comparative analysis of two popular and significant theories of adult learning: the transformation and the deep approach theories of learning. These theories are operative in different educational sectors, are significant, respectively, in each, and they may be seen as both touching on similar concerns with learning…

Who Benefits from a Low versus High Guidance CSCL Script and Why?

ERIC Educational Resources Information Center

Mende, Stephan; Proske, Antje; Körndle, Hermann; Narciss, Susanne

2017-01-01

Computer-supported collaborative learning (CSCL) scripts can foster learners' deep text comprehension. However, this depends on (a) the extent to which the learning activities targeted by a script promote deep text comprehension and (b) whether the guidance level provided by the script is adequate to induce the targeted learning activities…

Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey

PubMed Central

Zhang, Fan; Li, Xuelong

2018-01-01

The ultrasound imaging is one of the most common schemes to detect diseases in the clinical practice. There are many advantages of ultrasound imaging such as safety, convenience, and low cost. However, reading ultrasound imaging is not easy. To support the diagnosis of clinicians and reduce the load of doctors, many ultrasound computer-aided diagnosis (CAD) systems are proposed. In recent years, the success of deep learning in the image classification and segmentation led to more and more scholars realizing the potential of performance improvement brought by utilizing the deep learning in the ultrasound CAD system. This paper summarized the research which focuses on the ultrasound CAD system utilizing machine learning technology in recent years. This study divided the ultrasound CAD system into two categories. One is the traditional ultrasound CAD system which employed the manmade feature and the other is the deep learning ultrasound CAD system. The major feature and the classifier employed by the traditional ultrasound CAD system are introduced. As for the deep learning ultrasound CAD, newest applications are summarized. This paper will be useful for researchers who focus on the ultrasound CAD system. PMID:29687000

Geographical topic learning for social images with a deep neural network

NASA Astrophysics Data System (ADS)

Feng, Jiangfan; Xu, Xin

2017-03-01

The use of geographical tagging in social-media images is becoming a part of image metadata and a great interest for geographical information science. It is well recognized that geographical topic learning is crucial for geographical annotation. Existing methods usually exploit geographical characteristics using image preprocessing, pixel-based classification, and feature recognition. How to effectively exploit the high-level semantic feature and underlying correlation among different types of contents is a crucial task for geographical topic learning. Deep learning (DL) has recently demonstrated robust capabilities for image tagging and has been introduced into geoscience. It extracts high-level features computed from a whole image component, where the cluttered background may dominate spatial features in the deep representation. Therefore, a method of spatial-attentional DL for geographical topic learning is provided and we can regard it as a special case of DL combined with various deep networks and tuning tricks. Results demonstrated that the method is discriminative for different types of geographical topic learning. In addition, it outperforms other sequential processing models in a tagging task for a geographical image dataset.

Machine Learning in Ultrasound Computer-Aided Diagnostic Systems: A Survey.

PubMed

Huang, Qinghua; Zhang, Fan; Li, Xuelong

2018-01-01

The ultrasound imaging is one of the most common schemes to detect diseases in the clinical practice. There are many advantages of ultrasound imaging such as safety, convenience, and low cost. However, reading ultrasound imaging is not easy. To support the diagnosis of clinicians and reduce the load of doctors, many ultrasound computer-aided diagnosis (CAD) systems are proposed. In recent years, the success of deep learning in the image classification and segmentation led to more and more scholars realizing the potential of performance improvement brought by utilizing the deep learning in the ultrasound CAD system. This paper summarized the research which focuses on the ultrasound CAD system utilizing machine learning technology in recent years. This study divided the ultrasound CAD system into two categories. One is the traditional ultrasound CAD system which employed the manmade feature and the other is the deep learning ultrasound CAD system. The major feature and the classifier employed by the traditional ultrasound CAD system are introduced. As for the deep learning ultrasound CAD, newest applications are summarized. This paper will be useful for researchers who focus on the ultrasound CAD system.

Quantum-assisted Helmholtz machines: A quantum–classical deep learning framework for industrial datasets in near-term devices

NASA Astrophysics Data System (ADS)

Benedetti, Marcello; Realpe-Gómez, John; Perdomo-Ortiz, Alejandro

2018-07-01

Machine learning has been presented as one of the key applications for near-term quantum technologies, given its high commercial value and wide range of applicability. In this work, we introduce the quantum-assisted Helmholtz machine:a hybrid quantum–classical framework with the potential of tackling high-dimensional real-world machine learning datasets on continuous variables. Instead of using quantum computers only to assist deep learning, as previous approaches have suggested, we use deep learning to extract a low-dimensional binary representation of data, suitable for processing on relatively small quantum computers. Then, the quantum hardware and deep learning architecture work together to train an unsupervised generative model. We demonstrate this concept using 1644 quantum bits of a D-Wave 2000Q quantum device to model a sub-sampled version of the MNIST handwritten digit dataset with 16 × 16 continuous valued pixels. Although we illustrate this concept on a quantum annealer, adaptations to other quantum platforms, such as ion-trap technologies or superconducting gate-model architectures, could be explored within this flexible framework.

Application of deep learning to the classification of images from colposcopy.

PubMed

Sato, Masakazu; Horie, Koji; Hara, Aki; Miyamoto, Yuichiro; Kurihara, Kazuko; Tomio, Kensuke; Yokota, Harushige

2018-03-01

The objective of the present study was to investigate whether deep learning could be applied successfully to the classification of images from colposcopy. For this purpose, a total of 158 patients who underwent conization were enrolled, and medical records and data from the gynecological oncology database were retrospectively reviewed. Deep learning was performed with the Keras neural network and TensorFlow libraries. Using preoperative images from colposcopy as the input data and deep learning technology, the patients were classified into three groups [severe dysplasia, carcinoma in situ (CIS) and invasive cancer (IC)]. A total of 485 images were obtained for the analysis, of which 142 images were of severe dysplasia (2.9 images/patient), 257 were of CIS (3.3 images/patient), and 86 were of IC (4.1 images/patient). Of these, 233 images were captured with a green filter, and the remaining 252 were captured without a green filter. Following the application of L2 regularization, L1 regularization, dropout and data augmentation, the accuracy of the validation dataset was ~50%. Although the present study is preliminary, the results indicated that deep learning may be applied to classify colposcopy images.

Fault Diagnosis for Rotating Machinery Using Vibration Measurement Deep Statistical Feature Learning.

PubMed

Li, Chuan; Sánchez, René-Vinicio; Zurita, Grover; Cerrada, Mariela; Cabrera, Diego

2016-06-17

Fault diagnosis is important for the maintenance of rotating machinery. The detection of faults and fault patterns is a challenging part of machinery fault diagnosis. To tackle this problem, a model for deep statistical feature learning from vibration measurements of rotating machinery is presented in this paper. Vibration sensor signals collected from rotating mechanical systems are represented in the time, frequency, and time-frequency domains, each of which is then used to produce a statistical feature set. For learning statistical features, real-value Gaussian-Bernoulli restricted Boltzmann machines (GRBMs) are stacked to develop a Gaussian-Bernoulli deep Boltzmann machine (GDBM). The suggested approach is applied as a deep statistical feature learning tool for both gearbox and bearing systems. The fault classification performances in experiments using this approach are 95.17% for the gearbox, and 91.75% for the bearing system. The proposed approach is compared to such standard methods as a support vector machine, GRBM and a combination model. In experiments, the best fault classification rate was detected using the proposed model. The results show that deep learning with statistical feature extraction has an essential improvement potential for diagnosing rotating machinery faults.

Fault Diagnosis for Rotating Machinery Using Vibration Measurement Deep Statistical Feature Learning

PubMed Central

Li, Chuan; Sánchez, René-Vinicio; Zurita, Grover; Cerrada, Mariela; Cabrera, Diego

2016-01-01

Fault diagnosis is important for the maintenance of rotating machinery. The detection of faults and fault patterns is a challenging part of machinery fault diagnosis. To tackle this problem, a model for deep statistical feature learning from vibration measurements of rotating machinery is presented in this paper. Vibration sensor signals collected from rotating mechanical systems are represented in the time, frequency, and time-frequency domains, each of which is then used to produce a statistical feature set. For learning statistical features, real-value Gaussian-Bernoulli restricted Boltzmann machines (GRBMs) are stacked to develop a Gaussian-Bernoulli deep Boltzmann machine (GDBM). The suggested approach is applied as a deep statistical feature learning tool for both gearbox and bearing systems. The fault classification performances in experiments using this approach are 95.17% for the gearbox, and 91.75% for the bearing system. The proposed approach is compared to such standard methods as a support vector machine, GRBM and a combination model. In experiments, the best fault classification rate was detected using the proposed model. The results show that deep learning with statistical feature extraction has an essential improvement potential for diagnosing rotating machinery faults. PMID:27322273

Application of deep learning to the classification of images from colposcopy

PubMed Central

Sato, Masakazu; Horie, Koji; Hara, Aki; Miyamoto, Yuichiro; Kurihara, Kazuko; Tomio, Kensuke; Yokota, Harushige

2018-01-01

The objective of the present study was to investigate whether deep learning could be applied successfully to the classification of images from colposcopy. For this purpose, a total of 158 patients who underwent conization were enrolled, and medical records and data from the gynecological oncology database were retrospectively reviewed. Deep learning was performed with the Keras neural network and TensorFlow libraries. Using preoperative images from colposcopy as the input data and deep learning technology, the patients were classified into three groups [severe dysplasia, carcinoma in situ (CIS) and invasive cancer (IC)]. A total of 485 images were obtained for the analysis, of which 142 images were of severe dysplasia (2.9 images/patient), 257 were of CIS (3.3 images/patient), and 86 were of IC (4.1 images/patient). Of these, 233 images were captured with a green filter, and the remaining 252 were captured without a green filter. Following the application of L2 regularization, L1 regularization, dropout and data augmentation, the accuracy of the validation dataset was ~50%. Although the present study is preliminary, the results indicated that deep learning may be applied to classify colposcopy images. PMID:29456725

Deep learning based tissue analysis predicts outcome in colorectal cancer.

PubMed

Bychkov, Dmitrii; Linder, Nina; Turkki, Riku; Nordling, Stig; Kovanen, Panu E; Verrill, Clare; Walliander, Margarita; Lundin, Mikael; Haglund, Caj; Lundin, Johan

2018-02-21

Image-based machine learning and deep learning in particular has recently shown expert-level accuracy in medical image classification. In this study, we combine convolutional and recurrent architectures to train a deep network to predict colorectal cancer outcome based on images of tumour tissue samples. The novelty of our approach is that we directly predict patient outcome, without any intermediate tissue classification. We evaluate a set of digitized haematoxylin-eosin-stained tumour tissue microarray (TMA) samples from 420 colorectal cancer patients with clinicopathological and outcome data available. The results show that deep learning-based outcome prediction with only small tissue areas as input outperforms (hazard ratio 2.3; CI 95% 1.79-3.03; AUC 0.69) visual histological assessment performed by human experts on both TMA spot (HR 1.67; CI 95% 1.28-2.19; AUC 0.58) and whole-slide level (HR 1.65; CI 95% 1.30-2.15; AUC 0.57) in the stratification into low- and high-risk patients. Our results suggest that state-of-the-art deep learning techniques can extract more prognostic information from the tissue morphology of colorectal cancer than an experienced human observer.

Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion

NASA Astrophysics Data System (ADS)

Ma, Ling; Guo, Rongrong; Zhang, Guoyi; Tade, Funmilayo; Schuster, David M.; Nieh, Peter; Master, Viraj; Fei, Baowei

2017-02-01

Automatic segmentation of the prostate on CT images has many applications in prostate cancer diagnosis and therapy. However, prostate CT image segmentation is challenging because of the low contrast of soft tissue on CT images. In this paper, we propose an automatic segmentation method by combining a deep learning method and multi-atlas refinement. First, instead of segmenting the whole image, we extract the region of interesting (ROI) to delete irrelevant regions. Then, we use the convolutional neural networks (CNN) to learn the deep features for distinguishing the prostate pixels from the non-prostate pixels in order to obtain the preliminary segmentation results. CNN can automatically learn the deep features adapting to the data, which are different from some handcrafted features. Finally, we select some similar atlases to refine the initial segmentation results. The proposed method has been evaluated on a dataset of 92 prostate CT images. Experimental results show that our method achieved a Dice similarity coefficient of 86.80% as compared to the manual segmentation. The deep learning based method can provide a useful tool for automatic segmentation of the prostate on CT images and thus can have a variety of clinical applications.

Prediction of enhancer-promoter interactions via natural language processing.

PubMed

Zeng, Wanwen; Wu, Mengmeng; Jiang, Rui

2018-05-09

Precise identification of three-dimensional genome organization, especially enhancer-promoter interactions (EPIs), is important to deciphering gene regulation, cell differentiation and disease mechanisms. Currently, it is a challenging task to distinguish true interactions from other nearby non-interacting ones since the power of traditional experimental methods is limited due to low resolution or low throughput. We propose a novel computational framework EP2vec to assay three-dimensional genomic interactions. We first extract sequence embedding features, defined as fixed-length vector representations learned from variable-length sequences using an unsupervised deep learning method in natural language processing. Then, we train a classifier to predict EPIs using the learned representations in supervised way. Experimental results demonstrate that EP2vec obtains F1 scores ranging from 0.841~ 0.933 on different datasets, which outperforms existing methods. We prove the robustness of sequence embedding features by carrying out sensitivity analysis. Besides, we identify motifs that represent cell line-specific information through analysis of the learned sequence embedding features by adopting attention mechanism. Last, we show that even superior performance with F1 scores 0.889~ 0.940 can be achieved by combining sequence embedding features and experimental features. EP2vec sheds light on feature extraction for DNA sequences of arbitrary lengths and provides a powerful approach for EPIs identification.

A deep convolutional neural network-based automatic delineation strategy for multiple brain metastases stereotactic radiosurgery

PubMed Central

Stojadinovic, Strahinja; Hrycushko, Brian; Wardak, Zabi; Lau, Steven; Lu, Weiguo; Yan, Yulong; Jiang, Steve B.; Zhen, Xin; Timmerman, Robert; Nedzi, Lucien

2017-01-01

Accurate and automatic brain metastases target delineation is a key step for efficient and effective stereotactic radiosurgery (SRS) treatment planning. In this work, we developed a deep learning convolutional neural network (CNN) algorithm for segmenting brain metastases on contrast-enhanced T1-weighted magnetic resonance imaging (MRI) datasets. We integrated the CNN-based algorithm into an automatic brain metastases segmentation workflow and validated on both Multimodal Brain Tumor Image Segmentation challenge (BRATS) data and clinical patients' data. Validation on BRATS data yielded average DICE coefficients (DCs) of 0.75±0.07 in the tumor core and 0.81±0.04 in the enhancing tumor, which outperformed most techniques in the 2015 BRATS challenge. Segmentation results of patient cases showed an average of DCs 0.67±0.03 and achieved an area under the receiver operating characteristic curve of 0.98±0.01. The developed automatic segmentation strategy surpasses current benchmark levels and offers a promising tool for SRS treatment planning for multiple brain metastases. PMID:28985229

Applications of Deep Learning and Reinforcement Learning to Biological Data.

PubMed

Mahmud, Mufti; Kaiser, Mohammed Shamim; Hussain, Amir; Vassanelli, Stefano

2018-06-01

Rapid advances in hardware-based technologies during the past decades have opened up new possibilities for life scientists to gather multimodal data in various application domains, such as omics, bioimaging, medical imaging, and (brain/body)-machine interfaces. These have generated novel opportunities for development of dedicated data-intensive machine learning techniques. In particular, recent research in deep learning (DL), reinforcement learning (RL), and their combination (deep RL) promise to revolutionize the future of artificial intelligence. The growth in computational power accompanied by faster and increased data storage, and declining computing costs have already allowed scientists in various fields to apply these techniques on data sets that were previously intractable owing to their size and complexity. This paper provides a comprehensive survey on the application of DL, RL, and deep RL techniques in mining biological data. In addition, we compare the performances of DL techniques when applied to different data sets across various application domains. Finally, we outline open issues in this challenging research area and discuss future development perspectives.

Deep Learning for Flow Sculpting: Insights into Efficient Learning using Scientific Simulation Data

NASA Astrophysics Data System (ADS)

Stoecklein, Daniel; Lore, Kin Gwn; Davies, Michael; Sarkar, Soumik; Ganapathysubramanian, Baskar

2017-04-01

A new technique for shaping microfluid flow, known as flow sculpting, offers an unprecedented level of passive fluid flow control, with potential breakthrough applications in advancing manufacturing, biology, and chemistry research at the microscale. However, efficiently solving the inverse problem of designing a flow sculpting device for a desired fluid flow shape remains a challenge. Current approaches struggle with the many-to-one design space, requiring substantial user interaction and the necessity of building intuition, all of which are time and resource intensive. Deep learning has emerged as an efficient function approximation technique for high-dimensional spaces, and presents a fast solution to the inverse problem, yet the science of its implementation in similarly defined problems remains largely unexplored. We propose that deep learning methods can completely outpace current approaches for scientific inverse problems while delivering comparable designs. To this end, we show how intelligent sampling of the design space inputs can make deep learning methods more competitive in accuracy, while illustrating their generalization capability to out-of-sample predictions.

Phenotypic Antimicrobial Susceptibility Testing with Deep Learning Video Microscopy.

PubMed

Yu, Hui; Jing, Wenwen; Iriya, Rafael; Yang, Yunze; Syal, Karan; Mo, Manni; Grys, Thomas E; Haydel, Shelley E; Wang, Shaopeng; Tao, Nongjian

2018-05-15

Timely determination of antimicrobial susceptibility for a bacterial infection enables precision prescription, shortens treatment time, and helps minimize the spread of antibiotic resistant infections. Current antimicrobial susceptibility testing (AST) methods often take several days and thus impede these clinical and health benefits. Here, we present an AST method by imaging freely moving bacterial cells in urine in real time and analyzing the videos with a deep learning algorithm. The deep learning algorithm determines if an antibiotic inhibits a bacterial cell by learning multiple phenotypic features of the cell without the need for defining and quantifying each feature. We apply the method to urinary tract infection, a common infection that affects millions of people, to determine the minimum inhibitory concentration of pathogens from both bacteria spiked urine and clinical infected urine samples for different antibiotics within 30 min and validate the results with the gold standard broth macrodilution method. The deep learning video microscopy-based AST holds great potential to contribute to the solution of increasing drug-resistant infections.

Blackboxing: social learning strategies and cultural evolution.

PubMed

Heyes, Cecilia

2016-05-05

Social learning strategies (SLSs) enable humans, non-human animals, and artificial agents to make adaptive decisions aboutwhenthey should copy other agents, andwhothey should copy. Behavioural ecologists and economists have discovered an impressive range of SLSs, and explored their likely impact on behavioural efficiency and reproductive fitness while using the 'phenotypic gambit'; ignoring, or remaining deliberately agnostic about, the nature and origins of the cognitive processes that implement SLSs. Here I argue that this 'blackboxing' of SLSs is no longer a viable scientific strategy. It has contributed, through the 'social learning strategies tournament', to the premature conclusion that social learning is generally better than asocial learning, and to a deep puzzle about the relationship between SLSs and cultural evolution. The puzzle can be solved by recognizing that whereas most SLSs are 'planetary'--they depend on domain-general cognitive processes--some SLSs, found only in humans, are 'cook-like'--they depend on explicit, metacognitive rules, such ascopy digital natives. These metacognitive SLSs contribute to cultural evolution by fostering the development of processes that enhance the exclusivity, specificity, and accuracy of social learning. © 2016 The Author(s).

Large-scale Exploration of Neuronal Morphologies Using Deep Learning and Augmented Reality.

PubMed

Li, Zhongyu; Butler, Erik; Li, Kang; Lu, Aidong; Ji, Shuiwang; Zhang, Shaoting

2018-02-12

Recently released large-scale neuron morphological data has greatly facilitated the research in neuroinformatics. However, the sheer volume and complexity of these data pose significant challenges for efficient and accurate neuron exploration. In this paper, we propose an effective retrieval framework to address these problems, based on frontier techniques of deep learning and binary coding. For the first time, we develop a deep learning based feature representation method for the neuron morphological data, where the 3D neurons are first projected into binary images and then learned features using an unsupervised deep neural network, i.e., stacked convolutional autoencoders (SCAEs). The deep features are subsequently fused with the hand-crafted features for more accurate representation. Considering the exhaustive search is usually very time-consuming in large-scale databases, we employ a novel binary coding method to compress feature vectors into short binary codes. Our framework is validated on a public data set including 58,000 neurons, showing promising retrieval precision and efficiency compared with state-of-the-art methods. In addition, we develop a novel neuron visualization program based on the techniques of augmented reality (AR), which can help users take a deep exploration of neuron morphologies in an interactive and immersive manner.

Development and application of deep convolutional neural network in target detection

NASA Astrophysics Data System (ADS)

Jiang, Xiaowei; Wang, Chunping; Fu, Qiang

2018-04-01

With the development of big data and algorithms, deep convolution neural networks with more hidden layers have more powerful feature learning and feature expression ability than traditional machine learning methods, making artificial intelligence surpass human level in many fields. This paper first reviews the development and application of deep convolutional neural networks in the field of object detection in recent years, then briefly summarizes and ponders some existing problems in the current research, and the future development of deep convolutional neural network is prospected.

The Next Era: Deep Learning in Pharmaceutical Research.

PubMed

Ekins, Sean

2016-11-01

Over the past decade we have witnessed the increasing sophistication of machine learning algorithms applied in daily use from internet searches, voice recognition, social network software to machine vision software in cameras, phones, robots and self-driving cars. Pharmaceutical research has also seen its fair share of machine learning developments. For example, applying such methods to mine the growing datasets that are created in drug discovery not only enables us to learn from the past but to predict a molecule's properties and behavior in future. The latest machine learning algorithm garnering significant attention is deep learning, which is an artificial neural network with multiple hidden layers. Publications over the last 3 years suggest that this algorithm may have advantages over previous machine learning methods and offer a slight but discernable edge in predictive performance. The time has come for a balanced review of this technique but also to apply machine learning methods such as deep learning across a wider array of endpoints relevant to pharmaceutical research for which the datasets are growing such as physicochemical property prediction, formulation prediction, absorption, distribution, metabolism, excretion and toxicity (ADME/Tox), target prediction and skin permeation, etc. We also show that there are many potential applications of deep learning beyond cheminformatics. It will be important to perform prospective testing (which has been carried out rarely to date) in order to convince skeptics that there will be benefits from investing in this technique.

Deep Hashing for Scalable Image Search.

PubMed

Lu, Jiwen; Liong, Venice Erin; Zhou, Jie

2017-05-01

In this paper, we propose a new deep hashing (DH) approach to learn compact binary codes for scalable image search. Unlike most existing binary codes learning methods, which usually seek a single linear projection to map each sample into a binary feature vector, we develop a deep neural network to seek multiple hierarchical non-linear transformations to learn these binary codes, so that the non-linear relationship of samples can be well exploited. Our model is learned under three constraints at the top layer of the developed deep network: 1) the loss between the compact real-valued code and the learned binary vector is minimized, 2) the binary codes distribute evenly on each bit, and 3) different bits are as independent as possible. To further improve the discriminative power of the learned binary codes, we extend DH into supervised DH (SDH) and multi-label SDH by including a discriminative term into the objective function of DH, which simultaneously maximizes the inter-class variations and minimizes the intra-class variations of the learned binary codes with the single-label and multi-label settings, respectively. Extensive experimental results on eight widely used image search data sets show that our proposed methods achieve very competitive results with the state-of-the-arts.

ROOFN3D: Deep Learning Training Data for 3d Building Reconstruction

NASA Astrophysics Data System (ADS)

Wichmann, A.; Agoub, A.; Kada, M.

2018-05-01

Machine learning methods have gained in importance through the latest development of artificial intelligence and computer hardware. Particularly approaches based on deep learning have shown that they are able to provide state-of-the-art results for various tasks. However, the direct application of deep learning methods to improve the results of 3D building reconstruction is often not possible due, for example, to the lack of suitable training data. To address this issue, we present RoofN3D which provides a new 3D point cloud training dataset that can be used to train machine learning models for different tasks in the context of 3D building reconstruction. It can be used, among others, to train semantic segmentation networks or to learn the structure of buildings and the geometric model construction. Further details about RoofN3D and the developed data preparation framework, which enables the automatic derivation of training data, are described in this paper. Furthermore, we provide an overview of other available 3D point cloud training data and approaches from current literature in which solutions for the application of deep learning to unstructured and not gridded 3D point cloud data are presented.

DeepSynergy: predicting anti-cancer drug synergy with Deep Learning

PubMed Central

Preuer, Kristina; Lewis, Richard P I; Hochreiter, Sepp; Bender, Andreas; Bulusu, Krishna C; Klambauer, Günter

2018-01-01

Abstract Motivation While drug combination therapies are a well-established concept in cancer treatment, identifying novel synergistic combinations is challenging due to the size of combinatorial space. However, computational approaches have emerged as a time- and cost-efficient way to prioritize combinations to test, based on recently available large-scale combination screening data. Recently, Deep Learning has had an impact in many research areas by achieving new state-of-the-art model performance. However, Deep Learning has not yet been applied to drug synergy prediction, which is the approach we present here, termed DeepSynergy. DeepSynergy uses chemical and genomic information as input information, a normalization strategy to account for input data heterogeneity, and conical layers to model drug synergies. Results DeepSynergy was compared to other machine learning methods such as Gradient Boosting Machines, Random Forests, Support Vector Machines and Elastic Nets on the largest publicly available synergy dataset with respect to mean squared error. DeepSynergy significantly outperformed the other methods with an improvement of 7.2% over the second best method at the prediction of novel drug combinations within the space of explored drugs and cell lines. At this task, the mean Pearson correlation coefficient between the measured and the predicted values of DeepSynergy was 0.73. Applying DeepSynergy for classification of these novel drug combinations resulted in a high predictive performance of an AUC of 0.90. Furthermore, we found that all compared methods exhibit low predictive performance when extrapolating to unexplored drugs or cell lines, which we suggest is due to limitations in the size and diversity of the dataset. We envision that DeepSynergy could be a valuable tool for selecting novel synergistic drug combinations. Availability and implementation DeepSynergy is available via www.bioinf.jku.at/software/DeepSynergy. Contact klambauer@bioinf.jku.at Supplementary information Supplementary data are available at Bioinformatics online. PMID:29253077

Deep learning based syndrome diagnosis of chronic gastritis.

PubMed

Liu, Guo-Ping; Yan, Jian-Jun; Wang, Yi-Qin; Zheng, Wu; Zhong, Tao; Lu, Xiong; Qian, Peng

2014-01-01

In Traditional Chinese Medicine (TCM), most of the algorithms used to solve problems of syndrome diagnosis are superficial structure algorithms and not considering the cognitive perspective from the brain. However, in clinical practice, there is complex and nonlinear relationship between symptoms (signs) and syndrome. So we employed deep leaning and multilabel learning to construct the syndrome diagnostic model for chronic gastritis (CG) in TCM. The results showed that deep learning could improve the accuracy of syndrome recognition. Moreover, the studies will provide a reference for constructing syndrome diagnostic models and guide clinical practice.

Deep Learning Based Syndrome Diagnosis of Chronic Gastritis

PubMed Central

Liu, Guo-Ping; Wang, Yi-Qin; Zheng, Wu; Zhong, Tao; Lu, Xiong; Qian, Peng

2014-01-01

In Traditional Chinese Medicine (TCM), most of the algorithms used to solve problems of syndrome diagnosis are superficial structure algorithms and not considering the cognitive perspective from the brain. However, in clinical practice, there is complex and nonlinear relationship between symptoms (signs) and syndrome. So we employed deep leaning and multilabel learning to construct the syndrome diagnostic model for chronic gastritis (CG) in TCM. The results showed that deep learning could improve the accuracy of syndrome recognition. Moreover, the studies will provide a reference for constructing syndrome diagnostic models and guide clinical practice. PMID:24734118

An Automatic Detection System of Lung Nodule Based on Multi-Group Patch-Based Deep Learning Network.

PubMed

Jiang, Hongyang; Ma, He; Qian, Wei; Gao, Mengdi; Li, Yan

2017-07-14

High-efficiency lung nodule detection dramatically contributes to the risk assessment of lung cancer. It is a significant and challenging task to quickly locate the exact positions of lung nodules. Extensive work has been done by researchers around this domain for approximately two decades. However, previous computer aided detection (CADe) schemes are mostly intricate and time-consuming since they may require more image processing modules, such as the computed tomography (CT) image transformation, the lung nodule segmentation and the feature extraction, to construct a whole CADe system. It is difficult for those schemes to process and analyze enormous data when the medical images continue to increase. Besides, some state of the art deep learning schemes may be strict in the standard of database. This study proposes an effective lung nodule detection scheme based on multi-group patches cut out from the lung images, which are enhanced by the Frangi filter. Through combining two groups of images, a four-channel convolution neural networks (CNN) model is designed to learn the knowledge of radiologists for detecting nodules of four levels. This CADe scheme can acquire the sensitivity of 80.06% with 4.7 false positives per scan and the sensitivity of 94% with 15.1 false positives per scan. The results demonstrate that the multi-group patch-based learning system is efficient to improve the performance of lung nodule detection and greatly reduce the false positives under a huge amount of image data.

Identification and tracking of vertebrae in ultrasound using deep networks with unsupervised feature learning

NASA Astrophysics Data System (ADS)

Hetherington, Jorden; Pesteie, Mehran; Lessoway, Victoria A.; Abolmaesumi, Purang; Rohling, Robert N.

2017-03-01

Percutaneous needle insertion procedures on the spine often require proper identification of the vertebral level in order to effectively deliver anesthetics and analgesic agents to achieve adequate block. For example, in obstetric epidurals, the target is at the L3-L4 intervertebral space. The current clinical method involves "blind" identification of the vertebral level through manual palpation of the spine, which has only 30% accuracy. This implies the need for better anatomical identification prior to needle insertion. A system is proposed to identify the vertebrae, assigning them to their respective levels, and track them in a standard sequence of ultrasound images, when imaged in the paramedian plane. Machine learning techniques are developed to identify discriminative features of the laminae. In particular, a deep network is trained to automatically learn the anatomical features of the lamina peaks, and classify image patches, for pixel-level classification. The chosen network utilizes multiple connected auto-encoders to learn the anatomy. Pre-processing with ultrasound bone enhancement techniques is done to aid the pixel-level classification performance. Once the lamina are identified, vertebrae are assigned levels and tracked in sequential frames. Experimental results were evaluated against an expert sonographer. Based on data acquired from 15 subjects, vertebrae identification with sensitivity of 95% and precision of 95% was achieved within each frame. Between pairs of subsequently analyzed frames, matches of predicted vertebral level labels were correct in 94% of cases, when compared to matches of manually selected labels

Trans-species learning of cellular signaling systems with bimodal deep belief networks.

PubMed

Chen, Lujia; Cai, Chunhui; Chen, Vicky; Lu, Xinghua

2015-09-15

Model organisms play critical roles in biomedical research of human diseases and drug development. An imperative task is to translate information/knowledge acquired from model organisms to humans. In this study, we address a trans-species learning problem: predicting human cell responses to diverse stimuli, based on the responses of rat cells treated with the same stimuli. We hypothesized that rat and human cells share a common signal-encoding mechanism but employ different proteins to transmit signals, and we developed a bimodal deep belief network and a semi-restricted bimodal deep belief network to represent the common encoding mechanism and perform trans-species learning. These 'deep learning' models include hierarchically organized latent variables capable of capturing the statistical structures in the observed proteomic data in a distributed fashion. The results show that the models significantly outperform two current state-of-the-art classification algorithms. Our study demonstrated the potential of using deep hierarchical models to simulate cellular signaling systems. The software is available at the following URL: http://pubreview.dbmi.pitt.edu/TransSpeciesDeepLearning/. The data are available through SBV IMPROVER website, https://www.sbvimprover.com/challenge-2/overview, upon publication of the report by the organizers. xinghua@pitt.edu Supplementary data are available at Bioinformatics online. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

A novel deep learning approach for classification of EEG motor imagery signals.

PubMed

Tabar, Yousef Rezaei; Halici, Ugur

2017-02-01

Signal classification is an important issue in brain computer interface (BCI) systems. Deep learning approaches have been used successfully in many recent studies to learn features and classify different types of data. However, the number of studies that employ these approaches on BCI applications is very limited. In this study we aim to use deep learning methods to improve classification performance of EEG motor imagery signals. In this study we investigate convolutional neural networks (CNN) and stacked autoencoders (SAE) to classify EEG Motor Imagery signals. A new form of input is introduced to combine time, frequency and location information extracted from EEG signal and it is used in CNN having one 1D convolutional and one max-pooling layers. We also proposed a new deep network by combining CNN and SAE. In this network, the features that are extracted in CNN are classified through the deep network SAE. The classification performance obtained by the proposed method on BCI competition IV dataset 2b in terms of kappa value is 0.547. Our approach yields 9% improvement over the winner algorithm of the competition. Our results show that deep learning methods provide better classification performance compared to other state of art approaches. These methods can be applied successfully to BCI systems where the amount of data is large due to daily recording.

Teaching neuroanatomy using computer-aided learning: What makes for successful outcomes?

PubMed

Svirko, Elena; Mellanby, Jane

2017-11-01

Computer-aided learning (CAL) is an integral part of many medical courses. The neuroscience course at Oxford University for medical students includes CAL course of neuroanatomy. CAL is particularly suited to this since neuroanatomy requires much detailed three-dimensional visualization, which can be presented on screen. The CAL course was evaluated using the concept of approach to learning. The aims of university teaching are congruent with the deep approach-seeking meaning and relating new information to previous knowledge-rather than to the surface approach of concentrating on rote learning of detail. Seven cohorts of medical students (N = 869) filled in approach to learning scale and a questionnaire investigating their engagement with the CAL course. The students' scores on CAL-course-based neuroanatomy assessment and later university examinations were obtained. Although the students reported less use of the deep approach for the neuroanatomy CAL course than for the rest of their neuroanatomy course (mean = 24.99 vs. 31.49, P < 0.001), deep approach for CAL was positively correlated with neuroanatomy assessment performance (r = 0.12, P < 0.001). Time spent on the CAL course, enjoyment of it, the amount of CAL videos watched and quizzes completed were each significantly positively related to deep approach. The relationship between deep approach and enjoyment was particularly notable (25.5% shared variance). Reported relationships between deep approach and academic performance support the desirability of deep approach in university students. It is proposed that enjoyment of the course and the deep approach could be increased by incorporation of more clinical material which is what the students liked most. Anat Sci Educ 10: 560-569. © 2017 American Association of Anatomists. © 2017 American Association of Anatomists.

Exploring the relationships between epistemic beliefs about medicine and approaches to learning medicine: a structural equation modeling analysis.

PubMed

Chiu, Yen-Lin; Liang, Jyh-Chong; Hou, Cheng-Yen; Tsai, Chin-Chung

2016-07-18

Students' epistemic beliefs may vary in different domains; therefore, it may be beneficial for medical educators to better understand medical students' epistemic beliefs regarding medicine. Understanding how medical students are aware of medical knowledge and how they learn medicine is a critical issue of medical education. The main purposes of this study were to investigate medical students' epistemic beliefs relating to medical knowledge, and to examine their relationships with students' approaches to learning medicine. A total of 340 undergraduate medical students from 9 medical colleges in Taiwan were surveyed with the Medical-Specific Epistemic Beliefs (MSEB) questionnaire (i.e., multi-source, uncertainty, development, justification) and the Approach to Learning Medicine (ALM) questionnaire (i.e., surface motive, surface strategy, deep motive, and deep strategy). By employing the structural equation modeling technique, the confirmatory factor analysis and path analysis were conducted to validate the questionnaires and explore the structural relations between these two constructs. It was indicated that medical students with multi-source beliefs who were suspicious of medical knowledge transmitted from authorities were less likely to possess a surface motive and deep strategies. Students with beliefs regarding uncertain medical knowledge tended to utilize flexible approaches, that is, they were inclined to possess a surface motive but adopt deep strategies. Students with beliefs relating to justifying medical knowledge were more likely to have mixed motives (both surface and deep motives) and mixed strategies (both surface and deep strategies). However, epistemic beliefs regarding development did not have significant relations with approaches to learning. Unexpectedly, it was found that medical students with sophisticated epistemic beliefs (e.g., suspecting knowledge from medical experts) did not necessarily engage in deep approaches to learning medicine. Instead of a deep approach, medical students with sophisticated epistemic beliefs in uncertain and justifying medical knowledge intended to employ a flexible approach and a mixed approach, respectively.

Using Computer Technology to Foster Learning for Understanding

PubMed Central

VAN MELLE, ELAINE; TOMALTY, LEWIS

2000-01-01

The literature shows that students typically use either a surface approach to learning, in which the emphasis is on memorization of facts, or a deep approach to learning, in which learning for understanding is the primary focus. This paper describes how computer technology, specifically the use of a multimedia CD-ROM, was integrated into a microbiology curriculum as part of the transition from focusing on facts to fostering learning for understanding. Evaluation of the changes in approaches to learning over the course of the term showed a statistically significant shift in a deep approach to learning, as measured by the Study Process Questionnaire. Additional data collected showed that the use of computer technology supported this shift by providing students with the opportunity to apply what they had learned in class to order tests and interpret the test results in relation to specific patient-focused case studies. The extent of the impact, however, varied among different groups of students in the class. For example, students who were recent high school graduates did not show a statistically significant increase in deep learning scores over the course of the term and did not perform as well in the course. The results also showed that a surface approach to learning was an important aspect of learning for understanding, although only those students who were able to combine a surface with a deep approach to learning were successfully able to learn for understanding. Implications of this finding for the future use of computer technology and learning for understanding are considered. PMID:23653533

Efficacy of a Deep Learning System for Detecting Glaucomatous Optic Neuropathy Based on Color Fundus Photographs.

PubMed

Li, Zhixi; He, Yifan; Keel, Stuart; Meng, Wei; Chang, Robert T; He, Mingguang

2018-03-02

To assess the performance of a deep learning algorithm for detecting referable glaucomatous optic neuropathy (GON) based on color fundus photographs. A deep learning system for the classification of GON was developed for automated classification of GON on color fundus photographs. We retrospectively included 48 116 fundus photographs for the development and validation of a deep learning algorithm. This study recruited 21 trained ophthalmologists to classify the photographs. Referable GON was defined as vertical cup-to-disc ratio of 0.7 or more and other typical changes of GON. The reference standard was made until 3 graders achieved agreement. A separate validation dataset of 8000 fully gradable fundus photographs was used to assess the performance of this algorithm. The area under receiver operator characteristic curve (AUC) with sensitivity and specificity was applied to evaluate the efficacy of the deep learning algorithm detecting referable GON. In the validation dataset, this deep learning system achieved an AUC of 0.986 with sensitivity of 95.6% and specificity of 92.0%. The most common reasons for false-negative grading (n = 87) were GON with coexisting eye conditions (n = 44 [50.6%]), including pathologic or high myopia (n = 37 [42.6%]), diabetic retinopathy (n = 4 [4.6%]), and age-related macular degeneration (n = 3 [3.4%]). The leading reason for false-positive results (n = 480) was having other eye conditions (n = 458 [95.4%]), mainly including physiologic cupping (n = 267 [55.6%]). Misclassification as false-positive results amidst a normal-appearing fundus occurred in only 22 eyes (4.6%). A deep learning system can detect referable GON with high sensitivity and specificity. Coexistence of high or pathologic myopia is the most common cause resulting in false-negative results. Physiologic cupping and pathologic myopia were the most common reasons for false-positive results. Copyright © 2018 American Academy of Ophthalmology. Published by Elsevier Inc. All rights reserved.

A deep learning approach for pose estimation from volumetric OCT data.

PubMed

Gessert, Nils; Schlüter, Matthias; Schlaefer, Alexander

2018-05-01

Tracking the pose of instruments is a central problem in image-guided surgery. For microscopic scenarios, optical coherence tomography (OCT) is increasingly used as an imaging modality. OCT is suitable for accurate pose estimation due to its micrometer range resolution and volumetric field of view. However, OCT image processing is challenging due to speckle noise and reflection artifacts in addition to the images' 3D nature. We address pose estimation from OCT volume data with a new deep learning-based tracking framework. For this purpose, we design a new 3D convolutional neural network (CNN) architecture to directly predict the 6D pose of a small marker geometry from OCT volumes. We use a hexapod robot to automatically acquire labeled data points which we use to train 3D CNN architectures for multi-output regression. We use this setup to provide an in-depth analysis on deep learning-based pose estimation from volumes. Specifically, we demonstrate that exploiting volume information for pose estimation yields higher accuracy than relying on 2D representations with depth information. Supporting this observation, we provide quantitative and qualitative results that 3D CNNs effectively exploit the depth structure of marker objects. Regarding the deep learning aspect, we present efficient design principles for 3D CNNs, making use of insights from the 2D deep learning community. In particular, we present Inception3D as a new architecture which performs best for our application. We show that our deep learning approach reaches errors at our ground-truth label's resolution. We achieve a mean average error of 14.89 ± 9.3 µm and 0.096 ± 0.072° for position and orientation learning, respectively. Copyright © 2018 Elsevier B.V. All rights reserved.

Personal experience narratives by students: a teaching-learning tool in bioethics.

PubMed

Pandya, Radhika H; Shukla, Radha; Gor, Alpa P; Ganguly, Barna

2016-01-01

The principles of bioethics have been identified as important requirements for training basic medical doctors. Till now, various modalities have been used for teaching bioethics, such as lectures, followed by a small case-based discussion, case vignettes or debates among students. For effective teaching-learning of bioethics, it is necessary to integrate theory and practice rather than merely teach theoretical constructs without helping the students translate those constructs into practice. Classroom teaching can focus on the theoretical knowledge of professional relationships, patient-doctor relationships, issues at the beginning and end of life, reproductive technologies, etc. However, a better learning environment can be created through an experiencebased approach to complement lectures and facilitate successful teaching. Engaging students in reflective dialogue with their peers would allow them to refine their ideas with respect to learning ethics. It can help in the development both of the cognitive and affective domains of the teaching of bioethics. Real-life narratives by the interns, when used as case or situation analysis models for a particular ethical issue, can enhance other students' insight and give them a moral boost. Doing this can change the classroom atmosphere, enhance motivation, improve the students' aptitude and improve their attitude towards learning bioethics. Involving the students in this manner can prove to be a sustainable way of achieving the goal of deep reflective learning of bioethics and can serve as a new technique for maintaining the interest of students as well as teachers.

Deep Learning Method for Denial of Service Attack Detection Based on Restricted Boltzmann Machine.

PubMed

Imamverdiyev, Yadigar; Abdullayeva, Fargana

2018-06-01

In this article, the application of the deep learning method based on Gaussian-Bernoulli type restricted Boltzmann machine (RBM) to the detection of denial of service (DoS) attacks is considered. To increase the DoS attack detection accuracy, seven additional layers are added between the visible and the hidden layers of the RBM. Accurate results in DoS attack detection are obtained by optimization of the hyperparameters of the proposed deep RBM model. The form of the RBM that allows application of the continuous data is used. In this type of RBM, the probability distribution of the visible layer is replaced by a Gaussian distribution. Comparative analysis of the accuracy of the proposed method with Bernoulli-Bernoulli RBM, Gaussian-Bernoulli RBM, deep belief network type deep learning methods on DoS attack detection is provided. Detection accuracy of the methods is verified on the NSL-KDD data set. Higher accuracy from the proposed multilayer deep Gaussian-Bernoulli type RBM is obtained.

Deep learning architecture for iris recognition based on optimal Gabor filters and deep belief network

NASA Astrophysics Data System (ADS)

He, Fei; Han, Ye; Wang, Han; Ji, Jinchao; Liu, Yuanning; Ma, Zhiqiang

2017-03-01

Gabor filters are widely utilized to detect iris texture information in several state-of-the-art iris recognition systems. However, the proper Gabor kernels and the generative pattern of iris Gabor features need to be predetermined in application. The traditional empirical Gabor filters and shallow iris encoding ways are incapable of dealing with such complex variations in iris imaging including illumination, aging, deformation, and device variations. Thereby, an adaptive Gabor filter selection strategy and deep learning architecture are presented. We first employ particle swarm optimization approach and its binary version to define a set of data-driven Gabor kernels for fitting the most informative filtering bands, and then capture complex pattern from the optimal Gabor filtered coefficients by a trained deep belief network. A succession of comparative experiments validate that our optimal Gabor filters may produce more distinctive Gabor coefficients and our iris deep representations be more robust and stable than traditional iris Gabor codes. Furthermore, the depth and scales of the deep learning architecture are also discussed.

Comparison of hand-craft feature based SVM and CNN based deep learning framework for automatic polyp classification.

PubMed

Younghak Shin; Balasingham, Ilangko

2017-07-01

Colonoscopy is a standard method for screening polyps by highly trained physicians. Miss-detected polyps in colonoscopy are potential risk factor for colorectal cancer. In this study, we investigate an automatic polyp classification framework. We aim to compare two different approaches named hand-craft feature method and convolutional neural network (CNN) based deep learning method. Combined shape and color features are used for hand craft feature extraction and support vector machine (SVM) method is adopted for classification. For CNN approach, three convolution and pooling based deep learning framework is used for classification purpose. The proposed framework is evaluated using three public polyp databases. From the experimental results, we have shown that the CNN based deep learning framework shows better classification performance than the hand-craft feature based methods. It achieves over 90% of classification accuracy, sensitivity, specificity and precision.

Interpretable Deep Models for ICU Outcome Prediction

PubMed Central

Che, Zhengping; Purushotham, Sanjay; Khemani, Robinder; Liu, Yan

2016-01-01

Exponential surge in health care data, such as longitudinal data from electronic health records (EHR), sensor data from intensive care unit (ICU), etc., is providing new opportunities to discover meaningful data-driven characteristics and patterns ofdiseases. Recently, deep learning models have been employedfor many computational phenotyping and healthcare prediction tasks to achieve state-of-the-art performance. However, deep models lack interpretability which is crucial for wide adoption in medical research and clinical decision-making. In this paper, we introduce a simple yet powerful knowledge-distillation approach called interpretable mimic learning, which uses gradient boosting trees to learn interpretable models and at the same time achieves strong prediction performance as deep learning models. Experiment results on Pediatric ICU dataset for acute lung injury (ALI) show that our proposed method not only outperforms state-of-the-art approaches for morality and ventilator free days prediction tasks but can also provide interpretable models to clinicians. PMID:28269832

Can Creative Podcasting Promote Deep Learning? The Use of Podcasting for Learning Content in an Undergraduate Science Unit

ERIC Educational Resources Information Center

Pegrum, Mark; Bartle, Emma; Longnecker, Nancy

2015-01-01

This paper examines the effect of a podcasting task on the examination performance of several hundred first-year chemistry undergraduate students. Educational researchers have established that a deep approach to learning that promotes active understanding of meaning can lead to better student outcomes, higher grades and superior retention of…

Transforming Passive Receptivity of Knowledge into Deep Learning Experiences at the Undergraduate Level: An Example from Music Theory

ERIC Educational Resources Information Center

Ferenc, Anna

2015-01-01

This article discusses transformation of passive knowledge receptivity into experiences of deep learning in a lecture-based music theory course at the second-year undergraduate level through implementation of collaborative projects that evoke natural critical learning environments. It presents an example of such a project, addresses key features…

Using Flipped Classroom Approach to Explore Deep Learning in Large Classrooms

ERIC Educational Resources Information Center

Danker, Brenda

2015-01-01

This project used two Flipped Classroom approaches to stimulate deep learning in large classrooms during the teaching of a film module as part of a Diploma in Performing Arts course at Sunway University, Malaysia. The flipped classes utilized either a blended learning approach where students first watched online lectures as homework, and then…

Aligning Seminars with Bologna Requirements: Reciprocal Peer Tutoring, the Solo Taxonomy and Deep Learning

ERIC Educational Resources Information Center

Lueg, Rainer; Lueg, Klarissa; Lauridsen, Ole

2016-01-01

Changes in public policy, such as the Bologna Process, require students to be equipped with multifunctional competencies to master relevant tasks in unfamiliar situations. Achieving this goal might imply a change in many curricula toward deeper learning. As a didactical means to achieve deep learning results, the authors suggest reciprocal peer…

Student Engagement for Effective Teaching and Deep Learning

ERIC Educational Resources Information Center

Dunleavy, Jodene; Milton, Penny

2008-01-01

Today, all young people need to learn to "use their minds well" through deep engagement in learning that reflects skills, knowledge, and dispositions fit for their present lives as well as the ones they aspire to in the future. More than ever, their health and well being, success in the workplace, ability to construct identities and…

Are Deep Strategic Learners Better Suited to PBL? A Preliminary Study

ERIC Educational Resources Information Center

Papinczak, Tracey

2009-01-01

The aim of this study was to determine if medical students categorised as having deep and strategic approaches to their learning find problem-based learning (PBL) enjoyable and supportive of their learning, and achieve well in the first-year course. Quantitative and qualitative data were gathered from first-year medical students (N = 213). All…

Deep Learning in Distance Education: Are We Achieving the Goal?

ERIC Educational Resources Information Center

Shearer, Rick L.; Gregg, Andrea; Joo, K. P.

2015-01-01

As educators, one of our goals is to help students arrive at deeper levels of learning. However, how is this accomplished, especially in online courses? This design-based research study explored the concept of deep learning through a series of design changes in a graduate education course. A key question that emerged was through what learning…

Pleasure, Learning, Video Games, and Life: The Projective Stance

ERIC Educational Resources Information Center

Gee, James Paul

2005-01-01

This article addresses three questions. First, what is the deep pleasure that humans take from video games? Second, what is the relationship between video games and real life? Third, what do the answers to these questions have to do with learning? Good commercial video games are deep technologies for recruiting learning as a form of profound…

Understanding Clinical Mammographic Breast Density Assessment: a Deep Learning Perspective.

PubMed

Mohamed, Aly A; Luo, Yahong; Peng, Hong; Jankowitz, Rachel C; Wu, Shandong

2017-09-20

Mammographic breast density has been established as an independent risk marker for developing breast cancer. Breast density assessment is a routine clinical need in breast cancer screening and current standard is using the Breast Imaging and Reporting Data System (BI-RADS) criteria including four qualitative categories (i.e., fatty, scattered density, heterogeneously dense, or extremely dense). In each mammogram examination, a breast is typically imaged with two different views, i.e., the mediolateral oblique (MLO) view and cranial caudal (CC) view. The BI-RADS-based breast density assessment is a qualitative process made by visual observation of both the MLO and CC views by radiologists, where there is a notable inter- and intra-reader variability. In order to maintain consistency and accuracy in BI-RADS-based breast density assessment, gaining understanding on radiologists' reading behaviors will be educational. In this study, we proposed to leverage the newly emerged deep learning approach to investigate how the MLO and CC view images of a mammogram examination may have been clinically used by radiologists in coming up with a BI-RADS density category. We implemented a convolutional neural network (CNN)-based deep learning model, aimed at distinguishing the breast density categories using a large (15,415 images) set of real-world clinical mammogram images. Our results showed that the classification of density categories (in terms of area under the receiver operating characteristic curve) using MLO view images is significantly higher than that using the CC view. This indicates that most likely it is the MLO view that the radiologists have predominately used to determine the breast density BI-RADS categories. Our study holds a potential to further interpret radiologists' reading characteristics, enhance personalized clinical training to radiologists, and ultimately reduce reader variations in breast density assessment.

Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI.

PubMed

Zeng, Ling-Li; Wang, Huaning; Hu, Panpan; Yang, Bo; Pu, Weidan; Shen, Hui; Chen, Xingui; Liu, Zhening; Yin, Hong; Tan, Qingrong; Wang, Kai; Hu, Dewen

2018-04-01

A lack of a sufficiently large sample at single sites causes poor generalizability in automatic diagnosis classification of heterogeneous psychiatric disorders such as schizophrenia based on brain imaging scans. Advanced deep learning methods may be capable of learning subtle hidden patterns from high dimensional imaging data, overcome potential site-related variation, and achieve reproducible cross-site classification. However, deep learning-based cross-site transfer classification, despite less imaging site-specificity and more generalizability of diagnostic models, has not been investigated in schizophrenia. A large multi-site functional MRI sample (n = 734, including 357 schizophrenic patients from seven imaging resources) was collected, and a deep discriminant autoencoder network, aimed at learning imaging site-shared functional connectivity features, was developed to discriminate schizophrenic individuals from healthy controls. Accuracies of approximately 85·0% and 81·0% were obtained in multi-site pooling classification and leave-site-out transfer classification, respectively. The learned functional connectivity features revealed dysregulation of the cortical-striatal-cerebellar circuit in schizophrenia, and the most discriminating functional connections were primarily located within and across the default, salience, and control networks. The findings imply that dysfunctional integration of the cortical-striatal-cerebellar circuit across the default, salience, and control networks may play an important role in the "disconnectivity" model underlying the pathophysiology of schizophrenia. The proposed discriminant deep learning method may be capable of learning reliable connectome patterns and help in understanding the pathophysiology and achieving accurate prediction of schizophrenia across multiple independent imaging sites. Copyright © 2018 German Center for Neurodegenerative Diseases (DZNE). Published by Elsevier B.V. All rights reserved.

The rise of deep learning in drug discovery.

PubMed

Chen, Hongming; Engkvist, Ola; Wang, Yinhai; Olivecrona, Marcus; Blaschke, Thomas

2018-06-01

Over the past decade, deep learning has achieved remarkable success in various artificial intelligence research areas. Evolved from the previous research on artificial neural networks, this technology has shown superior performance to other machine learning algorithms in areas such as image and voice recognition, natural language processing, among others. The first wave of applications of deep learning in pharmaceutical research has emerged in recent years, and its utility has gone beyond bioactivity predictions and has shown promise in addressing diverse problems in drug discovery. Examples will be discussed covering bioactivity prediction, de novo molecular design, synthesis prediction and biological image analysis. Copyright © 2018 The Authors. Published by Elsevier Ltd.. All rights reserved.

Learning approaches as predictors of academic performance in first year health and science students.

PubMed

Salamonson, Yenna; Weaver, Roslyn; Chang, Sungwon; Koch, Jane; Bhathal, Ragbir; Khoo, Cheang; Wilson, Ian

2013-07-01

To compare health and science students' demographic characteristics and learning approaches across different disciplines, and to examine the relationship between learning approaches and academic performance. While there is increasing recognition of a need to foster learning approaches that improve the quality of student learning, little is known about students' learning approaches across different disciplines, and their relationships with academic performance. Prospective, correlational design. Using a survey design, a total of 919 first year health and science students studying in a university located in the western region of Sydney from the following disciplines were recruited to participate in the study - i) Nursing: n = 476, ii) Engineering: n = 75, iii) Medicine: n = 77, iv) Health Sciences: n = 204, and v) Medicinal Chemistry: n = 87. Although there was no statistically significant difference in the use of surface learning among the five discipline groups, there were wide variations in the use of deep learning approach. Furthermore, older students and those with English as an additional language were more likely to use deep learning approach. Controlling for hours spent in paid work during term-time and English language usage, both surface learning approach (β = -0.13, p = 0.001) and deep learning approach (β = 0.11, p = 0.009) emerged as independent and significant predictors of academic performance. Findings from this study provide further empirical evidence that underscore the importance for faculty to use teaching methods that foster deep instead of surface learning approaches, to improve the quality of student learning and academic performance. Copyright © 2013 Elsevier Ltd. All rights reserved.

Deep transfer learning for automatic target classification: MWIR to LWIR

NASA Astrophysics Data System (ADS)

Ding, Zhengming; Nasrabadi, Nasser; Fu, Yun

2016-05-01

Publisher's Note: This paper, originally published on 5/12/2016, was replaced with a corrected/revised version on 5/18/2016. If you downloaded the original PDF but are unable to access the revision, please contact SPIE Digital Library Customer Service for assistance. When dealing with sparse or no labeled data in the target domain, transfer learning shows its appealing performance by borrowing the supervised knowledge from external domains. Recently deep structure learning has been exploited in transfer learning due to its attractive power in extracting effective knowledge through multi-layer strategy, so that deep transfer learning is promising to address the cross-domain mismatch. In general, cross-domain disparity can be resulted from the difference between source and target distributions or different modalities, e.g., Midwave IR (MWIR) and Longwave IR (LWIR). In this paper, we propose a Weighted Deep Transfer Learning framework for automatic target classification through a task-driven fashion. Specifically, deep features and classifier parameters are obtained simultaneously for optimal classification performance. In this way, the proposed deep structures can extract more effective features with the guidance of the classifier performance; on the other hand, the classifier performance is further improved since it is optimized on more discriminative features. Furthermore, we build a weighted scheme to couple source and target output by assigning pseudo labels to target data, therefore we can transfer knowledge from source (i.e., MWIR) to target (i.e., LWIR). Experimental results on real databases demonstrate the superiority of the proposed algorithm by comparing with others.

Deep convolutional neural networks for automatic classification of gastric carcinoma using whole slide images in digital histopathology.

PubMed

Sharma, Harshita; Zerbe, Norman; Klempert, Iris; Hellwich, Olaf; Hufnagl, Peter

2017-11-01

Deep learning using convolutional neural networks is an actively emerging field in histological image analysis. This study explores deep learning methods for computer-aided classification in H&E stained histopathological whole slide images of gastric carcinoma. An introductory convolutional neural network architecture is proposed for two computerized applications, namely, cancer classification based on immunohistochemical response and necrosis detection based on the existence of tumor necrosis in the tissue. Classification performance of the developed deep learning approach is quantitatively compared with traditional image analysis methods in digital histopathology requiring prior computation of handcrafted features, such as statistical measures using gray level co-occurrence matrix, Gabor filter-bank responses, LBP histograms, gray histograms, HSV histograms and RGB histograms, followed by random forest machine learning. Additionally, the widely known AlexNet deep convolutional framework is comparatively analyzed for the corresponding classification problems. The proposed convolutional neural network architecture reports favorable results, with an overall classification accuracy of 0.6990 for cancer classification and 0.8144 for necrosis detection. Copyright © 2017 Elsevier Ltd. All rights reserved.

Deep learning for studies of galaxy morphology

NASA Astrophysics Data System (ADS)

Tuccillo, D.; Huertas-Company, M.; Decencière, E.; Velasco-Forero, S.

2017-06-01

Establishing accurate morphological measurements of galaxies in a reasonable amount of time for future big-data surveys such as EUCLID, the Large Synoptic Survey Telescope or the Wide Field Infrared Survey Telescope is a challenge. Because of its high level of abstraction with little human intervention, deep learning appears to be a promising approach. Deep learning is a rapidly growing discipline that models high-level patterns in data as complex multilayered networks. In this work we test the ability of deep convolutional networks to provide parametric properties of Hubble Space Telescope like galaxies (half-light radii, Sérsic indices, total flux etc..). We simulate a set of galaxies including point spread function and realistic noise from the CANDELS survey and try to recover the main galaxy parameters using deep-learning. We compare the results with the ones obtained with the commonly used profile fitting based software GALFIT. This way showing that with our method we obtain results at least equally good as the ones obtained with GALFIT but, once trained, with a factor 5 hundred time faster.

Nonlinear Deep Kernel Learning for Image Annotation.

PubMed

Jiu, Mingyuan; Sahbi, Hichem

2017-02-08

Multiple kernel learning (MKL) is a widely used technique for kernel design. Its principle consists in learning, for a given support vector classifier, the most suitable convex (or sparse) linear combination of standard elementary kernels. However, these combinations are shallow and often powerless to capture the actual similarity between highly semantic data, especially for challenging classification tasks such as image annotation. In this paper, we redefine multiple kernels using deep multi-layer networks. In this new contribution, a deep multiple kernel is recursively defined as a multi-layered combination of nonlinear activation functions, each one involves a combination of several elementary or intermediate kernels, and results into a positive semi-definite deep kernel. We propose four different frameworks in order to learn the weights of these networks: supervised, unsupervised, kernel-based semisupervised and Laplacian-based semi-supervised. When plugged into support vector machines (SVMs), the resulting deep kernel networks show clear gain, compared to several shallow kernels for the task of image annotation. Extensive experiments and analysis on the challenging ImageCLEF photo annotation benchmark, the COREL5k database and the Banana dataset validate the effectiveness of the proposed method.

A visual tracking method based on deep learning without online model updating

NASA Astrophysics Data System (ADS)

Tang, Cong; Wang, Yicheng; Feng, Yunsong; Zheng, Chao; Jin, Wei

2018-02-01

The paper proposes a visual tracking method based on deep learning without online model updating. In consideration of the advantages of deep learning in feature representation, deep model SSD (Single Shot Multibox Detector) is used as the object extractor in the tracking model. Simultaneously, the color histogram feature and HOG (Histogram of Oriented Gradient) feature are combined to select the tracking object. In the process of tracking, multi-scale object searching map is built to improve the detection performance of deep detection model and the tracking efficiency. In the experiment of eight respective tracking video sequences in the baseline dataset, compared with six state-of-the-art methods, the method in the paper has better robustness in the tracking challenging factors, such as deformation, scale variation, rotation variation, illumination variation, and background clutters, moreover, its general performance is better than other six tracking methods.

Automated Whole-Body Bone Lesion Detection for Multiple Myeloma on 68Ga-Pentixafor PET/CT Imaging Using Deep Learning Methods.

PubMed

Xu, Lina; Tetteh, Giles; Lipkova, Jana; Zhao, Yu; Li, Hongwei; Christ, Patrick; Piraud, Marie; Buck, Andreas; Shi, Kuangyu; Menze, Bjoern H

2018-01-01

The identification of bone lesions is crucial in the diagnostic assessment of multiple myeloma (MM). 68 Ga-Pentixafor PET/CT can capture the abnormal molecular expression of CXCR-4 in addition to anatomical changes. However, whole-body detection of dozens of lesions on hybrid imaging is tedious and error prone. It is even more difficult to identify lesions with a large heterogeneity. This study employed deep learning methods to automatically combine characteristics of PET and CT for whole-body MM bone lesion detection in a 3D manner. Two convolutional neural networks (CNNs), V-Net and W-Net, were adopted to segment and detect the lesions. The feasibility of deep learning for lesion detection on 68 Ga-Pentixafor PET/CT was first verified on digital phantoms generated using realistic PET simulation methods. Then the proposed methods were evaluated on real 68 Ga-Pentixafor PET/CT scans of MM patients. The preliminary results showed that deep learning method can leverage multimodal information for spatial feature representation, and W-Net obtained the best result for segmentation and lesion detection. It also outperformed traditional machine learning methods such as random forest classifier (RF), k -Nearest Neighbors ( k -NN), and support vector machine (SVM). The proof-of-concept study encourages further development of deep learning approach for MM lesion detection in population study.

Automated Whole-Body Bone Lesion Detection for Multiple Myeloma on 68Ga-Pentixafor PET/CT Imaging Using Deep Learning Methods

PubMed Central

Tetteh, Giles; Lipkova, Jana; Zhao, Yu; Li, Hongwei; Christ, Patrick; Buck, Andreas; Menze, Bjoern H.

2018-01-01

The identification of bone lesions is crucial in the diagnostic assessment of multiple myeloma (MM). 68Ga-Pentixafor PET/CT can capture the abnormal molecular expression of CXCR-4 in addition to anatomical changes. However, whole-body detection of dozens of lesions on hybrid imaging is tedious and error prone. It is even more difficult to identify lesions with a large heterogeneity. This study employed deep learning methods to automatically combine characteristics of PET and CT for whole-body MM bone lesion detection in a 3D manner. Two convolutional neural networks (CNNs), V-Net and W-Net, were adopted to segment and detect the lesions. The feasibility of deep learning for lesion detection on 68Ga-Pentixafor PET/CT was first verified on digital phantoms generated using realistic PET simulation methods. Then the proposed methods were evaluated on real 68Ga-Pentixafor PET/CT scans of MM patients. The preliminary results showed that deep learning method can leverage multimodal information for spatial feature representation, and W-Net obtained the best result for segmentation and lesion detection. It also outperformed traditional machine learning methods such as random forest classifier (RF), k-Nearest Neighbors (k-NN), and support vector machine (SVM). The proof-of-concept study encourages further development of deep learning approach for MM lesion detection in population study. PMID:29531504

Getting the Most Out of Dual-Listed Courses: Involving Undergraduate Students in Discussion Through Active Learning Techniques

NASA Astrophysics Data System (ADS)

Tasich, C. M.; Duncan, L. L.; Duncan, B. R.; Burkhardt, B. L.; Benneyworth, L. M.

2015-12-01

Dual-listed courses will persist in higher education because of resource limitations. The pedagogical differences between undergraduate and graduate STEM student groups and the underlying distinction in intellectual development levels between the two student groups complicate the inclusion of undergraduates in these courses. Active learning techniques are a possible remedy to the hardships undergraduate students experience in graduate-level courses. Through an analysis of both undergraduate and graduate student experiences while enrolled in a dual-listed course, we implemented a variety of learning techniques used to complement the learning of both student groups and enhance deep discussion. Here, we provide details concerning the implementation of four active learning techniques - role play, game, debate, and small group - that were used to help undergraduate students critically discuss primary literature. Student perceptions were gauged through an anonymous, end-of-course evaluation that contained basic questions comparing the course to other courses at the university and other salient aspects of the course. These were given as a Likert scale on which students rated a variety of statements (1 = strongly disagree, 3 = no opinion, and 5 = strongly agree). Undergraduates found active learning techniques to be preferable to traditional techniques with small-group discussions being rated the highest in both enjoyment and enhanced learning. The graduate student discussion leaders also found active learning techniques to improve discussion. In hindsight, students of all cultures may be better able to take advantage of such approaches and to critically read and discuss primary literature when written assignments are used to guide their reading. Applications of active learning techniques can not only address the gap between differing levels of students, but also serve as a complement to student engagement in any science course design.

Computer-aided assessment of breast density: comparison of supervised deep learning and feature-based statistical learning.

PubMed

Li, Songfeng; Wei, Jun; Chan, Heang-Ping; Helvie, Mark A; Roubidoux, Marilyn A; Lu, Yao; Zhou, Chuan; Hadjiiski, Lubomir M; Samala, Ravi K

2018-01-09

Breast density is one of the most significant factors that is associated with cancer risk. In this study, our purpose was to develop a supervised deep learning approach for automated estimation of percentage density (PD) on digital mammograms (DMs). The input 'for processing' DMs was first log-transformed, enhanced by a multi-resolution preprocessing scheme, and subsampled to a pixel size of 800 µm  ×  800 µm from 100 µm  ×  100 µm. A deep convolutional neural network (DCNN) was trained to estimate a probability map of breast density (PMD) by using a domain adaptation resampling method. The PD was estimated as the ratio of the dense area to the breast area based on the PMD. The DCNN approach was compared to a feature-based statistical learning approach. Gray level, texture and morphological features were extracted and a least absolute shrinkage and selection operator was used to combine the features into a feature-based PMD. With approval of the Institutional Review Board, we retrospectively collected a training set of 478 DMs and an independent test set of 183 DMs from patient files in our institution. Two experienced mammography quality standards act radiologists interactively segmented PD as the reference standard. Ten-fold cross-validation was used for model selection and evaluation with the training set. With cross-validation, DCNN obtained a Dice's coefficient (DC) of 0.79  ±  0.13 and Pearson's correlation (r) of 0.97, whereas feature-based learning obtained DC  =  0.72  ±  0.18 and r  =  0.85. For the independent test set, DCNN achieved DC  =  0.76  ±  0.09 and r  =  0.94, while feature-based learning achieved DC  =  0.62  ±  0.21 and r  =  0.75. Our DCNN approach was significantly better and more robust than the feature-based learning approach for automated PD estimation on DMs, demonstrating its potential use for automated density reporting as well as for model-based risk prediction.

Computer-aided assessment of breast density: comparison of supervised deep learning and feature-based statistical learning

NASA Astrophysics Data System (ADS)

Li, Songfeng; Wei, Jun; Chan, Heang-Ping; Helvie, Mark A.; Roubidoux, Marilyn A.; Lu, Yao; Zhou, Chuan; Hadjiiski, Lubomir M.; Samala, Ravi K.

2018-01-01

Breast density is one of the most significant factors that is associated with cancer risk. In this study, our purpose was to develop a supervised deep learning approach for automated estimation of percentage density (PD) on digital mammograms (DMs). The input ‘for processing’ DMs was first log-transformed, enhanced by a multi-resolution preprocessing scheme, and subsampled to a pixel size of 800 µm  ×  800 µm from 100 µm  ×  100 µm. A deep convolutional neural network (DCNN) was trained to estimate a probability map of breast density (PMD) by using a domain adaptation resampling method. The PD was estimated as the ratio of the dense area to the breast area based on the PMD. The DCNN approach was compared to a feature-based statistical learning approach. Gray level, texture and morphological features were extracted and a least absolute shrinkage and selection operator was used to combine the features into a feature-based PMD. With approval of the Institutional Review Board, we retrospectively collected a training set of 478 DMs and an independent test set of 183 DMs from patient files in our institution. Two experienced mammography quality standards act radiologists interactively segmented PD as the reference standard. Ten-fold cross-validation was used for model selection and evaluation with the training set. With cross-validation, DCNN obtained a Dice’s coefficient (DC) of 0.79  ±  0.13 and Pearson’s correlation (r) of 0.97, whereas feature-based learning obtained DC  =  0.72  ±  0.18 and r  =  0.85. For the independent test set, DCNN achieved DC  =  0.76  ±  0.09 and r  =  0.94, while feature-based learning achieved DC  =  0.62  ±  0.21 and r  =  0.75. Our DCNN approach was significantly better and more robust than the feature-based learning approach for automated PD estimation on DMs, demonstrating its potential use for automated density reporting as well as for model-based risk prediction.

Digging deeper on "deep" learning: A computational ecology approach.

PubMed

Buscema, Massimo; Sacco, Pier Luigi

2017-01-01

We propose an alternative approach to "deep" learning that is based on computational ecologies of structurally diverse artificial neural networks, and on dynamic associative memory responses to stimuli. Rather than focusing on massive computation of many different examples of a single situation, we opt for model-based learning and adaptive flexibility. Cross-fertilization of learning processes across multiple domains is the fundamental feature of human intelligence that must inform "new" artificial intelligence.

ML-o-Scope: A Diagnostic Visualization System for Deep Machine Learning Pipelines

DTIC Science & Technology

2014-05-16

ML-o-scope: a diagnostic visualization system for deep machine learning pipelines Daniel Bruckner Electrical Engineering and Computer Sciences... machine learning pipelines 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) 5d. PROJECT NUMBER 5e. TASK NUMBER 5f...the system as a support for tuning large scale object-classification pipelines. 1 Introduction A new generation of pipelined machine learning models

Multiagent cooperation and competition with deep reinforcement learning.

PubMed

Tampuu, Ardi; Matiisen, Tambet; Kodelja, Dorian; Kuzovkin, Ilya; Korjus, Kristjan; Aru, Juhan; Aru, Jaan; Vicente, Raul

2017-01-01

Evolution of cooperation and competition can appear when multiple adaptive agents share a biological, social, or technological niche. In the present work we study how cooperation and competition emerge between autonomous agents that learn by reinforcement while using only their raw visual input as the state representation. In particular, we extend the Deep Q-Learning framework to multiagent environments to investigate the interaction between two learning agents in the well-known video game Pong. By manipulating the classical rewarding scheme of Pong we show how competitive and collaborative behaviors emerge. We also describe the progression from competitive to collaborative behavior when the incentive to cooperate is increased. Finally we show how learning by playing against another adaptive agent, instead of against a hard-wired algorithm, results in more robust strategies. The present work shows that Deep Q-Networks can become a useful tool for studying decentralized learning of multiagent systems coping with high-dimensional environments.

Multiagent cooperation and competition with deep reinforcement learning

PubMed Central

Kodelja, Dorian; Kuzovkin, Ilya; Korjus, Kristjan; Aru, Juhan; Aru, Jaan; Vicente, Raul

2017-01-01

Evolution of cooperation and competition can appear when multiple adaptive agents share a biological, social, or technological niche. In the present work we study how cooperation and competition emerge between autonomous agents that learn by reinforcement while using only their raw visual input as the state representation. In particular, we extend the Deep Q-Learning framework to multiagent environments to investigate the interaction between two learning agents in the well-known video game Pong. By manipulating the classical rewarding scheme of Pong we show how competitive and collaborative behaviors emerge. We also describe the progression from competitive to collaborative behavior when the incentive to cooperate is increased. Finally we show how learning by playing against another adaptive agent, instead of against a hard-wired algorithm, results in more robust strategies. The present work shows that Deep Q-Networks can become a useful tool for studying decentralized learning of multiagent systems coping with high-dimensional environments. PMID:28380078

The Next Era: Deep Learning in Pharmaceutical Research

PubMed Central

Ekins, Sean

2016-01-01

Over the past decade we have witnessed the increasing sophistication of machine learning algorithms applied in daily use from internet searches, voice recognition, social network software to machine vision software in cameras, phones, robots and self-driving cars. Pharmaceutical research has also seen its fair share of machine learning developments. For example, applying such methods to mine the growing datasets that are created in drug discovery not only enables us to learn from the past but to predict a molecule’s properties and behavior in future. The latest machine learning algorithm garnering significant attention is deep learning, which is an artificial neural network with multiple hidden layers. Publications over the last 3 years suggest that this algorithm may have advantages over previous machine learning methods and offer a slight but discernable edge in predictive performance. The time has come for a balanced review of this technique but also to apply machine learning methods such as deep learning across a wider array of endpoints relevant to pharmaceutical research for which the datasets are growing such as physicochemical property prediction, formulation prediction, absorption, distribution, metabolism, excretion and toxicity (ADME/Tox), target prediction and skin permeation, etc. We also show that there are many potential applications of deep learning beyond cheminformatics. It will be important to perform prospective testing (which has been carried out rarely to date) in order to convince skeptics that there will be benefits from investing in this technique. PMID:27599991

DeepSig: deep learning improves signal peptide detection in proteins.

PubMed

Savojardo, Castrense; Martelli, Pier Luigi; Fariselli, Piero; Casadio, Rita

2018-05-15

The identification of signal peptides in protein sequences is an important step toward protein localization and function characterization. Here, we present DeepSig, an improved approach for signal peptide detection and cleavage-site prediction based on deep learning methods. Comparative benchmarks performed on an updated independent dataset of proteins show that DeepSig is the current best performing method, scoring better than other available state-of-the-art approaches on both signal peptide detection and precise cleavage-site identification. DeepSig is available as both standalone program and web server at https://deepsig.biocomp.unibo.it. All datasets used in this study can be obtained from the same website. pierluigi.martelli@unibo.it. Supplementary data are available at Bioinformatics online.

Deep learning on temporal-spectral data for anomaly detection

NASA Astrophysics Data System (ADS)

Ma, King; Leung, Henry; Jalilian, Ehsan; Huang, Daniel

2017-05-01

Detecting anomalies is important for continuous monitoring of sensor systems. One significant challenge is to use sensor data and autonomously detect changes that cause different conditions to occur. Using deep learning methods, we are able to monitor and detect changes as a result of some disturbance in the system. We utilize deep neural networks for sequence analysis of time series. We use a multi-step method for anomaly detection. We train the network to learn spectral and temporal features from the acoustic time series. We test our method using fiber-optic acoustic data from a pipeline.

Clinical evaluation of atlas and deep learning based automatic contouring for lung cancer.

PubMed

Lustberg, Tim; van Soest, Johan; Gooding, Mark; Peressutti, Devis; Aljabar, Paul; van der Stoep, Judith; van Elmpt, Wouter; Dekker, Andre

2018-02-01

Contouring of organs at risk (OARs) is an important but time consuming part of radiotherapy treatment planning. The aim of this study was to investigate whether using institutional created software-generated contouring will save time if used as a starting point for manual OAR contouring for lung cancer patients. Twenty CT scans of stage I-III NSCLC patients were used to compare user adjusted contours after an atlas-based and deep learning contour, against manual delineation. The lungs, esophagus, spinal cord, heart and mediastinum were contoured for this study. The time to perform the manual tasks was recorded. With a median time of 20 min for manual contouring, the total median time saved was 7.8 min when using atlas-based contouring and 10 min for deep learning contouring. Both atlas based and deep learning adjustment times were significantly lower than manual contouring time for all OARs except for the left lung and esophagus of the atlas based contouring. User adjustment of software generated contours is a viable strategy to reduce contouring time of OARs for lung radiotherapy while conforming to local clinical standards. In addition, deep learning contouring shows promising results compared to existing solutions. Copyright © 2017 The Authors. Published by Elsevier B.V. All rights reserved.

LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices.

PubMed

He, Ziyang; Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

2018-04-17

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices.

Comparing deep neural network and other machine learning algorithms for stroke prediction in a large-scale population-based electronic medical claims database.

PubMed

Chen-Ying Hung; Wei-Chen Chen; Po-Tsun Lai; Ching-Heng Lin; Chi-Chun Lee

2017-07-01

Electronic medical claims (EMCs) can be used to accurately predict the occurrence of a variety of diseases, which can contribute to precise medical interventions. While there is a growing interest in the application of machine learning (ML) techniques to address clinical problems, the use of deep-learning in healthcare have just gained attention recently. Deep learning, such as deep neural network (DNN), has achieved impressive results in the areas of speech recognition, computer vision, and natural language processing in recent years. However, deep learning is often difficult to comprehend due to the complexities in its framework. Furthermore, this method has not yet been demonstrated to achieve a better performance comparing to other conventional ML algorithms in disease prediction tasks using EMCs. In this study, we utilize a large population-based EMC database of around 800,000 patients to compare DNN with three other ML approaches for predicting 5-year stroke occurrence. The result shows that DNN and gradient boosting decision tree (GBDT) can result in similarly high prediction accuracies that are better compared to logistic regression (LR) and support vector machine (SVM) approaches. Meanwhile, DNN achieves optimal results by using lesser amounts of patient data when comparing to GBDT method.

LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices

PubMed Central

Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

2018-01-01

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices. PMID:29673171

On the Role of Discipline-Related Self-Concept in Deep and Surface Approaches to Learning among University Students

ERIC Educational Resources Information Center

Platow, Michael J.; Mavor, Kenneth I.; Grace, Diana M.

2013-01-01

The current research examined the role that students' discipline-related self-concepts may play in their deep and surface approaches to learning, their overall learning outcomes, and continued engagement in the discipline itself. Using a cross-lagged panel design of first-year university psychology students, a causal path was observed in which…

Evaluating Primary School Student's Deep Learning Approach to Science Lessons

ERIC Educational Resources Information Center

Ilkörücü Göçmençelebi, Sirin; Özkan, Muhlis; Bayram, Nuran

2012-01-01

This study examines the variables which help direct students to a deep learning approach to science lessons, with the aim of guiding programmers and teachers in primary education. The sample was composed of a total of 164 primary school students. The Learning Approaches to Science Scale developed by Ünal (2005) for Science and Technology lessons…

Deep Knowledge: Learning to Teach Science for Understanding and Equity. Teaching for Social Justice

ERIC Educational Resources Information Center

Larkin, Douglas B.

2013-01-01

"Deep Knowledge" is a book about how people's ideas change as they learn to teach. Using the experiences of six middle and high school student teachers as they learn to teach science in diverse classrooms, Larkin explores how their work changes the way they think about students, society, schools, and science itself. Through engaging case stories,…

The Effect of Peer Feedback for Blogging on College Students' Reflective Learning Processes

ERIC Educational Resources Information Center

Xie, Ying; Ke, Fengfeng; Sharma, Priya

2008-01-01

Reflection is an important prerequisite to making meaning of new information, and to advance from surface to deep learning. Strategies such as journal writing and peer feedback have been found to promote reflection as well as deep thinking and learning. This study used an empirical design to investigate the interaction effects of peer feedback and…

Examining Learning Approaches of Science Student Teachers According to the Class Level and Gender

ERIC Educational Resources Information Center

Tural Dincer, Guner; Akdeniz, Ali Riza

2008-01-01

There are many factors influence the level of students' achievement in education. Studies show that one of these factors is "learning approach of a student". Research findings generally have identified two approaches of learning: deep and surface. When a student uses the deep approach, he/she has an intrinsic interest in subject matter and is…

Using an In-Class Simulation in the First Accounting Class: Moving from Surface to Deep Learning

ERIC Educational Resources Information Center

Phillips, Mary E.; Graeff, Timothy R.

2014-01-01

As students often find the first accounting class to be abstract and difficult to understand, the authors designed an in-class simulation as an intervention to move students toward deep learning and away from surface learning. The simulation consists of buying and selling merchandise and accounting for transactions. The simulation is an effective…

Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: Evidence from whole-brain resting-state functional connectivity patterns of schizophrenia

PubMed Central

Kim, Junghoe; Calhoun, Vince D.; Shim, Eunsoo; Lee, Jong-Hwan

2015-01-01

Functional connectivity (FC) patterns obtained from resting-state functional magnetic resonance imaging data are commonly employed to study neuropsychiatric conditions by using pattern classifiers such as the support vector machine (SVM). Meanwhile, a deep neural network (DNN) with multiple hidden layers has shown its ability to systematically extract lower-to-higher level information of image and speech data from lower-to-higher hidden layers, markedly enhancing classification accuracy. The objective of this study was to adopt the DNN for whole-brain resting-state FC pattern classification of schizophrenia (SZ) patients vs. healthy controls (HCs) and identification of aberrant FC patterns associated with SZ. We hypothesized that the lower-to-higher level features learned via the DNN would significantly enhance the classification accuracy, and proposed an adaptive learning algorithm to explicitly control the weight sparsity in each hidden layer via L1-norm regularization. Furthermore, the weights were initialized via stacked autoencoder based pre-training to further improve the classification performance. Classification accuracy was systematically evaluated as a function of (1) the number of hidden layers/nodes, (2) the use of L1-norm regularization, (3) the use of the pre-training, (4) the use of framewise displacement (FD) removal, and (5) the use of anatomical/functional parcellation. Using FC patterns from anatomically parcellated regions without FD removal, an error rate of 14.2% was achieved by employing three hidden layers and 50 hidden nodes with both L1-norm regularization and pre-training, which was substantially lower than the error rate from the SVM (22.3%). Moreover, the trained DNN weights (i.e., the learned features) were found to represent the hierarchical organization of aberrant FC patterns in SZ compared with HC. Specifically, pairs of nodes extracted from the lower hidden layer represented sparse FC patterns implicated in SZ, which was quantified by using kurtosis/modularity measures and features from the higher hidden layer showed holistic/global FC patterns differentiating SZ from HC. Our proposed schemes and reported findings attained by using the DNN classifier and whole-brain FC data suggest that such approaches show improved ability to learn hidden patterns in brain imaging data, which may be useful for developing diagnostic tools for SZ and other neuropsychiatric disorders and identifying associated aberrant FC patterns. PMID:25987366

Learning representations for the early detection of sepsis with deep neural networks.

PubMed

Kam, Hye Jin; Kim, Ha Young

2017-10-01

Sepsis is one of the leading causes of death in intensive care unit patients. Early detection of sepsis is vital because mortality increases as the sepsis stage worsens. This study aimed to develop detection models for the early stage of sepsis using deep learning methodologies, and to compare the feasibility and performance of the new deep learning methodology with those of the regression method with conventional temporal feature extraction. Study group selection adhered to the InSight model. The results of the deep learning-based models and the InSight model were compared. With deep feedforward networks, the area under the ROC curve (AUC) of the models were 0.887 and 0.915 for the InSight and the new feature sets, respectively. For the model with the combined feature set, the AUC was the same as that of the basic feature set (0.915). For the long short-term memory model, only the basic feature set was applied and the AUC improved to 0.929 compared with the existing 0.887 of the InSight model. The contributions of this paper can be summarized in three ways: (i) improved performance without feature extraction using domain knowledge, (ii) verification of feature extraction capability of deep neural networks through comparison with reference features, and (iii) improved performance with feedforward neural networks using long short-term memory, a neural network architecture that can learn sequential patterns. Copyright © 2017 Elsevier Ltd. All rights reserved.

Surface and deep structures in graphics comprehension.

PubMed

Schnotz, Wolfgang; Baadte, Christiane

2015-05-01

Comprehension of graphics can be considered as a process of schema-mediated structure mapping from external graphics on internal mental models. Two experiments were conducted to test the hypothesis that graphics possess a perceptible surface structure as well as a semantic deep structure both of which affect mental model construction. The same content was presented to different groups of learners by graphics from different perspectives with different surface structures but the same deep structure. Deep structures were complementary: major features of the learning content in one experiment became minor features in the other experiment, and vice versa. Text was held constant. Participants were asked to read, understand, and memorize the learning material. Furthermore, they were either instructed to process the material from the perspective supported by the graphic or from an alternative perspective, or they received no further instruction. After learning, they were asked to recall the learning content from different perspectives by completing graphs of different formats as accurately as possible. Learners' recall was more accurate if the format of recall was the same as the learning format which indicates surface structure influences. However, participants also showed more accurate recall when they remembered the content from a perspective emphasizing the deep structure, regardless of the graphics format presented before. This included better recall of what they had not seen than of what they really had seen before. That is, deep structure effects overrode surface effects. Depending on context conditions, stimulation of additional cognitive processing by instruction had partially positive and partially negative effects.

Automatical and accurate segmentation of cerebral tissues in fMRI dataset with combination of image processing and deep learning

NASA Astrophysics Data System (ADS)

Kong, Zhenglun; Luo, Junyi; Xu, Shengpu; Li, Ting

2018-02-01

Image segmentation plays an important role in medical science. One application is multimodality imaging, especially the fusion of structural imaging with functional imaging, which includes CT, MRI and new types of imaging technology such as optical imaging to obtain functional images. The fusion process require precisely extracted structural information, in order to register the image to it. Here we used image enhancement, morphometry methods to extract the accurate contours of different tissues such as skull, cerebrospinal fluid (CSF), grey matter (GM) and white matter (WM) on 5 fMRI head image datasets. Then we utilized convolutional neural network to realize automatic segmentation of images in deep learning way. Such approach greatly reduced the processing time compared to manual and semi-automatic segmentation and is of great importance in improving speed and accuracy as more and more samples being learned. The contours of the borders of different tissues on all images were accurately extracted and 3D visualized. This can be used in low-level light therapy and optical simulation software such as MCVM. We obtained a precise three-dimensional distribution of brain, which offered doctors and researchers quantitative volume data and detailed morphological characterization for personal precise medicine of Cerebral atrophy/expansion. We hope this technique can bring convenience to visualization medical and personalized medicine.

Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis.

PubMed

Suk, Heung-Il; Lee, Seong-Whan; Shen, Dinggang

2014-11-01

For the last decade, it has been shown that neuroimaging can be a potential tool for the diagnosis of Alzheimer's Disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI), and also fusion of different modalities can further provide the complementary information to enhance diagnostic accuracy. Here, we focus on the problems of both feature representation and fusion of multimodal information from Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET). To our best knowledge, the previous methods in the literature mostly used hand-crafted features such as cortical thickness, gray matter densities from MRI, or voxel intensities from PET, and then combined these multimodal features by simply concatenating into a long vector or transforming into a higher-dimensional kernel space. In this paper, we propose a novel method for a high-level latent and shared feature representation from neuroimaging modalities via deep learning. Specifically, we use Deep Boltzmann Machine (DBM)(2), a deep network with a restricted Boltzmann machine as a building block, to find a latent hierarchical feature representation from a 3D patch, and then devise a systematic method for a joint feature representation from the paired patches of MRI and PET with a multimodal DBM. To validate the effectiveness of the proposed method, we performed experiments on ADNI dataset and compared with the state-of-the-art methods. In three binary classification problems of AD vs. healthy Normal Control (NC), MCI vs. NC, and MCI converter vs. MCI non-converter, we obtained the maximal accuracies of 95.35%, 85.67%, and 74.58%, respectively, outperforming the competing methods. By visual inspection of the trained model, we observed that the proposed method could hierarchically discover the complex latent patterns inherent in both MRI and PET. Copyright © 2014 Elsevier Inc. All rights reserved.

Hierarchical Feature Representation and Multimodal Fusion with Deep Learning for AD/MCI Diagnosis

PubMed Central

Suk, Heung-Il; Lee, Seong-Whan; Shen, Dinggang

2014-01-01

For the last decade, it has been shown that neuroimaging can be a potential tool for the diagnosis of Alzheimer’s Disease (AD) and its prodromal stage, Mild Cognitive Impairment (MCI), and also fusion of different modalities can further provide the complementary information to enhance diagnostic accuracy. Here, we focus on the problems of both feature representation and fusion of multimodal information from Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET). To our best knowledge, the previous methods in the literature mostly used hand-crafted features such as cortical thickness, gray matter densities from MRI, or voxel intensities from PET, and then combined these multimodal features by simply concatenating into a long vector or transforming into a higher-dimensional kernel space. In this paper, we propose a novel method for a high-level latent and shared feature representation from neuroimaging modalities via deep learning. Specifically, we use Deep Boltzmann Machine (DBM)1, a deep network with a restricted Boltzmann machine as a building block, to find a latent hierarchical feature representation from a 3D patch, and then devise a systematic method for a joint feature representation from the paired patches of MRI and PET with a multimodal DBM. To validate the effectiveness of the proposed method, we performed experiments on ADNI dataset and compared with the state-of-the-art methods. In three binary classification problems of AD vs. healthy Normal Control (NC), MCI vs. NC, and MCI converter vs. MCI non-converter, we obtained the maximal accuracies of 95.35%, 85.67%, and 74.58%, respectively, outperforming the competing methods. By visual inspection of the trained model, we observed that the proposed method could hierarchically discover the complex latent patterns inherent in both MRI and PET. PMID:25042445

Deep Learning for Flow Sculpting: Insights into Efficient Learning using Scientific Simulation Data

PubMed Central

Stoecklein, Daniel; Lore, Kin Gwn; Davies, Michael; Sarkar, Soumik; Ganapathysubramanian, Baskar

2017-01-01

A new technique for shaping microfluid flow, known as flow sculpting, offers an unprecedented level of passive fluid flow control, with potential breakthrough applications in advancing manufacturing, biology, and chemistry research at the microscale. However, efficiently solving the inverse problem of designing a flow sculpting device for a desired fluid flow shape remains a challenge. Current approaches struggle with the many-to-one design space, requiring substantial user interaction and the necessity of building intuition, all of which are time and resource intensive. Deep learning has emerged as an efficient function approximation technique for high-dimensional spaces, and presents a fast solution to the inverse problem, yet the science of its implementation in similarly defined problems remains largely unexplored. We propose that deep learning methods can completely outpace current approaches for scientific inverse problems while delivering comparable designs. To this end, we show how intelligent sampling of the design space inputs can make deep learning methods more competitive in accuracy, while illustrating their generalization capability to out-of-sample predictions. PMID:28402332

A comparative study of deep learning models for medical image classification

NASA Astrophysics Data System (ADS)

Dutta, Suvajit; Manideep, B. C. S.; Rai, Shalva; Vijayarajan, V.

2017-11-01

Deep Learning(DL) techniques are conquering over the prevailing traditional approaches of neural network, when it comes to the huge amount of dataset, applications requiring complex functions demanding increase accuracy with lower time complexities. Neurosciences has already exploited DL techniques, thus portrayed itself as an inspirational source for researchers exploring the domain of Machine learning. DL enthusiasts cover the areas of vision, speech recognition, motion planning and NLP as well, moving back and forth among fields. This concerns with building models that can successfully solve variety of tasks requiring intelligence and distributed representation. The accessibility to faster CPUs, introduction of GPUs-performing complex vector and matrix computations, supported agile connectivity to network. Enhanced software infrastructures for distributed computing worked in strengthening the thought that made researchers suffice DL methodologies. The paper emphases on the following DL procedures to traditional approaches which are performed manually for classifying medical images. The medical images are used for the study Diabetic Retinopathy(DR) and computed tomography (CT) emphysema data. Both DR and CT data diagnosis is difficult task for normal image classification methods. The initial work was carried out with basic image processing along with K-means clustering for identification of image severity levels. After determining image severity levels ANN has been applied on the data to get the basic classification result, then it is compared with the result of DNNs (Deep Neural Networks), which performed efficiently because of its multiple hidden layer features basically which increases accuracy factors, but the problem of vanishing gradient in DNNs made to consider Convolution Neural Networks (CNNs) as well for better results. The CNNs are found to be providing better outcomes when compared to other learning models aimed at classification of images. CNNs are favoured as they provide better visual processing models successfully classifying the noisy data as well. The work centres on the detection on Diabetic Retinopathy-loss in vision and recognition of computed tomography (CT) emphysema data measuring the severity levels for both cases. The paper discovers how various Machine Learning algorithms can be implemented ensuing a supervised approach, so as to get accurate results with less complexity possible.

Relaxation System

NASA Technical Reports Server (NTRS)

1987-01-01

Environ Corporation's relaxation system is built around a body lounge, a kind of super easy chair that incorporates sensory devices. Computer controlled enclosure provides filtered ionized air to create a feeling of invigoration, enhanced by mood changing aromas. Occupant is also surrounded by multidimensional audio and the lighting is programmed to change colors, patterns, and intensity periodically. These and other sensory stimulators are designed to provide an environment in which the learning process is stimulated, because research has proven that while an individual is in a deep state of relaxation, the mind is more receptive to new information.

A Pilot Study of Biomedical Text Comprehension using an Attention-Based Deep Neural Reader: Design and Experimental Analysis

PubMed Central

Lee, Kyubum; Kim, Byounggun; Jeon, Minji; Kim, Jihye; Tan, Aik Choon

2018-01-01

Background With the development of artificial intelligence (AI) technology centered on deep-learning, the computer has evolved to a point where it can read a given text and answer a question based on the context of the text. Such a specific task is known as the task of machine comprehension. Existing machine comprehension tasks mostly use datasets of general texts, such as news articles or elementary school-level storybooks. However, no attempt has been made to determine whether an up-to-date deep learning-based machine comprehension model can also process scientific literature containing expert-level knowledge, especially in the biomedical domain. Objective This study aims to investigate whether a machine comprehension model can process biomedical articles as well as general texts. Since there is no dataset for the biomedical literature comprehension task, our work includes generating a large-scale question answering dataset using PubMed and manually evaluating the generated dataset. Methods We present an attention-based deep neural model tailored to the biomedical domain. To further enhance the performance of our model, we used a pretrained word vector and biomedical entity type embedding. We also developed an ensemble method of combining the results of several independent models to reduce the variance of the answers from the models. Results The experimental results showed that our proposed deep neural network model outperformed the baseline model by more than 7% on the new dataset. We also evaluated human performance on the new dataset. The human evaluation result showed that our deep neural model outperformed humans in comprehension by 22% on average. Conclusions In this work, we introduced a new task of machine comprehension in the biomedical domain using a deep neural model. Since there was no large-scale dataset for training deep neural models in the biomedical domain, we created the new cloze-style datasets Biomedical Knowledge Comprehension Title (BMKC_T) and Biomedical Knowledge Comprehension Last Sentence (BMKC_LS) (together referred to as BioMedical Knowledge Comprehension) using the PubMed corpus. The experimental results showed that the performance of our model is much higher than that of humans. We observed that our model performed consistently better regardless of the degree of difficulty of a text, whereas humans have difficulty when performing biomedical literature comprehension tasks that require expert level knowledge. PMID:29305341

A proof-of-principle simulation for closed-loop control based on preexisting experimental thalamic DBS-enhanced instrumental learning.

PubMed

Wang, Ching-Fu; Yang, Shih-Hung; Lin, Sheng-Huang; Chen, Po-Chuan; Lo, Yu-Chun; Pan, Han-Chi; Lai, Hsin-Yi; Liao, Lun-De; Lin, Hui-Ching; Chen, Hsu-Yan; Huang, Wei-Chen; Huang, Wun-Jhu; Chen, You-Yin

Deep brain stimulation (DBS) has been applied as an effective therapy for treating Parkinson's disease or essential tremor. Several open-loop DBS control strategies have been developed for clinical experiments, but they are limited by short battery life and inefficient therapy. Therefore, many closed-loop DBS control systems have been designed to tackle these problems by automatically adjusting the stimulation parameters via feedback from neural signals, which has been reported to reduce the power consumption. However, when the association between the biomarkers of the model and stimulation is unclear, it is difficult to develop an optimal control scheme for other DBS applications, i.e., DBS-enhanced instrumental learning. Furthermore, few studies have investigated the effect of closed-loop DBS control for cognition function, such as instrumental skill learning, and have been implemented in simulation environments. In this paper, we proposed a proof-of-principle design for a closed-loop DBS system, cognitive-enhancing DBS (ceDBS), which enhanced skill learning based on in vivo experimental data. The ceDBS acquired local field potential (LFP) signal from the thalamic central lateral (CL) nuclei of animals through a neural signal processing system. A strong coupling of the theta oscillation (4-7 Hz) and the learning period was found in the water reward-related lever-pressing learning task. Therefore, the theta-band power ratio, which was the averaged theta band to averaged total band (1-55 Hz) power ratio, could be used as a physiological marker for enhancement of instrumental skill learning. The on-line extraction of the theta-band power ratio was implemented on a field-programmable gate array (FPGA). An autoregressive with exogenous inputs (ARX)-based predictor was designed to construct a CL-thalamic DBS model and forecast the future physiological marker according to the past physiological marker and applied DBS. The prediction could further assist the design of a closed-loop DBS controller. A DBS controller based on a fuzzy expert system was devised to automatically control DBS according to the predicted physiological marker via a set of rules. The simulated experimental results demonstrate that the ceDBS based on the closed-loop control architecture not only reduced power consumption using the predictive physiological marker, but also achieved a desired level of physiological marker through the DBS controller. Copyright © 2017 Elsevier Inc. All rights reserved.

Holography as deep learning

NASA Astrophysics Data System (ADS)

Gan, Wen-Cong; Shu, Fu-Wen

Quantum many-body problem with exponentially large degrees of freedom can be reduced to a tractable computational form by neural network method [G. Carleo and M. Troyer, Science 355 (2017) 602, arXiv:1606.02318.] The power of deep neural network (DNN) based on deep learning is clarified by mapping it to renormalization group (RG), which may shed lights on holographic principle by identifying a sequence of RG transformations to the AdS geometry. In this paper, we show that any network which reflects RG process has intrinsic hyperbolic geometry, and discuss the structure of entanglement encoded in the graph of DNN. We find the entanglement structure of DNN is of Ryu-Takayanagi form. Based on these facts, we argue that the emergence of holographic gravitational theory is related to deep learning process of the quantum-field theory.

Fault Diagnosis Based on Chemical Sensor Data with an Active Deep Neural Network

PubMed Central

Jiang, Peng; Hu, Zhixin; Liu, Jun; Yu, Shanen; Wu, Feng

2016-01-01

Big sensor data provide significant potential for chemical fault diagnosis, which involves the baseline values of security, stability and reliability in chemical processes. A deep neural network (DNN) with novel active learning for inducing chemical fault diagnosis is presented in this study. It is a method using large amount of chemical sensor data, which is a combination of deep learning and active learning criterion to target the difficulty of consecutive fault diagnosis. DNN with deep architectures, instead of shallow ones, could be developed through deep learning to learn a suitable feature representation from raw sensor data in an unsupervised manner using stacked denoising auto-encoder (SDAE) and work through a layer-by-layer successive learning process. The features are added to the top Softmax regression layer to construct the discriminative fault characteristics for diagnosis in a supervised manner. Considering the expensive and time consuming labeling of sensor data in chemical applications, in contrast to the available methods, we employ a novel active learning criterion for the particularity of chemical processes, which is a combination of Best vs. Second Best criterion (BvSB) and a Lowest False Positive criterion (LFP), for further fine-tuning of diagnosis model in an active manner rather than passive manner. That is, we allow models to rank the most informative sensor data to be labeled for updating the DNN parameters during the interaction phase. The effectiveness of the proposed method is validated in two well-known industrial datasets. Results indicate that the proposed method can obtain superior diagnosis accuracy and provide significant performance improvement in accuracy and false positive rate with less labeled chemical sensor data by further active learning compared with existing methods. PMID:27754386

Fault Diagnosis Based on Chemical Sensor Data with an Active Deep Neural Network.

PubMed

Jiang, Peng; Hu, Zhixin; Liu, Jun; Yu, Shanen; Wu, Feng

2016-10-13

Big sensor data provide significant potential for chemical fault diagnosis, which involves the baseline values of security, stability and reliability in chemical processes. A deep neural network (DNN) with novel active learning for inducing chemical fault diagnosis is presented in this study. It is a method using large amount of chemical sensor data, which is a combination of deep learning and active learning criterion to target the difficulty of consecutive fault diagnosis. DNN with deep architectures, instead of shallow ones, could be developed through deep learning to learn a suitable feature representation from raw sensor data in an unsupervised manner using stacked denoising auto-encoder (SDAE) and work through a layer-by-layer successive learning process. The features are added to the top Softmax regression layer to construct the discriminative fault characteristics for diagnosis in a supervised manner. Considering the expensive and time consuming labeling of sensor data in chemical applications, in contrast to the available methods, we employ a novel active learning criterion for the particularity of chemical processes, which is a combination of Best vs. Second Best criterion (BvSB) and a Lowest False Positive criterion (LFP), for further fine-tuning of diagnosis model in an active manner rather than passive manner. That is, we allow models to rank the most informative sensor data to be labeled for updating the DNN parameters during the interaction phase. The effectiveness of the proposed method is validated in two well-known industrial datasets. Results indicate that the proposed method can obtain superior diagnosis accuracy and provide significant performance improvement in accuracy and false positive rate with less labeled chemical sensor data by further active learning compared with existing methods.

Resolution of Singularities Introduced by Hierarchical Structure in Deep Neural Networks.

PubMed

Nitta, Tohru

2017-10-01

We present a theoretical analysis of singular points of artificial deep neural networks, resulting in providing deep neural network models having no critical points introduced by a hierarchical structure. It is considered that such deep neural network models have good nature for gradient-based optimization. First, we show that there exist a large number of critical points introduced by a hierarchical structure in deep neural networks as straight lines, depending on the number of hidden layers and the number of hidden neurons. Second, we derive a sufficient condition for deep neural networks having no critical points introduced by a hierarchical structure, which can be applied to general deep neural networks. It is also shown that the existence of critical points introduced by a hierarchical structure is determined by the rank and the regularity of weight matrices for a specific class of deep neural networks. Finally, two kinds of implementation methods of the sufficient conditions to have no critical points are provided. One is a learning algorithm that can avoid critical points introduced by the hierarchical structure during learning (called avoidant learning algorithm). The other is a neural network that does not have some critical points introduced by the hierarchical structure as an inherent property (called avoidant neural network).

Concussion classification via deep learning using whole-brain white matter fiber strains

PubMed Central

Cai, Yunliang; Wu, Shaoju; Zhao, Wei; Li, Zhigang; Wu, Zheyang

2018-01-01

Developing an accurate and reliable injury predictor is central to the biomechanical studies of traumatic brain injury. State-of-the-art efforts continue to rely on empirical, scalar metrics based on kinematics or model-estimated tissue responses explicitly pre-defined in a specific brain region of interest. They could suffer from loss of information. A single training dataset has also been used to evaluate performance but without cross-validation. In this study, we developed a deep learning approach for concussion classification using implicit features of the entire voxel-wise white matter fiber strains. Using reconstructed American National Football League (NFL) injury cases, leave-one-out cross-validation was employed to objectively compare injury prediction performances against two baseline machine learning classifiers (support vector machine (SVM) and random forest (RF)) and four scalar metrics via univariate logistic regression (Brain Injury Criterion (BrIC), cumulative strain damage measure of the whole brain (CSDM-WB) and the corpus callosum (CSDM-CC), and peak fiber strain in the CC). Feature-based machine learning classifiers including deep learning, SVM, and RF consistently outperformed all scalar injury metrics across all performance categories (e.g., leave-one-out accuracy of 0.828–0.862 vs. 0.690–0.776, and .632+ error of 0.148–0.176 vs. 0.207–0.292). Further, deep learning achieved the best cross-validation accuracy, sensitivity, AUC, and .632+ error. These findings demonstrate the superior performances of deep learning in concussion prediction and suggest its promise for future applications in biomechanical investigations of traumatic brain injury. PMID:29795640

Concussion classification via deep learning using whole-brain white matter fiber strains.

PubMed

Cai, Yunliang; Wu, Shaoju; Zhao, Wei; Li, Zhigang; Wu, Zheyang; Ji, Songbai

2018-01-01

Developing an accurate and reliable injury predictor is central to the biomechanical studies of traumatic brain injury. State-of-the-art efforts continue to rely on empirical, scalar metrics based on kinematics or model-estimated tissue responses explicitly pre-defined in a specific brain region of interest. They could suffer from loss of information. A single training dataset has also been used to evaluate performance but without cross-validation. In this study, we developed a deep learning approach for concussion classification using implicit features of the entire voxel-wise white matter fiber strains. Using reconstructed American National Football League (NFL) injury cases, leave-one-out cross-validation was employed to objectively compare injury prediction performances against two baseline machine learning classifiers (support vector machine (SVM) and random forest (RF)) and four scalar metrics via univariate logistic regression (Brain Injury Criterion (BrIC), cumulative strain damage measure of the whole brain (CSDM-WB) and the corpus callosum (CSDM-CC), and peak fiber strain in the CC). Feature-based machine learning classifiers including deep learning, SVM, and RF consistently outperformed all scalar injury metrics across all performance categories (e.g., leave-one-out accuracy of 0.828-0.862 vs. 0.690-0.776, and .632+ error of 0.148-0.176 vs. 0.207-0.292). Further, deep learning achieved the best cross-validation accuracy, sensitivity, AUC, and .632+ error. These findings demonstrate the superior performances of deep learning in concussion prediction and suggest its promise for future applications in biomechanical investigations of traumatic brain injury.

Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks.

PubMed

Yu, Lequan; Chen, Hao; Dou, Qi; Qin, Jing; Heng, Pheng-Ann

2017-04-01

Automated melanoma recognition in dermoscopy images is a very challenging task due to the low contrast of skin lesions, the huge intraclass variation of melanomas, the high degree of visual similarity between melanoma and non-melanoma lesions, and the existence of many artifacts in the image. In order to meet these challenges, we propose a novel method for melanoma recognition by leveraging very deep convolutional neural networks (CNNs). Compared with existing methods employing either low-level hand-crafted features or CNNs with shallower architectures, our substantially deeper networks (more than 50 layers) can acquire richer and more discriminative features for more accurate recognition. To take full advantage of very deep networks, we propose a set of schemes to ensure effective training and learning under limited training data. First, we apply the residual learning to cope with the degradation and overfitting problems when a network goes deeper. This technique can ensure that our networks benefit from the performance gains achieved by increasing network depth. Then, we construct a fully convolutional residual network (FCRN) for accurate skin lesion segmentation, and further enhance its capability by incorporating a multi-scale contextual information integration scheme. Finally, we seamlessly integrate the proposed FCRN (for segmentation) and other very deep residual networks (for classification) to form a two-stage framework. This framework enables the classification network to extract more representative and specific features based on segmented results instead of the whole dermoscopy images, further alleviating the insufficiency of training data. The proposed framework is extensively evaluated on ISBI 2016 Skin Lesion Analysis Towards Melanoma Detection Challenge dataset. Experimental results demonstrate the significant performance gains of the proposed framework, ranking the first in classification and the second in segmentation among 25 teams and 28 teams, respectively. This study corroborates that very deep CNNs with effective training mechanisms can be employed to solve complicated medical image analysis tasks, even with limited training data.

How evolution learns to generalise: Using the principles of learning theory to understand the evolution of developmental organisation.

PubMed

Kouvaris, Kostas; Clune, Jeff; Kounios, Loizos; Brede, Markus; Watson, Richard A

2017-04-01

One of the most intriguing questions in evolution is how organisms exhibit suitable phenotypic variation to rapidly adapt in novel selective environments. Such variability is crucial for evolvability, but poorly understood. In particular, how can natural selection favour developmental organisations that facilitate adaptive evolution in previously unseen environments? Such a capacity suggests foresight that is incompatible with the short-sighted concept of natural selection. A potential resolution is provided by the idea that evolution may discover and exploit information not only about the particular phenotypes selected in the past, but their underlying structural regularities: new phenotypes, with the same underlying regularities, but novel particulars, may then be useful in new environments. If true, we still need to understand the conditions in which natural selection will discover such deep regularities rather than exploiting 'quick fixes' (i.e., fixes that provide adaptive phenotypes in the short term, but limit future evolvability). Here we argue that the ability of evolution to discover such regularities is formally analogous to learning principles, familiar in humans and machines, that enable generalisation from past experience. Conversely, natural selection that fails to enhance evolvability is directly analogous to the learning problem of over-fitting and the subsequent failure to generalise. We support the conclusion that evolving systems and learning systems are different instantiations of the same algorithmic principles by showing that existing results from the learning domain can be transferred to the evolution domain. Specifically, we show that conditions that alleviate over-fitting in learning systems successfully predict which biological conditions (e.g., environmental variation, regularity, noise or a pressure for developmental simplicity) enhance evolvability. This equivalence provides access to a well-developed theoretical framework from learning theory that enables a characterisation of the general conditions for the evolution of evolvability.

Prediction of Bispectral Index during Target-controlled Infusion of Propofol and Remifentanil: A Deep Learning Approach.

PubMed

Lee, Hyung-Chul; Ryu, Ho-Geol; Chung, Eun-Jin; Jung, Chul-Woo

2018-03-01

The discrepancy between predicted effect-site concentration and measured bispectral index is problematic during intravenous anesthesia with target-controlled infusion of propofol and remifentanil. We hypothesized that bispectral index during total intravenous anesthesia would be more accurately predicted by a deep learning approach. Long short-term memory and the feed-forward neural network were sequenced to simulate the pharmacokinetic and pharmacodynamic parts of an empirical model, respectively, to predict intraoperative bispectral index during combined use of propofol and remifentanil. Inputs of long short-term memory were infusion histories of propofol and remifentanil, which were retrieved from target-controlled infusion pumps for 1,800 s at 10-s intervals. Inputs of the feed-forward network were the outputs of long short-term memory and demographic data such as age, sex, weight, and height. The final output of the feed-forward network was the bispectral index. The performance of bispectral index prediction was compared between the deep learning model and previously reported response surface model. The model hyperparameters comprised 8 memory cells in the long short-term memory layer and 16 nodes in the hidden layer of the feed-forward network. The model training and testing were performed with separate data sets of 131 and 100 cases. The concordance correlation coefficient (95% CI) were 0.561 (0.560 to 0.562) in the deep learning model, which was significantly larger than that in the response surface model (0.265 [0.263 to 0.266], P < 0.001). The deep learning model-predicted bispectral index during target-controlled infusion of propofol and remifentanil more accurately compared to the traditional model. The deep learning approach in anesthetic pharmacology seems promising because of its excellent performance and extensibility.

Automated detection of exudative age-related macular degeneration in spectral domain optical coherence tomography using deep learning.

PubMed

Treder, Maximilian; Lauermann, Jost Lennart; Eter, Nicole

2018-02-01

Our purpose was to use deep learning for the automated detection of age-related macular degeneration (AMD) in spectral domain optical coherence tomography (SD-OCT). A total of 1112 cross-section SD-OCT images of patients with exudative AMD and a healthy control group were used for this study. In the first step, an open-source multi-layer deep convolutional neural network (DCNN), which was pretrained with 1.2 million images from ImageNet, was trained and validated with 1012 cross-section SD-OCT scans (AMD: 701; healthy: 311). During this procedure training accuracy, validation accuracy and cross-entropy were computed. The open-source deep learning framework TensorFlow™ (Google Inc., Mountain View, CA, USA) was used to accelerate the deep learning process. In the last step, a created DCNN classifier, using the information of the above mentioned deep learning process, was tested in detecting 100 untrained cross-section SD-OCT images (AMD: 50; healthy: 50). Therefore, an AMD testing score was computed: 0.98 or higher was presumed for AMD. After an iteration of 500 training steps, the training accuracy and validation accuracies were 100%, and the cross-entropy was 0.005. The average AMD scores were 0.997 ± 0.003 in the AMD testing group and 0.9203 ± 0.085 in the healthy comparison group. The difference between the two groups was highly significant (p < 0.001). With a deep learning-based approach using TensorFlow™, it is possible to detect AMD in SD-OCT with high sensitivity and specificity. With more image data, an expansion of this classifier for other macular diseases or further details in AMD is possible, suggesting an application for this model as a support in clinical decisions. Another possible future application would involve the individual prediction of the progress and success of therapy for different diseases by automatically detecting hidden image information.

Deep SOMs for automated feature extraction and classification from big data streaming

NASA Astrophysics Data System (ADS)

Sakkari, Mohamed; Ejbali, Ridha; Zaied, Mourad

2017-03-01

In this paper, we proposed a deep self-organizing map model (Deep-SOMs) for automated features extracting and learning from big data streaming which we benefit from the framework Spark for real time streams and highly parallel data processing. The SOMs deep architecture is based on the notion of abstraction (patterns automatically extract from the raw data, from the less to more abstract). The proposed model consists of three hidden self-organizing layers, an input and an output layer. Each layer is made up of a multitude of SOMs, each map only focusing at local headmistress sub-region from the input image. Then, each layer trains the local information to generate more overall information in the higher layer. The proposed Deep-SOMs model is unique in terms of the layers architecture, the SOMs sampling method and learning. During the learning stage we use a set of unsupervised SOMs for feature extraction. We validate the effectiveness of our approach on large data sets such as Leukemia dataset and SRBCT. Results of comparison have shown that the Deep-SOMs model performs better than many existing algorithms for images classification.

DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection.

PubMed

Ouyang, Wanli; Zeng, Xingyu; Wang, Xiaogang; Qiu, Shi; Luo, Ping; Tian, Yonglong; Li, Hongsheng; Yang, Shuo; Wang, Zhe; Li, Hongyang; Loy, Chen Change; Wang, Kun; Yan, Junjie; Tang, Xiaoou

2016-07-07

In this paper, we propose deformable deep convolutional neural networks for generic object detection. This new deep learning object detection framework has innovations in multiple aspects. In the proposed new deep architecture, a new deformation constrained pooling (def-pooling) layer models the deformation of object parts with geometric constraint and penalty. A new pre-training strategy is proposed to learn feature representations more suitable for the object detection task and with good generalization capability. By changing the net structures, training strategies, adding and removing some key components in the detection pipeline, a set of models with large diversity are obtained, which significantly improves the effectiveness of model averaging. The proposed approach improves the mean averaged precision obtained by RCNN [16], which was the state-of-the-art, from 31% to 50.3% on the ILSVRC2014 detection test set. It also outperforms the winner of ILSVRC2014, GoogLeNet, by 6.1%. Detailed component-wise analysis is also provided through extensive experimental evaluation, which provides a global view for people to understand the deep learning object detection pipeline.

First-Year Students' Approaches to Learning, and Factors Related to Change or Stability in Their Deep Approach during a Pharmacy Course

ERIC Educational Resources Information Center

Varunki, Maaret; Katajavuori, Nina; Postareff, Liisa

2017-01-01

Research shows that a surface approach to learning is more common among students in the natural sciences, while students representing the "soft" sciences are more likely to apply a deep approach. However, findings conflict concerning the stability of approaches to learning in general. This study explores the variation in students'…

Nonparametric Representations for Integrated Inference, Control, and Sensing

DTIC Science & Technology

2015-10-01

Learning (ICML), 2013. [20] Jeff Donahue, Yangqing Jia, Oriol Vinyals, Judy Hoffman, Ning Zhang, Eric Tzeng, and Trevor Darrell. DeCAF: A deep ...unlimited. Multi-layer feature learning “SuperVision” Convolutional Neural Network (CNN) ImageNet Classification with Deep Convolutional Neural Networks...to develop a new framework for autonomous operations that will extend the state of the art in distributed learning and modeling from data, and

Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics

NASA Astrophysics Data System (ADS)

Wehmeyer, Christoph; Noé, Frank

2018-06-01

Inspired by the success of deep learning techniques in the physical and chemical sciences, we apply a modification of an autoencoder type deep neural network to the task of dimension reduction of molecular dynamics data. We can show that our time-lagged autoencoder reliably finds low-dimensional embeddings for high-dimensional feature spaces which capture the slow dynamics of the underlying stochastic processes—beyond the capabilities of linear dimension reduction techniques.

Deep learning-based features of breast MRI for prediction of occult invasive disease following a diagnosis of ductal carcinoma in situ: preliminary data

NASA Astrophysics Data System (ADS)

Zhu, Zhe; Harowicz, Michael; Zhang, Jun; Saha, Ashirbani; Grimm, Lars J.; Hwang, Shelley; Mazurowski, Maciej A.

2018-02-01

Approximately 25% of patients with ductal carcinoma in situ (DCIS) diagnosed from core needle biopsy are subsequently upstaged to invasive cancer at surgical excision. Identifying patients with occult invasive disease is important as it changes treatment and precludes enrollment in active surveillance for DCIS. In this study, we investigated upstaging of DCIS to invasive disease using deep features. While deep neural networks require large amounts of training data, the available data to predict DCIS upstaging is sparse and thus directly training a neural network is unlikely to be successful. In this work, a pre-trained neural network is used as a feature extractor and a support vector machine (SVM) is trained on the extracted features. We used the dynamic contrast-enhanced (DCE) MRIs of patients at our institution from January 1, 2000, through March 23, 2014 who underwent MRI following a diagnosis of DCIS. Among the 131 DCIS patients, there were 35 patients who were upstaged to invasive cancer. Area under the ROC curve within the 10-fold cross-validation scheme was used for validation of our predictive model. The use of deep features was able to achieve an AUC of 0.68 (95% CI: 0.56-0.78) to predict occult invasive disease. This preliminary work demonstrates the promise of deep features to predict surgical upstaging following a diagnosis of DCIS.

CGBVS-DNN: Prediction of Compound-protein Interactions Based on Deep Learning.

PubMed

Hamanaka, Masatoshi; Taneishi, Kei; Iwata, Hiroaki; Ye, Jun; Pei, Jianguo; Hou, Jinlong; Okuno, Yasushi

2017-01-01

Computational prediction of compound-protein interactions (CPIs) is of great importance for drug design as the first step in in-silico screening. We previously proposed chemical genomics-based virtual screening (CGBVS), which predicts CPIs by using a support vector machine (SVM). However, the CGBVS has problems when training using more than a million datasets of CPIs since SVMs require an exponential increase in the calculation time and computer memory. To solve this problem, we propose the CGBVS-DNN, in which we use deep neural networks, a kind of deep learning technique, instead of the SVM. Deep learning does not require learning all input data at once because the network can be trained with small mini-batches. Experimental results show that the CGBVS-DNN outperformed the original CGBVS with a quarter million CPIs. Results of cross-validation show that the accuracy of the CGBVS-DNN reaches up to 98.2 % (σ<0.01) with 4 million CPIs. © 2017 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.

Relevance of deep learning to facilitate the diagnosis of HER2 status in breast cancer

NASA Astrophysics Data System (ADS)

Vandenberghe, Michel E.; Scott, Marietta L. J.; Scorer, Paul W.; Söderberg, Magnus; Balcerzak, Denis; Barker, Craig

2017-04-01

Tissue biomarker scoring by pathologists is central to defining the appropriate therapy for patients with cancer. Yet, inter-pathologist variability in the interpretation of ambiguous cases can affect diagnostic accuracy. Modern artificial intelligence methods such as deep learning have the potential to supplement pathologist expertise to ensure constant diagnostic accuracy. We developed a computational approach based on deep learning that automatically scores HER2, a biomarker that defines patient eligibility for anti-HER2 targeted therapies in breast cancer. In a cohort of 71 breast tumour resection samples, automated scoring showed a concordance of 83% with a pathologist. The twelve discordant cases were then independently reviewed, leading to a modification of diagnosis from initial pathologist assessment for eight cases. Diagnostic discordance was found to be largely caused by perceptual differences in assessing HER2 expression due to high HER2 staining heterogeneity. This study provides evidence that deep learning aided diagnosis can facilitate clinical decision making in breast cancer by identifying cases at high risk of misdiagnosis.

Computer-aided classification of lung nodules on computed tomography images via deep learning technique

PubMed Central

Hua, Kai-Lung; Hsu, Che-Hao; Hidayati, Shintami Chusnul; Cheng, Wen-Huang; Chen, Yu-Jen

2015-01-01

Lung cancer has a poor prognosis when not diagnosed early and unresectable lesions are present. The management of small lung nodules noted on computed tomography scan is controversial due to uncertain tumor characteristics. A conventional computer-aided diagnosis (CAD) scheme requires several image processing and pattern recognition steps to accomplish a quantitative tumor differentiation result. In such an ad hoc image analysis pipeline, every step depends heavily on the performance of the previous step. Accordingly, tuning of classification performance in a conventional CAD scheme is very complicated and arduous. Deep learning techniques, on the other hand, have the intrinsic advantage of an automatic exploitation feature and tuning of performance in a seamless fashion. In this study, we attempted to simplify the image analysis pipeline of conventional CAD with deep learning techniques. Specifically, we introduced models of a deep belief network and a convolutional neural network in the context of nodule classification in computed tomography images. Two baseline methods with feature computing steps were implemented for comparison. The experimental results suggest that deep learning methods could achieve better discriminative results and hold promise in the CAD application domain. PMID:26346558

Computer-aided classification of lung nodules on computed tomography images via deep learning technique.

PubMed

Hua, Kai-Lung; Hsu, Che-Hao; Hidayati, Shintami Chusnul; Cheng, Wen-Huang; Chen, Yu-Jen

2015-01-01

Lung cancer has a poor prognosis when not diagnosed early and unresectable lesions are present. The management of small lung nodules noted on computed tomography scan is controversial due to uncertain tumor characteristics. A conventional computer-aided diagnosis (CAD) scheme requires several image processing and pattern recognition steps to accomplish a quantitative tumor differentiation result. In such an ad hoc image analysis pipeline, every step depends heavily on the performance of the previous step. Accordingly, tuning of classification performance in a conventional CAD scheme is very complicated and arduous. Deep learning techniques, on the other hand, have the intrinsic advantage of an automatic exploitation feature and tuning of performance in a seamless fashion. In this study, we attempted to simplify the image analysis pipeline of conventional CAD with deep learning techniques. Specifically, we introduced models of a deep belief network and a convolutional neural network in the context of nodule classification in computed tomography images. Two baseline methods with feature computing steps were implemented for comparison. The experimental results suggest that deep learning methods could achieve better discriminative results and hold promise in the CAD application domain.

Best Practice Strategies for Effective Use of Questions as a Teaching Tool

PubMed Central

Elsner, Jamie; Haines, Stuart T.

2013-01-01

Questions have long been used as a teaching tool by teachers and preceptors to assess students’ knowledge, promote comprehension, and stimulate critical thinking. Well-crafted questions lead to new insights, generate discussion, and promote the comprehensive exploration of subject matter. Poorly constructed questions can stifle learning by creating confusion, intimidating students, and limiting creative thinking. Teachers most often ask lower-order, convergent questions that rely on students’ factual recall of prior knowledge rather than asking higher-order, divergent questions that promote deep thinking, requiring students to analyze and evaluate concepts. This review summarizes the taxonomy of questions, provides strategies for formulating effective questions, and explores practical considerations to enhance student engagement and promote critical thinking. These concepts can be applied in the classroom and in experiential learning environments. PMID:24052658

Best practice strategies for effective use of questions as a teaching tool.

PubMed

Tofade, Toyin; Elsner, Jamie; Haines, Stuart T

2013-09-12

Questions have long been used as a teaching tool by teachers and preceptors to assess students' knowledge, promote comprehension, and stimulate critical thinking. Well-crafted questions lead to new insights, generate discussion, and promote the comprehensive exploration of subject matter. Poorly constructed questions can stifle learning by creating confusion, intimidating students, and limiting creative thinking. Teachers most often ask lower-order, convergent questions that rely on students' factual recall of prior knowledge rather than asking higher-order, divergent questions that promote deep thinking, requiring students to analyze and evaluate concepts. This review summarizes the taxonomy of questions, provides strategies for formulating effective questions, and explores practical considerations to enhance student engagement and promote critical thinking. These concepts can be applied in the classroom and in experiential learning environments.

Computational ghost imaging using deep learning

NASA Astrophysics Data System (ADS)

Shimobaba, Tomoyoshi; Endo, Yutaka; Nishitsuji, Takashi; Takahashi, Takayuki; Nagahama, Yuki; Hasegawa, Satoki; Sano, Marie; Hirayama, Ryuji; Kakue, Takashi; Shiraki, Atsushi; Ito, Tomoyoshi

2018-04-01

Computational ghost imaging (CGI) is a single-pixel imaging technique that exploits the correlation between known random patterns and the measured intensity of light transmitted (or reflected) by an object. Although CGI can obtain two- or three-dimensional images with a single or a few bucket detectors, the quality of the reconstructed images is reduced by noise due to the reconstruction of images from random patterns. In this study, we improve the quality of CGI images using deep learning. A deep neural network is used to automatically learn the features of noise-contaminated CGI images. After training, the network is able to predict low-noise images from new noise-contaminated CGI images.

Low Data Drug Discovery with One-Shot Learning.

PubMed

Altae-Tran, Han; Ramsundar, Bharath; Pappu, Aneesh S; Pande, Vijay

2017-04-26

Recent advances in machine learning have made significant contributions to drug discovery. Deep neural networks in particular have been demonstrated to provide significant boosts in predictive power when inferring the properties and activities of small-molecule compounds (Ma, J. et al. J. Chem. Inf. 2015, 55, 263-274). However, the applicability of these techniques has been limited by the requirement for large amounts of training data. In this work, we demonstrate how one-shot learning can be used to significantly lower the amounts of data required to make meaningful predictions in drug discovery applications. We introduce a new architecture, the iterative refinement long short-term memory, that, when combined with graph convolutional neural networks, significantly improves learning of meaningful distance metrics over small-molecules. We open source all models introduced in this work as part of DeepChem, an open-source framework for deep-learning in drug discovery (Ramsundar, B. deepchem.io. https://github.com/deepchem/deepchem, 2016).

Deep learning of orthographic representations in baboons.

PubMed

Hannagan, Thomas; Ziegler, Johannes C; Dufau, Stéphane; Fagot, Joël; Grainger, Jonathan

2014-01-01

What is the origin of our ability to learn orthographic knowledge? We use deep convolutional networks to emulate the primate's ventral visual stream and explore the recent finding that baboons can be trained to discriminate English words from nonwords. The networks were exposed to the exact same sequence of stimuli and reinforcement signals as the baboons in the experiment, and learned to map real visual inputs (pixels) of letter strings onto binary word/nonword responses. We show that the networks' highest levels of representations were indeed sensitive to letter combinations as postulated in our previous research. The model also captured the key empirical findings, such as generalization to novel words, along with some intriguing inter-individual differences. The present work shows the merits of deep learning networks that can simulate the whole processing chain all the way from the visual input to the response while allowing researchers to analyze the complex representations that emerge during the learning process.

Deep Learning for ECG Classification

NASA Astrophysics Data System (ADS)

Pyakillya, B.; Kazachenko, N.; Mikhailovsky, N.

2017-10-01

The importance of ECG classification is very high now due to many current medical applications where this problem can be stated. Currently, there are many machine learning (ML) solutions which can be used for analyzing and classifying ECG data. However, the main disadvantages of these ML results is use of heuristic hand-crafted or engineered features with shallow feature learning architectures. The problem relies in the possibility not to find most appropriate features which will give high classification accuracy in this ECG problem. One of the proposing solution is to use deep learning architectures where first layers of convolutional neurons behave as feature extractors and in the end some fully-connected (FCN) layers are used for making final decision about ECG classes. In this work the deep learning architecture with 1D convolutional layers and FCN layers for ECG classification is presented and some classification results are showed.

[Severity classification of chronic obstructive pulmonary disease based on deep learning].

PubMed

Ying, Jun; Yang, Ceyuan; Li, Quanzheng; Xue, Wanguo; Li, Tanshi; Cao, Wenzhe

2017-12-01

In this paper, a deep learning method has been raised to build an automatic classification algorithm of severity of chronic obstructive pulmonary disease. Large sample clinical data as input feature were analyzed for their weights in classification. Through feature selection, model training, parameter optimization and model testing, a classification prediction model based on deep belief network was built to predict severity classification criteria raised by the Global Initiative for Chronic Obstructive Lung Disease (GOLD). We get accuracy over 90% in prediction for two different standardized versions of severity criteria raised in 2007 and 2011 respectively. Moreover, we also got the contribution ranking of different input features through analyzing the model coefficient matrix and confirmed that there was a certain degree of agreement between the more contributive input features and the clinical diagnostic knowledge. The validity of the deep belief network model was proved by this result. This study provides an effective solution for the application of deep learning method in automatic diagnostic decision making.

Deep convolutional neural network based antenna selection in multiple-input multiple-output system

NASA Astrophysics Data System (ADS)

Cai, Jiaxin; Li, Yan; Hu, Ying

2018-03-01

Antenna selection of wireless communication system has attracted increasing attention due to the challenge of keeping a balance between communication performance and computational complexity in large-scale Multiple-Input MultipleOutput antenna systems. Recently, deep learning based methods have achieved promising performance for large-scale data processing and analysis in many application fields. This paper is the first attempt to introduce the deep learning technique into the field of Multiple-Input Multiple-Output antenna selection in wireless communications. First, the label of attenuation coefficients channel matrix is generated by minimizing the key performance indicator of training antenna systems. Then, a deep convolutional neural network that explicitly exploits the massive latent cues of attenuation coefficients is learned on the training antenna systems. Finally, we use the adopted deep convolutional neural network to classify the channel matrix labels of test antennas and select the optimal antenna subset. Simulation experimental results demonstrate that our method can achieve better performance than the state-of-the-art baselines for data-driven based wireless antenna selection.

Embellishing Problem-Solving Examples with Deep Structure Information Facilitates Transfer

ERIC Educational Resources Information Center

Lee, Hee Seung; Betts, Shawn; Anderson, John R.

2017-01-01

Appreciation of problem structure is critical to successful learning. Two experiments investigated effective ways of communicating problem structure in a computer-based learning environment and tested whether verbal instruction is necessary to specify solution steps, when deep structure is already embellished by instructional examples.…

Effect of semantic coherence on episodic memory processes in schizophrenia.

PubMed

Battal Merlet, Lâle; Morel, Shasha; Blanchet, Alain; Lockman, Hazlin; Kostova, Milena

2014-12-30

Schizophrenia is associated with severe episodic retrieval impairment. The aim of this study was to investigate the possibility that schizophrenia patients could improve their familiarity and/or recollection processes by manipulating the semantic coherence of to-be-learned stimuli and using deep encoding. Twelve schizophrenia patients and 12 healthy controls of comparable age, gender, and educational level undertook an associative recognition memory task. The stimuli consisted of pairs of words that were either related or unrelated to a given semantic category. The process dissociation procedure was used to calculate the estimates of familiarity and recollection processes. Both groups showed enhanced memory performances for semantically related words. However, in healthy controls, semantic relatedness led to enhanced recollection, while in schizophrenia patients, it induced enhanced familiarity. The familiarity estimates for related words were comparable in both groups, indicating that familiarity could be used as a compensatory mechanism in schizophrenia patients. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

Applying Deep Learning in Medical Images: The Case of Bone Age Estimation.

PubMed

Lee, Jang Hyung; Kim, Kwang Gi

2018-01-01

A diagnostic need often arises to estimate bone age from X-ray images of the hand of a subject during the growth period. Together with measured physical height, such information may be used as indicators for the height growth prognosis of the subject. We present a way to apply the deep learning technique to medical image analysis using hand bone age estimation as an example. Age estimation was formulated as a regression problem with hand X-ray images as input and estimated age as output. A set of hand X-ray images was used to form a training set with which a regression model was trained. An image preprocessing procedure is described which reduces image variations across data instances that are unrelated to age-wise variation. The use of Caffe, a deep learning tool is demonstrated. A rather simple deep learning network was adopted and trained for tutorial purpose. A test set distinct from the training set was formed to assess the validity of the approach. The measured mean absolute difference value was 18.9 months, and the concordance correlation coefficient was 0.78. It is shown that the proposed deep learning-based neural network can be used to estimate a subject's age from hand X-ray images, which eliminates the need for tedious atlas look-ups in clinical environments and should improve the time and cost efficiency of the estimation process.

The extraction of motion-onset VEP BCI features based on deep learning and compressed sensing.

PubMed

Ma, Teng; Li, Hui; Yang, Hao; Lv, Xulin; Li, Peiyang; Liu, Tiejun; Yao, Dezhong; Xu, Peng

2017-01-01

Motion-onset visual evoked potentials (mVEP) can provide a softer stimulus with reduced fatigue, and it has potential applications for brain computer interface(BCI)systems. However, the mVEP waveform is seriously masked in the strong background EEG activities, and an effective approach is needed to extract the corresponding mVEP features to perform task recognition for BCI control. In the current study, we combine deep learning with compressed sensing to mine discriminative mVEP information to improve the mVEP BCI performance. The deep learning and compressed sensing approach can generate the multi-modality features which can effectively improve the BCI performance with approximately 3.5% accuracy incensement over all 11 subjects and is more effective for those subjects with relatively poor performance when using the conventional features. Compared with the conventional amplitude-based mVEP feature extraction approach, the deep learning and compressed sensing approach has a higher classification accuracy and is more effective for subjects with relatively poor performance. According to the results, the deep learning and compressed sensing approach is more effective for extracting the mVEP feature to construct the corresponding BCI system, and the proposed feature extraction framework is easy to extend to other types of BCIs, such as motor imagery (MI), steady-state visual evoked potential (SSVEP)and P300. Copyright © 2016 Elsevier B.V. All rights reserved.

Combining Deep and Handcrafted Image Features for Presentation Attack Detection in Face Recognition Systems Using Visible-Light Camera Sensors

PubMed Central

Nguyen, Dat Tien; Pham, Tuyen Danh; Baek, Na Rae; Park, Kang Ryoung

2018-01-01

Although face recognition systems have wide application, they are vulnerable to presentation attack samples (fake samples). Therefore, a presentation attack detection (PAD) method is required to enhance the security level of face recognition systems. Most of the previously proposed PAD methods for face recognition systems have focused on using handcrafted image features, which are designed by expert knowledge of designers, such as Gabor filter, local binary pattern (LBP), local ternary pattern (LTP), and histogram of oriented gradients (HOG). As a result, the extracted features reflect limited aspects of the problem, yielding a detection accuracy that is low and varies with the characteristics of presentation attack face images. The deep learning method has been developed in the computer vision research community, which is proven to be suitable for automatically training a feature extractor that can be used to enhance the ability of handcrafted features. To overcome the limitations of previously proposed PAD methods, we propose a new PAD method that uses a combination of deep and handcrafted features extracted from the images by visible-light camera sensor. Our proposed method uses the convolutional neural network (CNN) method to extract deep image features and the multi-level local binary pattern (MLBP) method to extract skin detail features from face images to discriminate the real and presentation attack face images. By combining the two types of image features, we form a new type of image features, called hybrid features, which has stronger discrimination ability than single image features. Finally, we use the support vector machine (SVM) method to classify the image features into real or presentation attack class. Our experimental results indicate that our proposed method outperforms previous PAD methods by yielding the smallest error rates on the same image databases. PMID:29495417

Combining Deep and Handcrafted Image Features for Presentation Attack Detection in Face Recognition Systems Using Visible-Light Camera Sensors.

PubMed

Nguyen, Dat Tien; Pham, Tuyen Danh; Baek, Na Rae; Park, Kang Ryoung

2018-02-26

Although face recognition systems have wide application, they are vulnerable to presentation attack samples (fake samples). Therefore, a presentation attack detection (PAD) method is required to enhance the security level of face recognition systems. Most of the previously proposed PAD methods for face recognition systems have focused on using handcrafted image features, which are designed by expert knowledge of designers, such as Gabor filter, local binary pattern (LBP), local ternary pattern (LTP), and histogram of oriented gradients (HOG). As a result, the extracted features reflect limited aspects of the problem, yielding a detection accuracy that is low and varies with the characteristics of presentation attack face images. The deep learning method has been developed in the computer vision research community, which is proven to be suitable for automatically training a feature extractor that can be used to enhance the ability of handcrafted features. To overcome the limitations of previously proposed PAD methods, we propose a new PAD method that uses a combination of deep and handcrafted features extracted from the images by visible-light camera sensor. Our proposed method uses the convolutional neural network (CNN) method to extract deep image features and the multi-level local binary pattern (MLBP) method to extract skin detail features from face images to discriminate the real and presentation attack face images. By combining the two types of image features, we form a new type of image features, called hybrid features, which has stronger discrimination ability than single image features. Finally, we use the support vector machine (SVM) method to classify the image features into real or presentation attack class. Our experimental results indicate that our proposed method outperforms previous PAD methods by yielding the smallest error rates on the same image databases.

Deep ensemble learning of sparse regression models for brain disease diagnosis.

PubMed

Suk, Heung-Il; Lee, Seong-Whan; Shen, Dinggang

2017-04-01

Recent studies on brain imaging analysis witnessed the core roles of machine learning techniques in computer-assisted intervention for brain disease diagnosis. Of various machine-learning techniques, sparse regression models have proved their effectiveness in handling high-dimensional data but with a small number of training samples, especially in medical problems. In the meantime, deep learning methods have been making great successes by outperforming the state-of-the-art performances in various applications. In this paper, we propose a novel framework that combines the two conceptually different methods of sparse regression and deep learning for Alzheimer's disease/mild cognitive impairment diagnosis and prognosis. Specifically, we first train multiple sparse regression models, each of which is trained with different values of a regularization control parameter. Thus, our multiple sparse regression models potentially select different feature subsets from the original feature set; thereby they have different powers to predict the response values, i.e., clinical label and clinical scores in our work. By regarding the response values from our sparse regression models as target-level representations, we then build a deep convolutional neural network for clinical decision making, which thus we call 'Deep Ensemble Sparse Regression Network.' To our best knowledge, this is the first work that combines sparse regression models with deep neural network. In our experiments with the ADNI cohort, we validated the effectiveness of the proposed method by achieving the highest diagnostic accuracies in three classification tasks. We also rigorously analyzed our results and compared with the previous studies on the ADNI cohort in the literature. Copyright © 2017 Elsevier B.V. All rights reserved.

Deep ensemble learning of sparse regression models for brain disease diagnosis

PubMed Central

Suk, Heung-Il; Lee, Seong-Whan; Shen, Dinggang

2018-01-01

Recent studies on brain imaging analysis witnessed the core roles of machine learning techniques in computer-assisted intervention for brain disease diagnosis. Of various machine-learning techniques, sparse regression models have proved their effectiveness in handling high-dimensional data but with a small number of training samples, especially in medical problems. In the meantime, deep learning methods have been making great successes by outperforming the state-of-the-art performances in various applications. In this paper, we propose a novel framework that combines the two conceptually different methods of sparse regression and deep learning for Alzheimer’s disease/mild cognitive impairment diagnosis and prognosis. Specifically, we first train multiple sparse regression models, each of which is trained with different values of a regularization control parameter. Thus, our multiple sparse regression models potentially select different feature subsets from the original feature set; thereby they have different powers to predict the response values, i.e., clinical label and clinical scores in our work. By regarding the response values from our sparse regression models as target-level representations, we then build a deep convolutional neural network for clinical decision making, which thus we call ‘ Deep Ensemble Sparse Regression Network.’ To our best knowledge, this is the first work that combines sparse regression models with deep neural network. In our experiments with the ADNI cohort, we validated the effectiveness of the proposed method by achieving the highest diagnostic accuracies in three classification tasks. We also rigorously analyzed our results and compared with the previous studies on the ADNI cohort in the literature. PMID:28167394

An application of programmatic assessment for learning (PAL) system for general practice training.

PubMed

Schuwirth, Lambert; Valentine, Nyoli; Dilena, Paul

2017-01-01

Aim: Programmatic assessment for learning (PAL) is becoming more and more popular as a concept but its implementation is not without problems. In this paper we describe the design principles behind a PAL program in a general practice training context. Design principles: The PAL program was designed to optimise the meaningfulness of assessment information for the registrar and to make him/her use that information to self regulate their learning. The main principles in the program were cognitivist and transformative. The main cognitive principles we used were fostering the understanding of deep structures and stimulating transfer by making registrars constantly connect practice experiences with background knowledge. Ericsson's deliberate practice approach was built in with regard to the provision of feedback combined with Pintrich's model of self regulation. Mezirow's transformative learning and insights from social network theory on collaborative learning were used to support the registrars in their development to become GP professionals. Finally the principal of test enhanced learning was optimised. Epilogue: We have provided this example explain the design decisions behind our program, but not want to present our program as the solution to any given situation.

Medical students' reflective writing about a task-based learning experience on public health communication.

PubMed

Koh, Yang Huang; Wong, Mee Lian; Lee, Jeanette Jen-Mai

2014-02-01

Medical educators constantly face the challenge of preparing students for public health practice. This study aimed to analyze students' reflections to gain insight into their task-based experiences in the public health communication selective. We have also examined their self-reported learning outcomes and benefits with regard to application of public health communication. Each student wrote a semi-structured reflective journal about his or her experiences leading to the delivery of a public health talk by the group. Records from 41 students were content-analyzed for recurring themes and sub-themes. Students reported a wide range of personal and professional issues. Their writings were characterized by a deep sense of self-awareness and social relatedness such as increased self-worth, communications skills, and collaborative learning. The learning encounter challenged assumptions, and enhanced awareness of the complexity of behaviour change Students also wrote about learning being more enjoyable and how the selective had forced them to adopt a more thoughtful stance towards knowledge acquisition and assimilation. Task-based learning combined with a process for reflection holds promise as an educational strategy for teaching public health communication, and cultivating the habits of reflective practice.

Blackboxing: social learning strategies and cultural evolution

PubMed Central

Heyes, Cecilia

2016-01-01

Social learning strategies (SLSs) enable humans, non-human animals, and artificial agents to make adaptive decisions about when they should copy other agents, and who they should copy. Behavioural ecologists and economists have discovered an impressive range of SLSs, and explored their likely impact on behavioural efficiency and reproductive fitness while using the ‘phenotypic gambit’; ignoring, or remaining deliberately agnostic about, the nature and origins of the cognitive processes that implement SLSs. Here I argue that this ‘blackboxing' of SLSs is no longer a viable scientific strategy. It has contributed, through the ‘social learning strategies tournament', to the premature conclusion that social learning is generally better than asocial learning, and to a deep puzzle about the relationship between SLSs and cultural evolution. The puzzle can be solved by recognizing that whereas most SLSs are ‘planetary'—they depend on domain-general cognitive processes—some SLSs, found only in humans, are ‘cook-like'—they depend on explicit, metacognitive rules, such as copy digital natives. These metacognitive SLSs contribute to cultural evolution by fostering the development of processes that enhance the exclusivity, specificity, and accuracy of social learning. PMID:27069046

Do sophisticated epistemic beliefs predict meaningful learning? Findings from a structural equation model of undergraduate biology learning

NASA Astrophysics Data System (ADS)

Lee, Silvia Wen-Yu; Liang, Jyh-Chong; Tsai, Chin-Chung

2016-10-01

This study investigated the relationships among college students' epistemic beliefs in biology (EBB), conceptions of learning biology (COLB), and strategies of learning biology (SLB). EBB includes four dimensions, namely 'multiple-source,' 'uncertainty,' 'development,' and 'justification.' COLB is further divided into 'constructivist' and 'reproductive' conceptions, while SLB represents deep strategies and surface learning strategies. Questionnaire responses were gathered from 303 college students. The results of the confirmatory factor analysis and structural equation modelling showed acceptable model fits. Mediation testing further revealed two paths with complete mediation. In sum, students' epistemic beliefs of 'uncertainty' and 'justification' in biology were statistically significant in explaining the constructivist and reproductive COLB, respectively; and 'uncertainty' was statistically significant in explaining the deep SLB as well. The results of mediation testing further revealed that 'uncertainty' predicted surface strategies through the mediation of 'reproductive' conceptions; and the relationship between 'justification' and deep strategies was mediated by 'constructivist' COLB. This study provides evidence for the essential roles some epistemic beliefs play in predicting students' learning.

Enhancing deep convolutional neural network scheme for breast cancer diagnosis with unlabeled data.

PubMed

Sun, Wenqing; Tseng, Tzu-Liang Bill; Zhang, Jianying; Qian, Wei

2017-04-01

In this study we developed a graph based semi-supervised learning (SSL) scheme using deep convolutional neural network (CNN) for breast cancer diagnosis. CNN usually needs a large amount of labeled data for training and fine tuning the parameters, and our proposed scheme only requires a small portion of labeled data in training set. Four modules were included in the diagnosis system: data weighing, feature selection, dividing co-training data labeling, and CNN. 3158 region of interests (ROIs) with each containing a mass extracted from 1874 pairs of mammogram images were used for this study. Among them 100 ROIs were treated as labeled data while the rest were treated as unlabeled. The area under the curve (AUC) observed in our study was 0.8818, and the accuracy of CNN is 0.8243 using the mixed labeled and unlabeled data. Copyright © 2016. Published by Elsevier Ltd.

Trans-species learning of cellular signaling systems with bimodal deep belief networks

PubMed Central

Chen, Lujia; Cai, Chunhui; Chen, Vicky; Lu, Xinghua

2015-01-01

Motivation: Model organisms play critical roles in biomedical research of human diseases and drug development. An imperative task is to translate information/knowledge acquired from model organisms to humans. In this study, we address a trans-species learning problem: predicting human cell responses to diverse stimuli, based on the responses of rat cells treated with the same stimuli. Results: We hypothesized that rat and human cells share a common signal-encoding mechanism but employ different proteins to transmit signals, and we developed a bimodal deep belief network and a semi-restricted bimodal deep belief network to represent the common encoding mechanism and perform trans-species learning. These ‘deep learning’ models include hierarchically organized latent variables capable of capturing the statistical structures in the observed proteomic data in a distributed fashion. The results show that the models significantly outperform two current state-of-the-art classification algorithms. Our study demonstrated the potential of using deep hierarchical models to simulate cellular signaling systems. Availability and implementation: The software is available at the following URL: http://pubreview.dbmi.pitt.edu/TransSpeciesDeepLearning/. The data are available through SBV IMPROVER website, https://www.sbvimprover.com/challenge-2/overview, upon publication of the report by the organizers. Contact: xinghua@pitt.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:25995230

Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data.

PubMed

Aliper, Alexander; Plis, Sergey; Artemov, Artem; Ulloa, Alvaro; Mamoshina, Polina; Zhavoronkov, Alex

2016-07-05

Deep learning is rapidly advancing many areas of science and technology with multiple success stories in image, text, voice and video recognition, robotics, and autonomous driving. In this paper we demonstrate how deep neural networks (DNN) trained on large transcriptional response data sets can classify various drugs to therapeutic categories solely based on their transcriptional profiles. We used the perturbation samples of 678 drugs across A549, MCF-7, and PC-3 cell lines from the LINCS Project and linked those to 12 therapeutic use categories derived from MeSH. To train the DNN, we utilized both gene level transcriptomic data and transcriptomic data processed using a pathway activation scoring algorithm, for a pooled data set of samples perturbed with different concentrations of the drug for 6 and 24 hours. In both pathway and gene level classification, DNN achieved high classification accuracy and convincingly outperformed the support vector machine (SVM) model on every multiclass classification problem, however, models based on pathway level data performed significantly better. For the first time we demonstrate a deep learning neural net trained on transcriptomic data to recognize pharmacological properties of multiple drugs across different biological systems and conditions. We also propose using deep neural net confusion matrices for drug repositioning. This work is a proof of principle for applying deep learning to drug discovery and development.

Deep learning applications for predicting pharmacological properties of drugs and drug repurposing using transcriptomic data

PubMed Central

Aliper, Alexander; Plis, Sergey; Artemov, Artem; Ulloa, Alvaro; Mamoshina, Polina; Zhavoronkov, Alex

2016-01-01

Deep learning is rapidly advancing many areas of science and technology with multiple success stories in image, text, voice and video recognition, robotics and autonomous driving. In this paper we demonstrate how deep neural networks (DNN) trained on large transcriptional response data sets can classify various drugs to therapeutic categories solely based on their transcriptional profiles. We used the perturbation samples of 678 drugs across A549, MCF‐7 and PC‐3 cell lines from the LINCS project and linked those to 12 therapeutic use categories derived from MeSH. To train the DNN, we utilized both gene level transcriptomic data and transcriptomic data processed using a pathway activation scoring algorithm, for a pooled dataset of samples perturbed with different concentrations of the drug for 6 and 24 hours. In both gene and pathway level classification, DNN convincingly outperformed support vector machine (SVM) model on every multiclass classification problem, however, models based on a pathway level classification perform better. For the first time we demonstrate a deep learning neural net trained on transcriptomic data to recognize pharmacological properties of multiple drugs across different biological systems and conditions. We also propose using deep neural net confusion matrices for drug repositioning. This work is a proof of principle for applying deep learning to drug discovery and development. PMID:27200455

Towards automatic pulmonary nodule management in lung cancer screening with deep learning

NASA Astrophysics Data System (ADS)

Ciompi, Francesco; Chung, Kaman; van Riel, Sarah J.; Setio, Arnaud Arindra Adiyoso; Gerke, Paul K.; Jacobs, Colin; Th. Scholten, Ernst; Schaefer-Prokop, Cornelia; Wille, Mathilde M. W.; Marchianò, Alfonso; Pastorino, Ugo; Prokop, Mathias; van Ginneken, Bram

2017-04-01

The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

Towards automatic pulmonary nodule management in lung cancer screening with deep learning.

PubMed

Ciompi, Francesco; Chung, Kaman; van Riel, Sarah J; Setio, Arnaud Arindra Adiyoso; Gerke, Paul K; Jacobs, Colin; Scholten, Ernst Th; Schaefer-Prokop, Cornelia; Wille, Mathilde M W; Marchianò, Alfonso; Pastorino, Ugo; Prokop, Mathias; van Ginneken, Bram

2017-04-19

The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers.

Towards automatic pulmonary nodule management in lung cancer screening with deep learning

PubMed Central

Ciompi, Francesco; Chung, Kaman; van Riel, Sarah J.; Setio, Arnaud Arindra Adiyoso; Gerke, Paul K.; Jacobs, Colin; Th. Scholten, Ernst; Schaefer-Prokop, Cornelia; Wille, Mathilde M. W.; Marchianò, Alfonso; Pastorino, Ugo; Prokop, Mathias; van Ginneken, Bram

2017-01-01

The introduction of lung cancer screening programs will produce an unprecedented amount of chest CT scans in the near future, which radiologists will have to read in order to decide on a patient follow-up strategy. According to the current guidelines, the workup of screen-detected nodules strongly relies on nodule size and nodule type. In this paper, we present a deep learning system based on multi-stream multi-scale convolutional networks, which automatically classifies all nodule types relevant for nodule workup. The system processes raw CT data containing a nodule without the need for any additional information such as nodule segmentation or nodule size and learns a representation of 3D data by analyzing an arbitrary number of 2D views of a given nodule. The deep learning system was trained with data from the Italian MILD screening trial and validated on an independent set of data from the Danish DLCST screening trial. We analyze the advantage of processing nodules at multiple scales with a multi-stream convolutional network architecture, and we show that the proposed deep learning system achieves performance at classifying nodule type that surpasses the one of classical machine learning approaches and is within the inter-observer variability among four experienced human observers. PMID:28422152

Problem-based learning: an approach to enhancing learning and understanding of optics for first-year students

NASA Astrophysics Data System (ADS)

Bowe, Brian W.; Daly, Siobhan; Flynn, Cathal; Howard, Robert

2003-03-01

In this paper a model for the implementation of a problem-based learning (PBL) course for a typical year physics one programme is described. Reference is made to how PBL has been implemented in relation to geometrical and physical optics. PBL derives from the theory that learning is an active process in which the learner constructs new knowledge on the basis of current knowledge, unlike traditional teaching practices in higher education, where the emphasis is on the transmission of factual knowledge. The course consists of a set of optics related real life problems that are carefully constructed to meet specified learning outcomes. The students, working in groups, encounter these problem-solving situations and are facilitated to produce a solution. The PBL course promotes student engagement in order to achieve higher levels of cognitive learning. Evaluation of the course indicates that the students adopt a deep learning approach and that they attain a thorough understanding of the subject instead of the superficial understanding associated with surface learning. The methodology also helps students to develop metacognitive skills. Another outcome of this teaching methodology is the development of key skills such as the ability to work in a group and to communicate, and present, information effectively.

Manifold learning of brain MRIs by deep learning.

PubMed

Brosch, Tom; Tam, Roger

2013-01-01

Manifold learning of medical images plays a potentially important role for modeling anatomical variability within a population with pplications that include segmentation, registration, and prediction of clinical parameters. This paper describes a novel method for learning the manifold of 3D brain images that, unlike most existing manifold learning methods, does not require the manifold space to be locally linear, and does not require a predefined similarity measure or a prebuilt proximity graph. Our manifold learning method is based on deep learning, a machine learning approach that uses layered networks (called deep belief networks, or DBNs) and has received much attention recently in the computer vision field due to their success in object recognition tasks. DBNs have traditionally been too computationally expensive for application to 3D images due to the large number of trainable parameters. Our primary contributions are (1) a much more computationally efficient training method for DBNs that makes training on 3D medical images with a resolution of up to 128 x 128 x 128 practical, and (2) the demonstration that DBNs can learn a low-dimensional manifold of brain volumes that detects modes of variations that correlate to demographic and disease parameters.

Machine learning in heart failure: ready for prime time.

PubMed

Awan, Saqib Ejaz; Sohel, Ferdous; Sanfilippo, Frank Mario; Bennamoun, Mohammed; Dwivedi, Girish

2018-03-01

The aim of this review is to present an up-to-date overview of the application of machine learning methods in heart failure including diagnosis, classification, readmissions and medication adherence. Recent studies have shown that the application of machine learning techniques may have the potential to improve heart failure outcomes and management, including cost savings by improving existing diagnostic and treatment support systems. Recently developed deep learning methods are expected to yield even better performance than traditional machine learning techniques in performing complex tasks by learning the intricate patterns hidden in big medical data. The review summarizes the recent developments in the application of machine and deep learning methods in heart failure management.

AggNet: Deep Learning From Crowds for Mitosis Detection in Breast Cancer Histology Images.

PubMed

Albarqouni, Shadi; Baur, Christoph; Achilles, Felix; Belagiannis, Vasileios; Demirci, Stefanie; Navab, Nassir

2016-05-01

The lack of publicly available ground-truth data has been identified as the major challenge for transferring recent developments in deep learning to the biomedical imaging domain. Though crowdsourcing has enabled annotation of large scale databases for real world images, its application for biomedical purposes requires a deeper understanding and hence, more precise definition of the actual annotation task. The fact that expert tasks are being outsourced to non-expert users may lead to noisy annotations introducing disagreement between users. Despite being a valuable resource for learning annotation models from crowdsourcing, conventional machine-learning methods may have difficulties dealing with noisy annotations during training. In this manuscript, we present a new concept for learning from crowds that handle data aggregation directly as part of the learning process of the convolutional neural network (CNN) via additional crowdsourcing layer (AggNet). Besides, we present an experimental study on learning from crowds designed to answer the following questions. 1) Can deep CNN be trained with data collected from crowdsourcing? 2) How to adapt the CNN to train on multiple types of annotation datasets (ground truth and crowd-based)? 3) How does the choice of annotation and aggregation affect the accuracy? Our experimental setup involved Annot8, a self-implemented web-platform based on Crowdflower API realizing image annotation tasks for a publicly available biomedical image database. Our results give valuable insights into the functionality of deep CNN learning from crowd annotations and prove the necessity of data aggregation integration.