term learning architecture: Topics by Science.gov

Sample records for term learning architecture

The entropy reduction engine: Integrating planning, scheduling, and control

NASA Technical Reports Server (NTRS)

Drummond, Mark; Bresina, John L.; Kedar, Smadar T.

1991-01-01

The Entropy Reduction Engine, an architecture for the integration of planning, scheduling, and control, is described. The architecture is motivated, presented, and analyzed in terms of its different components; namely, problem reduction, temporal projection, and situated control rule execution. Experience with this architecture has motivated the recent integration of learning. The learning methods are described along with their impact on architecture performance.
A processing architecture for associative short-term memory in electronic noses

NASA Astrophysics Data System (ADS)

Pioggia, G.; Ferro, M.; Di Francesco, F.; DeRossi, D.

2006-11-01

Electronic nose (e-nose) architectures usually consist of several modules that process various tasks such as control, data acquisition, data filtering, feature selection and pattern analysis. Heterogeneous techniques derived from chemometrics, neural networks, and fuzzy rules used to implement such tasks may lead to issues concerning module interconnection and cooperation. Moreover, a new learning phase is mandatory once new measurements have been added to the dataset, thus causing changes in the previously derived model. Consequently, if a loss in the previous learning occurs (catastrophic interference), real-time applications of e-noses are limited. To overcome these problems this paper presents an architecture for dynamic and efficient management of multi-transducer data processing techniques and for saving an associative short-term memory of the previously learned model. The architecture implements an artificial model of a hippocampus-based working memory, enabling the system to be ready for real-time applications. Starting from the base models available in the architecture core, dedicated models for neurons, maps and connections were tailored to an artificial olfactory system devoted to analysing olive oil. In order to verify the ability of the processing architecture in associative and short-term memory, a paired-associate learning test was applied. The avoidance of catastrophic interference was observed.
An Architecture Combining IMS-LD and Web Services for Flexible Data-Transfer in CSCL

ERIC Educational Resources Information Center

Magnisalis, Ioannis; Demetriadis, Stavros

2017-01-01

This article presents evaluation data regarding the MAPIS3 architecture which is proposed as a solution for the data-transfer among various tools to promote flexible collaborative learning designs. We describe the problem that this architecture deals with as "tool orchestration" in collaborative learning settings. This term refers to a…
Bio-inspired adaptive feedback error learning architecture for motor control.

PubMed

Tolu, Silvia; Vanegas, Mauricio; Luque, Niceto R; Garrido, Jesús A; Ros, Eduardo

2012-10-01

This study proposes an adaptive control architecture based on an accurate regression method called Locally Weighted Projection Regression (LWPR) and on a bio-inspired module, such as a cerebellar-like engine. This hybrid architecture takes full advantage of the machine learning module (LWPR kernel) to abstract an optimized representation of the sensorimotor space while the cerebellar component integrates this to generate corrective terms in the framework of a control task. Furthermore, we illustrate how the use of a simple adaptive error feedback term allows to use the proposed architecture even in the absence of an accurate analytic reference model. The presented approach achieves an accurate control with low gain corrective terms (for compliant control schemes). We evaluate the contribution of the different components of the proposed scheme comparing the obtained performance with alternative approaches. Then, we show that the presented architecture can be used for accurate manipulation of different objects when their physical properties are not directly known by the controller. We evaluate how the scheme scales for simulated plants of high Degrees of Freedom (7-DOFs).
A digital protection system incorporating knowledge based learning

NASA Astrophysics Data System (ADS)

Watson, Karan; Russell, B. Don; McCall, Kurt

A digital system architecture used to diagnoses the operating state and health of electric distribution lines and to generate actions for line protection is presented. The architecture is described functionally and to a limited extent at the hardware level. This architecture incorporates multiple analysis and fault-detection techniques utilizing a variety of parameters. In addition, a knowledge-based decision maker, a long-term memory retention and recall scheme, and a learning environment are described. Preliminary laboratory implementations of the system elements have been completed. Enhanced protection for electric distribution feeders is provided by this system. Advantages of the system are enumerated.
From Low-Lying Roofs to Towering Spires: Toward a Heideggerian Understanding of Learning Environments

ERIC Educational Resources Information Center

Ream, Todd C.; Ream, Tyler W.

2005-01-01

This article explores the significance that environments play in terms of the learning process. In the United States, the legacy of John Dewey's intellectual efforts left a theoretical understanding that views the architectural composition of learning environments as instrumental mediums which house the educational process. This understanding of…
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.
Framewise phoneme classification with bidirectional LSTM and other neural network architectures.

PubMed

Graves, Alex; Schmidhuber, Jürgen

2005-01-01

In this paper, we present bidirectional Long Short Term Memory (LSTM) networks, and a modified, full gradient version of the LSTM learning algorithm. We evaluate Bidirectional LSTM (BLSTM) and several other network architectures on the benchmark task of framewise phoneme classification, using the TIMIT database. Our main findings are that bidirectional networks outperform unidirectional ones, and Long Short Term Memory (LSTM) is much faster and also more accurate than both standard Recurrent Neural Nets (RNNs) and time-windowed Multilayer Perceptrons (MLPs). Our results support the view that contextual information is crucial to speech processing, and suggest that BLSTM is an effective architecture with which to exploit it.
Case study on perspicacity of collaborative learning experiences

NASA Astrophysics Data System (ADS)

Abdullah, Fadzidah; Majid, Noor Hanita Abdul; Numen, Ibrahim; Kesuma Azmin, Aida; Abd. Rahim, Zaiton; Denan, Zuraini; Emin Sisman, Muhammet

2017-12-01

In the attempt to relate to the architectural practice, architectural education today has augmented the development of collaborative learning environment in the campus scenario. Presently, collaborative work among students from the same program and university is considered common. Hence, attempts of collaboration is extended into having learning and teaching collaboration by means of inter-universities. The School of Architecture, at the International Islamic University Malaysia (IIUM) has explored into having collaboration across the continent with Fatih Sultan Mehmet Waqf University (FSMWU), among faculty members and students of the two (2) universities This paper explicates the empirical study on students’ perspicacity of their collaborative learning experiences; in term of effectiveness, generative behaviour, and teamwork. Survey with three (3) open-ended questions are distributed to students to express their opinions on learning collaboration that they have had during the execution of the Joint Summer School Program (JSSP). Feedback on their perspicacity is obtained and organised into numerical and understandable data display, using qualitative data processing software. Albeit the relevancy of collaborative learning, students gave both positive and negative feedbacks on their experiences. Suggestions are given to enhance the quality of collaborative learning experience for future development
An Approach to Building a Learning Management System that Emphasizes on Incorporating Individualized Dissemination with Intelligent Tutoring

NASA Astrophysics Data System (ADS)

Ghosh, Sreya

2017-02-01

This article proposes a new six-model architecture for an intelligent tutoring system to be incorporated in a learning management system with domain-independence feature and individualized dissemination. The present six model architecture aims to simulate a human tutor. Some recent extensions of using intelligent tutoring system (ITS) explores learning management systems to behave as a real teacher during a teaching-learning process, by taking care of, mainly, the dynamic response system. However, the present paper argues that to mimic a human teacher it needs not only the dynamic response but also the incorporation of the teacher's dynamic review of students' performance and keeping track of their current level of understanding. Here, the term individualization has been used to refer to tailor making of contents and its dissemination fitting to the individual needs and capabilities of learners who is taking a course online and is subjected to teaching in absentia. This paper describes how the individual models of the proposed architecture achieves the features of ITS.
Interaction with Machine Improvisation

NASA Astrophysics Data System (ADS)

Assayag, Gerard; Bloch, George; Cont, Arshia; Dubnov, Shlomo

We describe two multi-agent architectures for an improvisation oriented musician-machine interaction systems that learn in real time from human performers. The improvisation kernel is based on sequence modeling and statistical learning. We present two frameworks of interaction with this kernel. In the first, the stylistic interaction is guided by a human operator in front of an interactive computer environment. In the second framework, the stylistic interaction is delegated to machine intelligence and therefore, knowledge propagation and decision are taken care of by the computer alone. The first framework involves a hybrid architecture using two popular composition/performance environments, Max and OpenMusic, that are put to work and communicate together, each one handling the process at a different time/memory scale. The second framework shares the same representational schemes with the first but uses an Active Learning architecture based on collaborative, competitive and memory-based learning to handle stylistic interactions. Both systems are capable of processing real-time audio/video as well as MIDI. After discussing the general cognitive background of improvisation practices, the statistical modelling tools and the concurrent agent architecture are presented. Then, an Active Learning scheme is described and considered in terms of using different improvisation regimes for improvisation planning. Finally, we provide more details about the different system implementations and describe several performances with the system.
Large-Scale Modeling of Wordform Learning and Representation

ERIC Educational Resources Information Center

Sibley, Daragh E.; Kello, Christopher T.; Plaut, David C.; Elman, Jeffrey L.

2008-01-01

The forms of words as they appear in text and speech are central to theories and models of lexical processing. Nonetheless, current methods for simulating their learning and representation fail to approach the scale and heterogeneity of real wordform lexicons. A connectionist architecture termed the "sequence encoder" is used to learn…
Learning and tuning fuzzy logic controllers through reinforcements.

PubMed

Berenji, H R; Khedkar, P

1992-01-01

A method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system is presented. It is shown that: the generalized approximate-reasoning-based intelligent control (GARIC) architecture learns and tunes a fuzzy logic controller even when only weak reinforcement, such as a binary failure signal, is available; introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward network, which can then adaptively improve performance by using gradient descent methods. The GARIC architecture is applied to a cart-pole balancing system and demonstrates significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.
Architecture for robot intelligence

NASA Technical Reports Server (NTRS)

Peters, II, Richard Alan (Inventor)

2004-01-01

An architecture for robot intelligence enables a robot to learn new behaviors and create new behavior sequences autonomously and interact with a dynamically changing environment. Sensory information is mapped onto a Sensory Ego-Sphere (SES) that rapidly identifies important changes in the environment and functions much like short term memory. Behaviors are stored in a DBAM that creates an active map from the robot's current state to a goal state and functions much like long term memory. A dream state converts recent activities stored in the SES and creates or modifies behaviors in the DBAM.
The Role of Architectural and Learning Constraints in Neural Network Models: A Case Study on Visual Space Coding.

PubMed

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

2017-01-01

The recent "deep learning revolution" in artificial neural networks had strong impact and widespread deployment for engineering applications, but the use of deep learning for neurocomputational modeling has been so far limited. In this article we argue that unsupervised deep learning represents an important step forward for improving neurocomputational models of perception and cognition, because it emphasizes the role of generative learning as opposed to discriminative (supervised) learning. As a case study, we present a series of simulations investigating the emergence of neural coding of visual space for sensorimotor transformations. We compare different network architectures commonly used as building blocks for unsupervised deep learning by systematically testing the type of receptive fields and gain modulation developed by the hidden neurons. In particular, we compare Restricted Boltzmann Machines (RBMs), which are stochastic, generative networks with bidirectional connections trained using contrastive divergence, with autoencoders, which are deterministic networks trained using error backpropagation. For both learning architectures we also explore the role of sparse coding, which has been identified as a fundamental principle of neural computation. The unsupervised models are then compared with supervised, feed-forward networks that learn an explicit mapping between different spatial reference frames. Our simulations show that both architectural and learning constraints strongly influenced the emergent coding of visual space in terms of distribution of tuning functions at the level of single neurons. Unsupervised models, and particularly RBMs, were found to more closely adhere to neurophysiological data from single-cell recordings in the primate parietal cortex. These results provide new insights into how basic properties of artificial neural networks might be relevant for modeling neural information processing in biological systems.
The Role of Architectural and Learning Constraints in Neural Network Models: A Case Study on Visual Space Coding

PubMed Central

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

2017-01-01

The recent “deep learning revolution” in artificial neural networks had strong impact and widespread deployment for engineering applications, but the use of deep learning for neurocomputational modeling has been so far limited. In this article we argue that unsupervised deep learning represents an important step forward for improving neurocomputational models of perception and cognition, because it emphasizes the role of generative learning as opposed to discriminative (supervised) learning. As a case study, we present a series of simulations investigating the emergence of neural coding of visual space for sensorimotor transformations. We compare different network architectures commonly used as building blocks for unsupervised deep learning by systematically testing the type of receptive fields and gain modulation developed by the hidden neurons. In particular, we compare Restricted Boltzmann Machines (RBMs), which are stochastic, generative networks with bidirectional connections trained using contrastive divergence, with autoencoders, which are deterministic networks trained using error backpropagation. For both learning architectures we also explore the role of sparse coding, which has been identified as a fundamental principle of neural computation. The unsupervised models are then compared with supervised, feed-forward networks that learn an explicit mapping between different spatial reference frames. Our simulations show that both architectural and learning constraints strongly influenced the emergent coding of visual space in terms of distribution of tuning functions at the level of single neurons. Unsupervised models, and particularly RBMs, were found to more closely adhere to neurophysiological data from single-cell recordings in the primate parietal cortex. These results provide new insights into how basic properties of artificial neural networks might be relevant for modeling neural information processing in biological systems. PMID:28377709
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
Excessive Stress Disrupts the Architecture of the Developing Brain. Working Paper #3

ERIC Educational Resources Information Center

National Scientific Council on the Developing Child, 2005

2005-01-01

New research suggests that exceptionally stressful experiences early in life may have long-term consequences for a child's learning, behavior, and both physical and mental health. Some types of "positive stress" in a child's life--overcoming the challenges and frustrations of learning a new, difficult task, for instance--can be beneficial. Severe,…
Architecture for Multiple Interacting Robot Intelligences

NASA Technical Reports Server (NTRS)

Peters, Richard Alan, II (Inventor)

2008-01-01

An architecture for robot intelligence enables a robot to learn new behaviors and create new behavior sequences autonomously and interact with a dynamically changing environment. Sensory information is mapped onto a Sensory Ego-Sphere (SES) that rapidly identifies important changes in the environment and functions much like short term memory. Behaviors are stored in a database associative memory (DBAM) that creates an active map from the robot's current state to a goal state and functions much like long term memory. A dream state converts recent activities stored in the SES and creates or modifies behaviors in the DBAM.

Using enterprise architecture to analyse how organisational structure impact motivation and learning

NASA Astrophysics Data System (ADS)

Närman, Pia; Johnson, Pontus; Gingnell, Liv

2016-06-01

When technology, environment, or strategies change, organisations need to adjust their structures accordingly. These structural changes do not always enhance the organisational performance as intended partly because organisational developers do not understand the consequences of structural changes in performance. This article presents a model-based analysis framework for quantitative analysis of the effect of organisational structure on organisation performance in terms of employee motivation and learning. The model is based on Mintzberg's work on organisational structure. The quantitative analysis is formalised using the Object Constraint Language (OCL) and the Unified Modelling Language (UML) and implemented in an enterprise architecture tool.
Learning and tuning fuzzy logic controllers through reinforcements

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.; Khedkar, Pratap

1992-01-01

A new method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system is presented. In particular, our Generalized Approximate Reasoning-based Intelligent Control (GARIC) architecture: (1) learns and tunes a fuzzy logic controller even when only weak reinforcements, such as a binary failure signal, is available; (2) introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; (3) introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and (4) learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward network, which can then adaptively improve performance by using gradient descent methods. We extend the AHC algorithm of Barto, Sutton, and Anderson to include the prior control knowledge of human operators. The GARIC architecture is applied to a cart-pole balancing system and has demonstrated significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.
Toward an Integration of Deep Learning and Neuroscience

PubMed Central

Marblestone, Adam H.; Wayne, Greg; Kording, Konrad P.

2016-01-01

Neuroscience has focused on the detailed implementation of computation, studying neural codes, dynamics and circuits. In machine learning, however, artificial neural networks tend to eschew precisely designed codes, dynamics or circuits in favor of brute force optimization of a cost function, often using simple and relatively uniform initial architectures. Two recent developments have emerged within machine learning that create an opportunity to connect these seemingly divergent perspectives. First, structured architectures are used, including dedicated systems for attention, recursion and various forms of short- and long-term memory storage. Second, cost functions and training procedures have become more complex and are varied across layers and over time. Here we think about the brain in terms of these ideas. We hypothesize that (1) the brain optimizes cost functions, (2) the cost functions are diverse and differ across brain locations and over development, and (3) optimization operates within a pre-structured architecture matched to the computational problems posed by behavior. In support of these hypotheses, we argue that a range of implementations of credit assignment through multiple layers of neurons are compatible with our current knowledge of neural circuitry, and that the brain's specialized systems can be interpreted as enabling efficient optimization for specific problem classes. Such a heterogeneously optimized system, enabled by a series of interacting cost functions, serves to make learning data-efficient and precisely targeted to the needs of the organism. We suggest directions by which neuroscience could seek to refine and test these hypotheses. PMID:27683554
RACE/A: an architectural account of the interactions between learning, task control, and retrieval dynamics.

PubMed

van Maanen, Leendert; van Rijn, Hedderik; Taatgen, Niels

2012-01-01

This article discusses how sequential sampling models can be integrated in a cognitive architecture. The new theory Retrieval by Accumulating Evidence in an Architecture (RACE/A) combines the level of detail typically provided by sequential sampling models with the level of task complexity typically provided by cognitive architectures. We will use RACE/A to model data from two variants of a picture-word interference task in a psychological refractory period design. These models will demonstrate how RACE/A enables interactions between sequential sampling and long-term declarative learning, and between sequential sampling and task control. In a traditional sequential sampling model, the onset of the process within the task is unclear, as is the number of sampling processes. RACE/A provides a theoretical basis for estimating the onset of sequential sampling processes during task execution and allows for easy modeling of multiple sequential sampling processes within a task. Copyright © 2011 Cognitive Science Society, Inc.
Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors.

PubMed

Godino-Llorente, J I; Gómez-Vilda, P

2004-02-01

It is well known that vocal and voice diseases do not necessarily cause perceptible changes in the acoustic voice signal. Acoustic analysis is a useful tool to diagnose voice diseases being a complementary technique to other methods based on direct observation of the vocal folds by laryngoscopy. Through the present paper two neural-network based classification approaches applied to the automatic detection of voice disorders will be studied. Structures studied are multilayer perceptron and learning vector quantization fed using short-term vectors calculated accordingly to the well-known Mel Frequency Coefficient cepstral parameterization. The paper shows that these architectures allow the detection of voice disorders--including glottic cancer--under highly reliable conditions. Within this context, the Learning Vector quantization methodology demonstrated to be more reliable than the multilayer perceptron architecture yielding 96% frame accuracy under similar working conditions.
The Sigma Cognitive Architecture and System: Towards Functionally Elegant Grand Unification

NASA Astrophysics Data System (ADS)

Rosenbloom, Paul S.; Demski, Abram; Ustun, Volkan

2016-12-01

Sigma (Σ) is a cognitive architecture and system whose development is driven by a combination of four desiderata: grand unification, generic cognition, functional elegance, and sufficient efficiency. Work towards these desiderata is guided by the graphical architecture hypothesis, that key to progress on them is combining what has been learned from over three decades' worth of separate work on cognitive architectures and graphical models. In this article, these four desiderata are motivated and explained, and then combined with the graphical architecture hypothesis to yield a rationale for the development of Sigma. The current state of the cognitive architecture is then introduced in detail, along with the graphical architecture that sits below it and implements it. Progress in extending Sigma beyond these architectures and towards a full cognitive system is then detailed in terms of both a systematic set of higher level cognitive idioms that have been developed and several virtual humans that are built from combinations of these idioms. Sigma as a whole is then analyzed in terms of how well the progress to date satisfies the desiderata. This article thus provides the first full motivation, presentation and analysis of Sigma, along with a diversity of more specific results that have been generated during its development.
Outline of a novel architecture for cortical computation.

PubMed

Majumdar, Kaushik

2008-03-01

In this paper a novel architecture for cortical computation has been proposed. This architecture is composed of computing paths consisting of neurons and synapses. These paths have been decomposed into lateral, longitudinal and vertical components. Cortical computation has then been decomposed into lateral computation (LaC), longitudinal computation (LoC) and vertical computation (VeC). It has been shown that various loop structures in the cortical circuit play important roles in cortical computation as well as in memory storage and retrieval, keeping in conformity with the molecular basis of short and long term memory. A new learning scheme for the brain has also been proposed and how it is implemented within the proposed architecture has been explained. A few mathematical results about the architecture have been proposed, some of which are without proof.
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.
"Notice of Violation of IEEE Publication Principles" Multiobjective Reinforcement Learning: A Comprehensive Overview.

PubMed

Liu, Chunming; Xu, Xin; Hu, Dewen

2013-04-29

Reinforcement learning is a powerful mechanism for enabling agents to learn in an unknown environment, and most reinforcement learning algorithms aim to maximize some numerical value, which represents only one long-term objective. However, multiple long-term objectives are exhibited in many real-world decision and control problems; therefore, recently, there has been growing interest in solving multiobjective reinforcement learning (MORL) problems with multiple conflicting objectives. The aim of this paper is to present a comprehensive overview of MORL. In this paper, the basic architecture, research topics, and naive solutions of MORL are introduced at first. Then, several representative MORL approaches and some important directions of recent research are reviewed. The relationships between MORL and other related research are also discussed, which include multiobjective optimization, hierarchical reinforcement learning, and multi-agent reinforcement learning. Finally, research challenges and open problems of MORL techniques are highlighted.
Artificial intelligent e-learning architecture

NASA Astrophysics Data System (ADS)

Alharbi, Mafawez; Jemmali, Mahdi

2017-03-01

Many institutions and university has forced to use e learning, due to its ability to provide additional and flexible solutions for students and researchers. E-learning In the last decade have transported about the extreme changes in the distribution of education allowing learners to access multimedia course material at any time, from anywhere to suit their specific needs. In the form of e learning, instructors and learners live in different places and they do not engage in a classroom environment, but within virtual universe. Many researches have defined e learning based on their objectives. Therefore, there are small number of e-learning architecture have proposed in the literature. However, the proposed architecture has lack of embedding intelligent system in the architecture of e learning. This research argues that unexplored potential remains, as there is scope for e learning to be intelligent system. This research proposes e-learning architecture that incorporates intelligent system. There are intelligence components, which built into the architecture.
A Distributed Intelligent E-Learning System

ERIC Educational Resources Information Center

Kristensen, Terje

2016-01-01

An E-learning system based on a multi-agent (MAS) architecture combined with the Dynamic Content Manager (DCM) model of E-learning, is presented. We discuss the benefits of using such a multi-agent architecture. Finally, the MAS architecture is compared with a pure service-oriented architecture (SOA). This MAS architecture may also be used within…
Application of fuzzy logic-neural network based reinforcement learning to proximity and docking operations: Translational controller results

NASA Technical Reports Server (NTRS)

Jani, Yashvant

1992-01-01

The reinforcement learning techniques developed at Ames Research Center are being applied to proximity and docking operations using the Shuttle and Solar Maximum Mission (SMM) satellite simulation. In utilizing these fuzzy learning techniques, we also use the Approximate Reasoning based Intelligent Control (ARIC) architecture, and so we use two terms interchangeable to imply the same. This activity is carried out in the Software Technology Laboratory utilizing the Orbital Operations Simulator (OOS). This report is the deliverable D3 in our project activity and provides the test results of the fuzzy learning translational controller. This report is organized in six sections. Based on our experience and analysis with the attitude controller, we have modified the basic configuration of the reinforcement learning algorithm in ARIC as described in section 2. The shuttle translational controller and its implementation in fuzzy learning architecture is described in section 3. Two test cases that we have performed are described in section 4. Our results and conclusions are discussed in section 5, and section 6 provides future plans and summary for the project.
Learning and tuning fuzzy logic controllers through reinforcements

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.; Khedkar, Pratap

1992-01-01

This paper presents a new method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system. In particular, our generalized approximate reasoning-based intelligent control (GARIC) architecture (1) learns and tunes a fuzzy logic controller even when only weak reinforcement, such as a binary failure signal, is available; (2) introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; (3) introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and (4) learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward neural network, which can then adaptively improve performance by using gradient descent methods. We extend the AHC algorithm of Barto et al. (1983) to include the prior control knowledge of human operators. The GARIC architecture is applied to a cart-pole balancing system and demonstrates significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.
Optimization of neural network architecture using genetic programming improves detection and modeling of gene-gene interactions in studies of human diseases

PubMed Central

Ritchie, Marylyn D; White, Bill C; Parker, Joel S; Hahn, Lance W; Moore, Jason H

2003-01-01

Background Appropriate definition of neural network architecture prior to data analysis is crucial for successful data mining. This can be challenging when the underlying model of the data is unknown. The goal of this study was to determine whether optimizing neural network architecture using genetic programming as a machine learning strategy would improve the ability of neural networks to model and detect nonlinear interactions among genes in studies of common human diseases. Results Using simulated data, we show that a genetic programming optimized neural network approach is able to model gene-gene interactions as well as a traditional back propagation neural network. Furthermore, the genetic programming optimized neural network is better than the traditional back propagation neural network approach in terms of predictive ability and power to detect gene-gene interactions when non-functional polymorphisms are present. Conclusion This study suggests that a machine learning strategy for optimizing neural network architecture may be preferable to traditional trial-and-error approaches for the identification and characterization of gene-gene interactions in common, complex human diseases. PMID:12846935
Policy improvement by a model-free Dyna architecture.

PubMed

Hwang, Kao-Shing; Lo, Chia-Yue

2013-05-01

The objective of this paper is to accelerate the process of policy improvement in reinforcement learning. The proposed Dyna-style system combines two learning schemes, one of which utilizes a temporal difference method for direct learning; the other uses relative values for indirect learning in planning between two successive direct learning cycles. Instead of establishing a complicated world model, the approach introduces a simple predictor of average rewards to actor-critic architecture in the simulation (planning) mode. The relative value of a state, defined as the accumulated differences between immediate reward and average reward, is used to steer the improvement process in the right direction. The proposed learning scheme is applied to control a pendulum system for tracking a desired trajectory to demonstrate its adaptability and robustness. Through reinforcement signals from the environment, the system takes the appropriate action to drive an unknown dynamic to track desired outputs in few learning cycles. Comparisons are made between the proposed model-free method, a connectionist adaptive heuristic critic, and an advanced method of Dyna-Q learning in the experiments of labyrinth exploration. The proposed method outperforms its counterparts in terms of elapsed time and convergence rate.
A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses.

PubMed

Qiao, Ning; Mostafa, Hesham; Corradi, Federico; Osswald, Marc; Stefanini, Fabio; Sumislawska, Dora; Indiveri, Giacomo

2015-01-01

Implementing compact, low-power artificial neural processing systems with real-time on-line learning abilities is still an open challenge. In this paper we present a full-custom mixed-signal VLSI device with neuromorphic learning circuits that emulate the biophysics of real spiking neurons and dynamic synapses for exploring the properties of computational neuroscience models and for building brain-inspired computing systems. The proposed architecture allows the on-chip configuration of a wide range of network connectivities, including recurrent and deep networks, with short-term and long-term plasticity. The device comprises 128 K analog synapse and 256 neuron circuits with biologically plausible dynamics and bi-stable spike-based plasticity mechanisms that endow it with on-line learning abilities. In addition to the analog circuits, the device comprises also asynchronous digital logic circuits for setting different synapse and neuron properties as well as different network configurations. This prototype device, fabricated using a 180 nm 1P6M CMOS process, occupies an area of 51.4 mm(2), and consumes approximately 4 mW for typical experiments, for example involving attractor networks. Here we describe the details of the overall architecture and of the individual circuits and present experimental results that showcase its potential. By supporting a wide range of cortical-like computational modules comprising plasticity mechanisms, this device will enable the realization of intelligent autonomous systems with on-line learning capabilities.
An introduction to deep learning on biological sequence data: examples and solutions.

PubMed

Jurtz, Vanessa Isabell; Johansen, Alexander Rosenberg; Nielsen, Morten; Almagro Armenteros, Jose Juan; Nielsen, Henrik; Sønderby, Casper Kaae; Winther, Ole; Sønderby, Søren Kaae

2017-11-15

Deep neural network architectures such as convolutional and long short-term memory networks have become increasingly popular as machine learning tools during the recent years. The availability of greater computational resources, more data, new algorithms for training deep models and easy to use libraries for implementation and training of neural networks are the drivers of this development. The use of deep learning has been especially successful in image recognition; and the development of tools, applications and code examples are in most cases centered within this field rather than within biology. Here, we aim to further the development of deep learning methods within biology by providing application examples and ready to apply and adapt code templates. Given such examples, we illustrate how architectures consisting of convolutional and long short-term memory neural networks can relatively easily be designed and trained to state-of-the-art performance on three biological sequence problems: prediction of subcellular localization, protein secondary structure and the binding of peptides to MHC Class II molecules. All implementations and datasets are available online to the scientific community at https://github.com/vanessajurtz/lasagne4bio. skaaesonderby@gmail.com. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com
Diversity of devices along with diversity of data formats as a new challenge in global teaching and learning system

NASA Astrophysics Data System (ADS)

Sultana, Razia; Christ, Andreas; Meyrueis, Patrick

2014-07-01

The popularity of mobile communication devices is increasing day by day among students, especially for e-learning activities. "Always-ready-to-use" feature of mobile devices is a key motivation for students to use it even in a short break for a short time. This leads to new requirements regarding learning content presentation, user interfaces, and system architecture for heterogeneous devices. To support diverse devices is not enough to establish global teaching and learning system, it is equally important to support various formats of data along with different sort of devices having different capabilities in terms of processing power, display size, supported data formats, operating system, access method of data etc. Not only the existing data formats but also upcoming data formats, such as due to research results in the area of optics and photonics, virtual reality etc should be considered. This paper discusses the importance, risk and challenges of supporting heterogeneous devices to provide heterogeneous data as a learning content to make global teaching and learning system literally come true at anytime and anywhere. We proposed and implemented a sustainable architecture to support device and data format independent learning system.
A comparison of 1D and 2D LSTM architectures for the recognition of handwritten Arabic

NASA Astrophysics Data System (ADS)

Yousefi, Mohammad Reza; Soheili, Mohammad Reza; Breuel, Thomas M.; Stricker, Didier

2015-01-01

In this paper, we present an Arabic handwriting recognition method based on recurrent neural network. We use the Long Short Term Memory (LSTM) architecture, that have proven successful in different printed and handwritten OCR tasks. Applications of LSTM for handwriting recognition employ the two-dimensional architecture to deal with the variations in both vertical and horizontal axis. However, we show that using a simple pre-processing step that normalizes the position and baseline of letters, we can make use of 1D LSTM, which is faster in learning and convergence, and yet achieve superior performance. In a series of experiments on IFN/ENIT database for Arabic handwriting recognition, we demonstrate that our proposed pipeline can outperform 2D LSTM networks. Furthermore, we provide comparisons with 1D LSTM networks trained with manually crafted features to show that the automatically learned features in a globally trained 1D LSTM network with our normalization step can even outperform such systems.
An Energy-Efficient Multi-Tier Architecture for Fall Detection Using Smartphones.

PubMed

Guvensan, M Amac; Kansiz, A Oguz; Camgoz, N Cihan; Turkmen, H Irem; Yavuz, A Gokhan; Karsligil, M Elif

2017-06-23

Automatic detection of fall events is vital to providing fast medical assistance to the causality, particularly when the injury causes loss of consciousness. Optimization of the energy consumption of mobile applications, especially those which run 24/7 in the background, is essential for longer use of smartphones. In order to improve energy-efficiency without compromising on the fall detection performance, we propose a novel 3-tier architecture that combines simple thresholding methods with machine learning algorithms. The proposed method is implemented on a mobile application, called uSurvive, for Android smartphones. It runs as a background service and monitors the activities of a person in daily life and automatically sends a notification to the appropriate authorities and/or user defined contacts when it detects a fall. The performance of the proposed method was evaluated in terms of fall detection performance and energy consumption. Real life performance tests conducted on two different models of smartphone demonstrate that our 3-tier architecture with feature reduction could save up to 62% of energy compared to machine learning only solutions. In addition to this energy saving, the hybrid method has a 93% of accuracy, which is superior to thresholding methods and better than machine learning only solutions.

Industrial Landscapes: Perception and Classification as Learning Activities

ERIC Educational Resources Information Center

Peters, Gary; Larkin, Robert P.

1977-01-01

Suggests a high school or college level program of subjective perception and evaluation of industrial landscapes. Slides of local or national industrial sites can be rated and classified as pleasing or unpleasing in terms of variables such as architectural style of building, smokestacks, age, and visible pollution. (AV)
Investigating Architectural Issues in Neuromorphic Computing

DTIC Science & Technology

2012-05-01

term grasp. Some of these include learning, vision , audition and olfaction , ability to navigate an environment, and goal seeking. These abilities have...17 Figure 14: Word/sentence level accuracy versus the ambiguity: (a) Word accuracy vs . letter ambiguity, (b) (b) Sentence...accuracy vs . letter ambiguity, and (c) (b) Sentence accuracy vs . word ambiguity
Evaluation of a deep learning architecture for MR imaging prediction of ATRX in glioma patients

NASA Astrophysics Data System (ADS)

Korfiatis, Panagiotis; Kline, Timothy L.; Erickson, Bradley J.

2018-02-01

Predicting mutation/loss of alpha-thalassemia/mental retardation syndrome X-linked (ATRX) gene utilizing MR imaging is of high importance since it is a predictor of response and prognosis in brain tumors. In this study, we compare a deep neural network approach based on a residual deep neural network (ResNet) architecture and one based on a classical machine learning approach and evaluate their ability in predicting ATRX mutation status without the need for a distinct tumor segmentation step. We found that the ResNet50 (50 layers) architecture, pre trained on ImageNet data was the best performing model, achieving an accuracy of 0.91 for the test set (classification of a slice as no tumor, ATRX mutated, or mutated) in terms of f1 score in a test set of 35 cases. The SVM classifier achieved 0.63 for differentiating the Flair signal abnormality regions from the test patients based on their mutation status. We report a method that alleviates the need for extensive preprocessing and acts as a proof of concept that deep neural network architectures can be used to predict molecular biomarkers from routine medical images.
A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses

PubMed Central

Qiao, Ning; Mostafa, Hesham; Corradi, Federico; Osswald, Marc; Stefanini, Fabio; Sumislawska, Dora; Indiveri, Giacomo

2015-01-01

Implementing compact, low-power artificial neural processing systems with real-time on-line learning abilities is still an open challenge. In this paper we present a full-custom mixed-signal VLSI device with neuromorphic learning circuits that emulate the biophysics of real spiking neurons and dynamic synapses for exploring the properties of computational neuroscience models and for building brain-inspired computing systems. The proposed architecture allows the on-chip configuration of a wide range of network connectivities, including recurrent and deep networks, with short-term and long-term plasticity. The device comprises 128 K analog synapse and 256 neuron circuits with biologically plausible dynamics and bi-stable spike-based plasticity mechanisms that endow it with on-line learning abilities. In addition to the analog circuits, the device comprises also asynchronous digital logic circuits for setting different synapse and neuron properties as well as different network configurations. This prototype device, fabricated using a 180 nm 1P6M CMOS process, occupies an area of 51.4 mm2, and consumes approximately 4 mW for typical experiments, for example involving attractor networks. Here we describe the details of the overall architecture and of the individual circuits and present experimental results that showcase its potential. By supporting a wide range of cortical-like computational modules comprising plasticity mechanisms, this device will enable the realization of intelligent autonomous systems with on-line learning capabilities. PMID:25972778
A conceptual cognitive architecture for robots to learn behaviors from demonstrations in robotic aid area.

PubMed

Tan, Huan; Liang, Chen

2011-01-01

This paper proposes a conceptual hybrid cognitive architecture for cognitive robots to learn behaviors from demonstrations in robotic aid situations. Unlike the current cognitive architectures, this architecture puts concentration on the requirements of the safety, the interaction, and the non-centralized processing in robotic aid situations. Imitation learning technologies for cognitive robots have been integrated into this architecture for rapidly transferring the knowledge and skills between human teachers and robots.
An architecture for an autonomous learning robot

NASA Technical Reports Server (NTRS)

Tillotson, Brian

1988-01-01

An autonomous learning device must solve the example bounding problem, i.e., it must divide the continuous universe into discrete examples from which to learn. We describe an architecture which incorporates an example bounder for learning. The architecture is implemented in the GPAL program. An example run with a real mobile robot shows that the program learns and uses new causal, qualitative, and quantitative relationships.
Segmented-memory recurrent neural networks.

PubMed

Chen, Jinmiao; Chaudhari, Narendra S

2009-08-01

Conventional recurrent neural networks (RNNs) have difficulties in learning long-term dependencies. To tackle this problem, we propose an architecture called segmented-memory recurrent neural network (SMRNN). A symbolic sequence is broken into segments and then presented as inputs to the SMRNN one symbol per cycle. The SMRNN uses separate internal states to store symbol-level context, as well as segment-level context. The symbol-level context is updated for each symbol presented for input. The segment-level context is updated after each segment. The SMRNN is trained using an extended real-time recurrent learning algorithm. We test the performance of SMRNN on the information latching problem, the "two-sequence problem" and the problem of protein secondary structure (PSS) prediction. Our implementation results indicate that SMRNN performs better on long-term dependency problems than conventional RNNs. Besides, we also theoretically analyze how the segmented memory of SMRNN helps learning long-term temporal dependencies and study the impact of the segment length.
A generalized LSTM-like training algorithm for second-order recurrent neural networks

PubMed Central

Monner, Derek; Reggia, James A.

2011-01-01

The Long Short Term Memory (LSTM) is a second-order recurrent neural network architecture that excels at storing sequential short-term memories and retrieving them many time-steps later. LSTM’s original training algorithm provides the important properties of spatial and temporal locality, which are missing from other training approaches, at the cost of limiting it’s applicability to a small set of network architectures. Here we introduce the Generalized Long Short-Term Memory (LSTM-g) training algorithm, which provides LSTM-like locality while being applicable without modification to a much wider range of second-order network architectures. With LSTM-g, all units have an identical set of operating instructions for both activation and learning, subject only to the configuration of their local environment in the network; this is in contrast to the original LSTM training algorithm, where each type of unit has its own activation and training instructions. When applied to LSTM architectures with peephole connections, LSTM-g takes advantage of an additional source of back-propagated error which can enable better performance than the original algorithm. Enabled by the broad architectural applicability of LSTM-g, we demonstrate that training recurrent networks engineered for specific tasks can produce better results than single-layer networks. We conclude that LSTM-g has the potential to both improve the performance and broaden the applicability of spatially and temporally local gradient-based training algorithms for recurrent neural networks. PMID:21803542
Lifelong learning of human actions with deep neural network self-organization.

PubMed

Parisi, German I; Tani, Jun; Weber, Cornelius; Wermter, Stefan

2017-12-01

Lifelong learning is fundamental in autonomous robotics for the acquisition and fine-tuning of knowledge through experience. However, conventional deep neural models for action recognition from videos do not account for lifelong learning but rather learn a batch of training data with a predefined number of action classes and samples. Thus, there is the need to develop learning systems with the ability to incrementally process available perceptual cues and to adapt their responses over time. We propose a self-organizing neural architecture for incrementally learning to classify human actions from video sequences. The architecture comprises growing self-organizing networks equipped with recurrent neurons for processing time-varying patterns. We use a set of hierarchically arranged recurrent networks for the unsupervised learning of action representations with increasingly large spatiotemporal receptive fields. Lifelong learning is achieved in terms of prediction-driven neural dynamics in which the growth and the adaptation of the recurrent networks are driven by their capability to reconstruct temporally ordered input sequences. Experimental results on a classification task using two action benchmark datasets show that our model is competitive with state-of-the-art methods for batch learning also when a significant number of sample labels are missing or corrupted during training sessions. Additional experiments show the ability of our model to adapt to non-stationary input avoiding catastrophic interference. Copyright © 2017 The Author(s). Published by Elsevier Ltd.. All rights reserved.
Cognitive Architectures for Multimedia Learning

ERIC Educational Resources Information Center

Reed, Stephen K.

2006-01-01

This article provides a tutorial overview of cognitive architectures that can form a theoretical foundation for designing multimedia instruction. Cognitive architectures include a description of memory stores, memory codes, and cognitive operations. Architectures that are relevant to multimedia learning include Paivio's dual coding theory,…
Visual Information Literacy: Reading a Documentary Photograph

ERIC Educational Resources Information Center

Abilock, Debbie

2008-01-01

Like a printed text, an architectural blueprint, a mathematical equation, or a musical score, a visual image is its own language. Visual literacy has three components: (1) learning; (2) thinking; and (3) communicating. A "literate" person is able to decipher the basic code and syntax, interpret the signs and symbols, correctly apply terms from an…
ARCHITECTURE AS PEDAGOGY: INTERDISCIPLINARY DESIGN AND CREATION OF A CARBON NEUTRAL IDAHO ENVIRONMENTAL LEARNING CENTER AT THE UNIVERSITY OF IDAHO MCCALL FIELD CAMPUS

EPA Science Inventory

Output 1. (short-term) Design a carbon neutral field campus with the following design components: structural systems, building envelope, environmental systems, site construction, building materials, information technology, spatial systems and integration ...

PROFILES OF SIGNIFICANT SCHOOLS--HEATHCOTE ELEMENTARY SCHOOL, SCARSDALE, NEW YORK.

ERIC Educational Resources Information Center

WEINSTOCK, RUTH

THE DESIGN OF THE HEATHCOTE ELEMENTARY SCHOOL WAS INVESTIGATED IN TERMS OF THE SCHOOL'S EDUCATIONAL PROGRAM, ARCHITECTURAL INNOVATIONS IN DESIGN, AND SPECIAL FEATURES OF INTEREST. THE PLANNERS OF HEATHCOTE WERE COMMITTED TO TWO FUNDAMENTAL PRINCIPLES OF EDUCATION--ONE DEALING WITH THE CONDITIONS UNDER WHICH CHILDREN LEARN BEST, THE OTHER DEALING…

Neural Classifiers for Learning Higher-Order Correlations

NASA Astrophysics Data System (ADS)

Güler, Marifi

1999-01-01

Studies by various authors suggest that higher-order networks can be more powerful and are biologically more plausible with respect to the more traditional multilayer networks. These architectures make explicit use of nonlinear interactions between input variables in the form of higher-order units or product units. If it is known a priori that the problem to be implemented possesses a given set of invariances like in the translation, rotation, and scale invariant pattern recognition problems, those invariances can be encoded, thus eliminating all higher-order terms which are incompatible with the invariances. In general, however, it is a serious set-back that the complexity of learning increases exponentially with the size of inputs. This paper reviews higher-order networks and introduces an implicit representation in which learning complexity is mainly decided by the number of higher-order terms to be learned and increases only linearly with the input size.

Cluster: Drafting. Course: Architectural Drafting. Research Project.

ERIC Educational Resources Information Center

Sanford - Lee County Schools, NC.

The sequence of 10 units is designed for use with an instructor in architectural drafting, and is also keyed to other texts. Each unit contains several task packages specifying prerequisites, rationale for learning, objectives, learning activities to be supervised by the instructor, and learning practice. The units cover: architectural lettering…

Efficient k-Winner-Take-All Competitive Learning Hardware Architecture for On-Chip Learning

PubMed Central

Ou, Chien-Min; Li, Hui-Ya; Hwang, Wen-Jyi

2012-01-01

A novel k-winners-take-all (k-WTA) competitive learning (CL) hardware architecture is presented for on-chip learning in this paper. The architecture is based on an efficient pipeline allowing k-WTA competition processes associated with different training vectors to be performed concurrently. The pipeline architecture employs a novel codeword swapping scheme so that neurons failing the competition for a training vector are immediately available for the competitions for the subsequent training vectors. The architecture is implemented by the field programmable gate array (FPGA). It is used as a hardware accelerator in a system on programmable chip (SOPC) for realtime on-chip learning. Experimental results show that the SOPC has significantly lower training time than that of other k-WTA CL counterparts operating with or without hardware support.

An attention-gating recurrent working memory architecture for emergent speech representation

NASA Astrophysics Data System (ADS)

Elshaw, Mark; Moore, Roger K.; Klein, Michael

2010-06-01

This paper describes an attention-gating recurrent self-organising map approach for emergent speech representation. Inspired by evidence from human cognitive processing, the architecture combines two main neural components. The first component, the attention-gating mechanism, uses actor-critic learning to perform selective attention towards speech. Through this selective attention approach, the attention-gating mechanism controls access to working memory processing. The second component, the recurrent self-organising map memory, develops a temporal-distributed representation of speech using phone-like structures. Representing speech in terms of phonetic features in an emergent self-organised fashion, according to research on child cognitive development, recreates the approach found in infants. Using this representational approach, in a fashion similar to infants, should improve the performance of automatic recognition systems through aiding speech segmentation and fast word learning.

An Energy-Efficient Multi-Tier Architecture for Fall Detection on Smartphones

PubMed Central

Guvensan, M. Amac; Kansiz, A. Oguz; Camgoz, N. Cihan; Turkmen, H. Irem; Yavuz, A. Gokhan; Karsligil, M. Elif

2017-01-01

Automatic detection of fall events is vital to providing fast medical assistance to the causality, particularly when the injury causes loss of consciousness. Optimization of the energy consumption of mobile applications, especially those which run 24/7 in the background, is essential for longer use of smartphones. In order to improve energy-efficiency without compromising on the fall detection performance, we propose a novel 3-tier architecture that combines simple thresholding methods with machine learning algorithms. The proposed method is implemented on a mobile application, called uSurvive, for Android smartphones. It runs as a background service and monitors the activities of a person in daily life and automatically sends a notification to the appropriate authorities and/or user defined contacts when it detects a fall. The performance of the proposed method was evaluated in terms of fall detection performance and energy consumption. Real life performance tests conducted on two different models of smartphone demonstrate that our 3-tier architecture with feature reduction could save up to 62% of energy compared to machine learning only solutions. In addition to this energy saving, the hybrid method has a 93% of accuracy, which is superior to thresholding methods and better than machine learning only solutions. PMID:28644378

Architectural Design of a LMS with LTSA-Conformance

ERIC Educational Resources Information Center

Sengupta, Souvik; Dasgupta, Ranjan

2017-01-01

This paper illustrates an approach for architectural design of a Learning Management System (LMS), which is verifiable against the Learning Technology System Architecture (LTSA) conformance rules. We introduce a new method for software architectural design that extends the Unified Modeling Language (UML) component diagram with the formal…

A Novel Architecture for E-Learning Knowledge Assessment Systems

ERIC Educational Resources Information Center

Gierlowski, Krzysztof; Nowicki, Krzysztof

2009-01-01

In this article we propose a novel e-learning system, dedicated strictly to knowledge assessment tasks. In its functioning it utilizes web-based technologies, but its design differs radically from currently popular e-learning solutions which rely mostly on thin-client architecture. Our research proved that such architecture, while well suited for…

«

1

2

3

4

5

»

«

2

3

4

5

6

»

A Concept Transformation Learning Model for Architectural Design Learning Process

ERIC Educational Resources Information Center

Wu, Yun-Wu; Weng, Kuo-Hua; Young, Li-Ming

2016-01-01

Generally, in the foundation course of architectural design, much emphasis is placed on teaching of the basic design skills without focusing on teaching students to apply the basic design concepts in their architectural designs or promoting students' own creativity. Therefore, this study aims to propose a concept transformation learning model to…

The TENOR Architecture for Advanced Distributed Learning and Intelligent Training

DTIC Science & Technology

2002-01-01

called TENOR, for Training Education Network on Request. There have been a number of recent learning systems developed that leverage off Internet...AG2-14256 AIAA 2002-1054 The TENOR Architecture for Advanced Distributed Learning and Intelligent Training C. Tibaudo, J. Kristl and J. Schroeder...COVERED 4. TITLE AND SUBTITLE The TENOR Architecture for Advanced Distributed Learning and Intelligent Training 5a. CONTRACT NUMBER F33615-00-M

A Neuromorphic Architecture for Object Recognition and Motion Anticipation Using Burst-STDP

PubMed Central

Balduzzi, David; Tononi, Giulio

2012-01-01

In this work we investigate the possibilities offered by a minimal framework of artificial spiking neurons to be deployed in silico. Here we introduce a hierarchical network architecture of spiking neurons which learns to recognize moving objects in a visual environment and determine the correct motor output for each object. These tasks are learned through both supervised and unsupervised spike timing dependent plasticity (STDP). STDP is responsible for the strengthening (or weakening) of synapses in relation to pre- and post-synaptic spike times and has been described as a Hebbian paradigm taking place both in vitro and in vivo. We utilize a variation of STDP learning, called burst-STDP, which is based on the notion that, since spikes are expensive in terms of energy consumption, then strong bursting activity carries more information than single (sparse) spikes. Furthermore, this learning algorithm takes advantage of homeostatic renormalization, which has been hypothesized to promote memory consolidation during NREM sleep. Using this learning rule, we design a spiking neural network architecture capable of object recognition, motion detection, attention towards important objects, and motor control outputs. We demonstrate the abilities of our design in a simple environment with distractor objects, multiple objects moving concurrently, and in the presence of noise. Most importantly, we show how this neural network is capable of performing these tasks using a simple leaky-integrate-and-fire (LIF) neuron model with binary synapses, making it fully compatible with state-of-the-art digital neuromorphic hardware designs. As such, the building blocks and learning rules presented in this paper appear promising for scalable fully neuromorphic systems to be implemented in hardware chips. PMID:22615855

PELS: A Noble Architecture and Framework for a Personal E-Learning System (PELS)

ERIC Educational Resources Information Center

Dewan, Jahangir; Chowdhury, Morshed; Batten, Lynn

2014-01-01

This article presents a personal e-learning system architecture in the context of a social network environment. The main objective of a personal e-learning system is to develop individual skills on a specific subject and share resources with peers. The authors' system architecture defines the organisation and management of a personal learning…

Creating a New Architecture for the Learning College

ERIC Educational Resources Information Center

O'Banion, Terry

2007-01-01

The publication of "A Nation at Risk" in 1983 triggered a series of major reform efforts in education that are still evolving. As part of the reform efforts, leaders began to refer to a Learning Revolution that would "place learning first by overhauling the traditional architecture of education." The old architecture--time-bound, place-bound,…

LTSA Conformance Testing to Architectural Design of LMS Using Ontology

ERIC Educational Resources Information Center

Sengupta, Souvik; Dasgupta, Ranjan

2017-01-01

This paper proposes a new methodology for checking conformance of the software architectural design of Learning Management System (LMS) to Learning Technology System Architecture (LTSA). In our approach, the architectural designing of LMS follows the formal modeling style of Acme. An ontology is built to represent the LTSA rules and the software…

Component-Based Approach in Learning Management System Development

ERIC Educational Resources Information Center

Zaitseva, Larisa; Bule, Jekaterina; Makarov, Sergey

2013-01-01

The paper describes component-based approach (CBA) for learning management system development. Learning object as components of e-learning courses and their metadata is considered. The architecture of learning management system based on CBA being developed in Riga Technical University, namely its architecture, elements and possibilities are…

A Case Study of Learning Architecture and Reciprocity

ERIC Educational Resources Information Center

Smith, Anne B.

2009-01-01

This ethnographic case study follows the trajectory of one child's learning disposition, reciprocity, and its relationship to the "learning architecture" of her early childhood and primary school learning environments, over eighteen months. Learning dispositions are coping strategies or habits of mind, and tendencies to respond to and select from…

A novel approach to locomotion learning: Actor-Critic architecture using central pattern generators and dynamic motor primitives.

PubMed

Li, Cai; Lowe, Robert; Ziemke, Tom

2014-01-01

In this article, we propose an architecture of a bio-inspired controller that addresses the problem of learning different locomotion gaits for different robot morphologies. The modeling objective is split into two: baseline motion modeling and dynamics adaptation. Baseline motion modeling aims to achieve fundamental functions of a certain type of locomotion and dynamics adaptation provides a "reshaping" function for adapting the baseline motion to desired motion. Based on this assumption, a three-layer architecture is developed using central pattern generators (CPGs, a bio-inspired locomotor center for the baseline motion) and dynamic motor primitives (DMPs, a model with universal "reshaping" functions). In this article, we use this architecture with the actor-critic algorithms for finding a good "reshaping" function. In order to demonstrate the learning power of the actor-critic based architecture, we tested it on two experiments: (1) learning to crawl on a humanoid and, (2) learning to gallop on a puppy robot. Two types of actor-critic algorithms (policy search and policy gradient) are compared in order to evaluate the advantages and disadvantages of different actor-critic based learning algorithms for different morphologies. Finally, based on the analysis of the experimental results, a generic view/architecture for locomotion learning is discussed in the conclusion.

A novel approach to locomotion learning: Actor-Critic architecture using central pattern generators and dynamic motor primitives

PubMed Central

Li, Cai; Lowe, Robert; Ziemke, Tom

2014-01-01

In this article, we propose an architecture of a bio-inspired controller that addresses the problem of learning different locomotion gaits for different robot morphologies. The modeling objective is split into two: baseline motion modeling and dynamics adaptation. Baseline motion modeling aims to achieve fundamental functions of a certain type of locomotion and dynamics adaptation provides a “reshaping” function for adapting the baseline motion to desired motion. Based on this assumption, a three-layer architecture is developed using central pattern generators (CPGs, a bio-inspired locomotor center for the baseline motion) and dynamic motor primitives (DMPs, a model with universal “reshaping” functions). In this article, we use this architecture with the actor-critic algorithms for finding a good “reshaping” function. In order to demonstrate the learning power of the actor-critic based architecture, we tested it on two experiments: (1) learning to crawl on a humanoid and, (2) learning to gallop on a puppy robot. Two types of actor-critic algorithms (policy search and policy gradient) are compared in order to evaluate the advantages and disadvantages of different actor-critic based learning algorithms for different morphologies. Finally, based on the analysis of the experimental results, a generic view/architecture for locomotion learning is discussed in the conclusion. PMID:25324773

Multimedia And Internetworking Architecture Infrastructure On Interactive E-Learning System

NASA Astrophysics Data System (ADS)

Indah, K. A. T.; Sukarata, G.

2018-01-01

Interactive e-learning is a distance learning method that involves information technology, electronic system or computer as one means of learning system used for teaching and learning process that is implemented without having face to face directly between teacher and student. A strong dependence on emerging technologies greatly influences the way in which the architecture is designed to produce a powerful interactive e-learning network. In this paper analyzed an architecture model where learning can be done interactively, involving many participants (N-way synchronized distance learning) using video conferencing technology. Also used broadband internet network as well as multicast techniques as a troubleshooting method for bandwidth usage can be efficient.

Learning Efficient Sparse and Low Rank Models.

PubMed

Sprechmann, P; Bronstein, A M; Sapiro, G

2015-09-01

Parsimony, including sparsity and low rank, has been shown to successfully model data in numerous machine learning and signal processing tasks. Traditionally, such modeling approaches rely on an iterative algorithm that minimizes an objective function with parsimony-promoting terms. The inherently sequential structure and data-dependent complexity and latency of iterative optimization constitute a major limitation in many applications requiring real-time performance or involving large-scale data. Another limitation encountered by these modeling techniques is the difficulty of their inclusion in discriminative learning scenarios. In this work, we propose to move the emphasis from the model to the pursuit algorithm, and develop a process-centric view of parsimonious modeling, in which a learned deterministic fixed-complexity pursuit process is used in lieu of iterative optimization. We show a principled way to construct learnable pursuit process architectures for structured sparse and robust low rank models, derived from the iteration of proximal descent algorithms. These architectures learn to approximate the exact parsimonious representation at a fraction of the complexity of the standard optimization methods. We also show that appropriate training regimes allow to naturally extend parsimonious models to discriminative settings. State-of-the-art results are demonstrated on several challenging problems in image and audio processing with several orders of magnitude speed-up compared to the exact optimization algorithms.

An Evolutionary Upgrade of Cognitive Load Theory: Using the Human Motor System and Collaboration to Support the Learning of Complex Cognitive Tasks

ERIC Educational Resources Information Center

Paas, Fred; Sweller, John

2012-01-01

Cognitive load theory is intended to provide instructional strategies derived from experimental, cognitive load effects. Each effect is based on our knowledge of human cognitive architecture, primarily the limited capacity and duration of a human working memory. These limitations are ameliorated by changes in long-term memory associated with…

Internet Architecture: Lessons Learned and Looking Forward

DTIC Science & Technology

2006-12-01

Internet Architecture: Lessons Learned and Looking Forward Geoffrey G. Xie Department of Computer Science Naval Postgraduate School April 2006... Internet architecture. Report Documentation Page Form ApprovedOMB No. 0704-0188 Public reporting burden for the collection of information is...readers are referred there for more information about a specific protocol or concept. 2. Origin of Internet Architecture The Internet is easily

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.

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.

Inclusive design in architectural practice: Experiential learning of disability in architectural education.

PubMed

Mulligan, Kerry; Calder, Allyson; Mulligan, Hilda

2018-04-01

The built environment can facilitate or impede an individual's ability to participate in society. This is particularly so for people with disability. Architects are well placed to be advocates for design that enhances societal equality. This qualitative study explored architectural design students' perceptions of inclusive design, their reflections resulting from an experiential learning module and the subsequent influence of these on their design practice. Twenty four architectural design students participated in focus groups or individual interviews. Data were analyzed thematically. Three themes were evident: 1) Inclusive design was perceived as challenging, 2) Appreciation for the opportunity to learn about the perspectives of people with disabilities, and 3) Change of attitude toward inclusive design. Experiential learning had fostered reflection, changes in attitude and the realization that inclusive design, should begin at the start of the design process. For equitable access for all people to become reality, experiential learning, coupled with positive examples of inclusive design should be embedded in architectural education. Copyright © 2017 Elsevier Inc. All rights reserved.

Architectural and Functional Design and Evaluation of E-Learning VUIS Based on the Proposed IEEE LTSA Reference Model.

ERIC Educational Resources Information Center

O'Droma, Mairtin S.; Ganchev, Ivan; McDonnell, Fergal

2003-01-01

Presents a comparative analysis from the Institute of Electrical and Electronics Engineers (IEEE) Learning Technology Standards Committee's (LTSC) of the architectural and functional design of e-learning delivery platforms and applications, e-learning course authoring tools, and learning management systems (LMSs), with a view of assessing how…

Proposing an Optimal Learning Architecture for the Digital Enterprise.

ERIC Educational Resources Information Center

O'Driscoll, Tony

2003-01-01

Discusses the strategic role of learning in information age organizations; analyzes parallels between the application of technology to business and the application of technology to learning; and proposes a learning architecture that aligns with the knowledge-based view of the firm and optimizes the application of technology to achieve proficiency…

Virtual Workshop Environment (VWE): A Taxonomy and Service Oriented Architecture (SOA) Framework for Modularized Virtual Learning Environments (VLE)--Applying the Learning Object Concept to the VLE

ERIC Educational Resources Information Center

Paulsson, Fredrik; Naeve, Ambjorn

2006-01-01

Based on existing Learning Object taxonomies, this article suggests an alternative Learning Object taxonomy, combined with a general Service Oriented Architecture (SOA) framework, aiming to transfer the modularized concept of Learning Objects to modularized Virtual Learning Environments. The taxonomy and SOA-framework exposes a need for a clearer…

«

2

3

4

5

6

»

«

3

4

5

6

7

»

Combining Digital Archives Content with Serious Game Approach to Create a Gamified Learning Experience

NASA Astrophysics Data System (ADS)

Shih, D.-T.; Lin, C. L.; Tseng, C.-Y.

2015-08-01

This paper presents an interdisciplinary to develop content-aware application that combines game with learning on specific categories of digital archives. The employment of content-oriented game enhances the gamification and efficacy of learning in culture education on architectures and history of Hsinchu County, Taiwan. The gamified form of the application is used as a backbone to support and provide a strong stimulation to engage users in learning art and culture, therefore this research is implementing under the goal of "The Digital ARt/ARchitecture Project". The purpose of the abovementioned project is to develop interactive serious game approaches and applications for Hsinchu County historical archives and architectures. Therefore, we present two applications, "3D AR for Hukou Old " and "Hsinchu County History Museum AR Tour" which are in form of augmented reality (AR). By using AR imaging techniques to blend real object and virtual content, the users can immerse in virtual exhibitions of Hukou Old Street and Hsinchu County History Museum, and to learn in ubiquitous computing environment. This paper proposes a content system that includes tools and materials used to create representations of digitized cultural archives including historical artifacts, documents, customs, religion, and architectures. The Digital ARt / ARchitecture Project is based on the concept of serious game and consists of three aspects: content creation, target management, and AR presentation. The project focuses on developing a proper approach to serve as an interactive game, and to offer a learning opportunity for appreciating historic architectures by playing AR cards. Furthermore, the card game aims to provide multi-faceted understanding and learning experience to help user learning through 3D objects, hyperlinked web data, and the manipulation of learning mode, and then effectively developing their learning levels on cultural and historical archives in Hsinchu County.

Architecture for Implementation of a Lifelong Online Learning Environment (LOLE)

ERIC Educational Resources Information Center

Caron, Philippe; Beaudoin, Gregg; Leblanc, Frederic; Grant, Andrew

2007-01-01

This article describes an architecture for the implementation of a lifelong online learning environment (LOLE). The stakeholder independent architecture enables the development of a LOLE system to fulfill the complex requirements of the different actors involved in lifelong education. A particular emphasis is placed on the continuation of a…

Semantic Web-Driven LMS Architecture towards a Holistic Learning Process Model Focused on Personalization

ERIC Educational Resources Information Center

Kerkiri, Tania

2010-01-01

A comprehensive presentation is here made on the modular architecture of an e-learning platform with a distinctive emphasis on content personalization, combining advantages from semantic web technology, collaborative filtering and recommendation systems. Modules of this architecture handle information about both the domain-specific didactic…

Prediction of brain maturity in infants using machine-learning algorithms.

PubMed

Smyser, Christopher D; Dosenbach, Nico U F; Smyser, Tara A; Snyder, Abraham Z; Rogers, Cynthia E; Inder, Terrie E; Schlaggar, Bradley L; Neil, Jeffrey J

2016-08-01

Recent resting-state functional MRI investigations have demonstrated that much of the large-scale functional network architecture supporting motor, sensory and cognitive functions in older pediatric and adult populations is present in term- and prematurely-born infants. Application of new analytical approaches can help translate the improved understanding of early functional connectivity provided through these studies into predictive models of neurodevelopmental outcome. One approach to achieving this goal is multivariate pattern analysis, a machine-learning, pattern classification approach well-suited for high-dimensional neuroimaging data. It has previously been adapted to predict brain maturity in children and adolescents using structural and resting state-functional MRI data. In this study, we evaluated resting state-functional MRI data from 50 preterm-born infants (born at 23-29weeks of gestation and without moderate-severe brain injury) scanned at term equivalent postmenstrual age compared with data from 50 term-born control infants studied within the first week of life. Using 214 regions of interest, binary support vector machines distinguished term from preterm infants with 84% accuracy (p<0.0001). Inter- and intra-hemispheric connections throughout the brain were important for group categorization, indicating that widespread changes in the brain's functional network architecture associated with preterm birth are detectable by term equivalent age. Support vector regression enabled quantitative estimation of birth gestational age in single subjects using only term equivalent resting state-functional MRI data, indicating that the present approach is sensitive to the degree of disruption of brain development associated with preterm birth (using gestational age as a surrogate for the extent of disruption). This suggests that support vector regression may provide a means for predicting neurodevelopmental outcome in individual infants. Copyright © 2016 Elsevier Inc. All rights reserved.

Prediction of brain maturity in infants using machine-learning algorithms

PubMed Central

Smyser, Christopher D.; Dosenbach, Nico U.F.; Smyser, Tara A.; Snyder, Abraham Z.; Rogers, Cynthia E.; Inder, Terrie E.; Schlaggar, Bradley L.; Neil, Jeffrey J.

2016-01-01

Recent resting-state functional MRI investigations have demonstrated that much of the large-scale functional network architecture supporting motor, sensory and cognitive functions in older pediatric and adult populations is present in term- and prematurely-born infants. Application of new analytical approaches can help translate the improved understanding of early functional connectivity provided through these studies into predictive models of neurodevelopmental outcome. One approach to achieving this goal is multivariate pattern analysis, a machine-learning, pattern classification approach well-suited for high-dimensional neuroimaging data. It has previously been adapted to predict brain maturity in children and adolescents using structural and resting state-functional MRI data. In this study, we evaluated resting state-functional MRI data from 50 preterm-born infants (born at 23–29 weeks of gestation and without moderate–severe brain injury) scanned at term equivalent postmenstrual age compared with data from 50 term-born control infants studied within the first week of life. Using 214 regions of interest, binary support vector machines distinguished term from preterm infants with 84% accuracy (p < 0.0001). Inter- and intra-hemispheric connections throughout the brain were important for group categorization, indicating that widespread changes in the brain's functional network architecture associated with preterm birth are detectable by term equivalent age. Support vector regression enabled quantitative estimation of birth gestational age in single subjects using only term equivalent resting state-functional MRI data, indicating that the present approach is sensitive to the degree of disruption of brain development associated with preterm birth (using gestational age as a surrogate for the extent of disruption). This suggests that support vector regression may provide a means for predicting neurodevelopmental outcome in individual infants. PMID:27179605

Design, Analysis and User Acceptance of Architectural Design Education in Learning System Based on Knowledge Management Theory

ERIC Educational Resources Information Center

Wu, Yun-Wu; Lin, Yu-An; Wen, Ming-Hui; Perng, Yeng-Hong; Hsu, I-Ting

2016-01-01

The major purpose of this study is to develop an architectural design knowledge management learning system with corresponding learning activities to help the students have meaningful learning and improve their design capability in their learning process. Firstly, the system can help the students to obtain and share useful knowledge. Secondly,…

Lifelong Learning in Architectural Design Studio: The Learning Contract Approach

ERIC Educational Resources Information Center

Hassanpour, B.; Che-Ani, A. I.; Usman, I. M. S.; Johar, S.; Tawil, N. M.

2015-01-01

Avant-garde educational systems are striving to find lifelong learning methods. Different fields and majors have tested a variety of proposed models and found varying difficulties and strengths. Architecture is one of the most critical areas of education because of its special characteristics, such as learning by doing and complicated evaluation…

An Integration Architecture of Virtual Campuses with External e-Learning Tools

ERIC Educational Resources Information Center

Navarro, Antonio; Cigarran, Juan; Huertas, Francisco; Rodriguez-Artacho, Miguel; Cogolludo, Alberto

2014-01-01

Technology enhanced learning relies on a variety of software architectures and platforms to provide different kinds of management service and enhanced instructional interaction. As e-learning support has become more complex, there is a need for virtual campuses that combine learning management systems with the services demanded by educational…

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks

PubMed Central

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-01-01

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction. PMID:28672867

Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks.

PubMed

Yu, Haiyang; Wu, Zhihai; Wang, Shuqin; Wang, Yunpeng; Ma, Xiaolei

2017-06-26

Predicting large-scale transportation network traffic has become an important and challenging topic in recent decades. Inspired by the domain knowledge of motion prediction, in which the future motion of an object can be predicted based on previous scenes, we propose a network grid representation method that can retain the fine-scale structure of a transportation network. Network-wide traffic speeds are converted into a series of static images and input into a novel deep architecture, namely, spatiotemporal recurrent convolutional networks (SRCNs), for traffic forecasting. The proposed SRCNs inherit the advantages of deep convolutional neural networks (DCNNs) and long short-term memory (LSTM) neural networks. The spatial dependencies of network-wide traffic can be captured by DCNNs, and the temporal dynamics can be learned by LSTMs. An experiment on a Beijing transportation network with 278 links demonstrates that SRCNs outperform other deep learning-based algorithms in both short-term and long-term traffic prediction.

Learning from external environments using Soar

NASA Technical Reports Server (NTRS)

Laird, John E.

1989-01-01

Soar, like the previous PRODIGY and Theo, is a problem-solving architecture that attempts to learn from experience; unlike them, it takes a more uniform approach, using a single forward-chaining architecture for planning and execution. Its single learning mechanism, designated 'chunking', is domain-independent. Two developmental approaches have been employed with Soar: the first of these allows the architecture to attempt a problem on its own, while the second involves a degree of external guidance. This learning through guidance is integrated with general problem-solving and autonomous learning, leading to an avoidance of human interaction for simple problems that Soar can solve on its own.

A Blended Learning Approach to the Teaching of Professional Practice in Architecture

ERIC Educational Resources Information Center

Lane, Murray; Osborne, Lindy; Crowther, Philip

2015-01-01

This paper reports on a number of blended learning activities conducted in two subjects of a Master of Architecture degree at a major Australian university. The subjects were related to "professional practice" and as such represent a little researched area of architectural curriculum. The research provides some insight into the student…

A Mobile Service Oriented Multiple Object Tracking Augmented Reality Architecture for Education and Learning Experiences

ERIC Educational Resources Information Center

Rattanarungrot, Sasithorn; White, Martin; Newbury, Paul

2014-01-01

This paper describes the design of our service-oriented architecture to support mobile multiple object tracking augmented reality applications applied to education and learning scenarios. The architecture is composed of a mobile multiple object tracking augmented reality client, a web service framework, and dynamic content providers. Tracking of…

Promoting Adult Learning in Public Places: Two Asian Case Studies of Adult Learning about Peace through Museums and Peace Architecture

ERIC Educational Resources Information Center

Duffy, Gavin

2009-01-01

This paper explores an area of adult learning that has received little attention of late, the terrain of public education through museums and civic architecture. The goal of promoting adult learning in public places e.g. through the work of museums has become commonplace in countries seeking to encourage adult learning about peace. This invariably…

The VREST learning environment.

PubMed

Kunst, E E; Geelkerken, R H; Sanders, A J B

2005-01-01

The VREST learning environment is an integrated architecture to improve the education of health care professionals. It is a combination of a learning, content and assessment management system based on virtual reality. The generic architecture is now being build and tested around the Lichtenstein protocol for hernia inguinalis repair.

Combining metric episodes with semantic event concepts within the Symbolic and Sub-Symbolic Robotics Intelligence Control System (SS-RICS)

NASA Astrophysics Data System (ADS)

Kelley, Troy D.; McGhee, S.

2013-05-01

This paper describes the ongoing development of a robotic control architecture that inspired by computational cognitive architectures from the discipline of cognitive psychology. The Symbolic and Sub-Symbolic Robotics Intelligence Control System (SS-RICS) combines symbolic and sub-symbolic representations of knowledge into a unified control architecture. The new architecture leverages previous work in cognitive architectures, specifically the development of the Adaptive Character of Thought-Rational (ACT-R) and Soar. This paper details current work on learning from episodes or events. The use of episodic memory as a learning mechanism has, until recently, been largely ignored by computational cognitive architectures. This paper details work on metric level episodic memory streams and methods for translating episodes into abstract schemas. The presentation will include research on learning through novelty and self generated feedback mechanisms for autonomous systems.

Analysis of Accuracy and Epoch on Back-propagation BFGS Quasi-Newton

NASA Astrophysics Data System (ADS)

Silaban, Herlan; Zarlis, Muhammad; Sawaluddin

2017-12-01

Back-propagation is one of the learning algorithms on artificial neural networks that have been widely used to solve various problems, such as pattern recognition, prediction and classification. The Back-propagation architecture will affect the outcome of learning processed. BFGS Quasi-Newton is one of the functions that can be used to change the weight of back-propagation. This research tested some back-propagation architectures using classical back-propagation and back-propagation with BFGS. There are 7 architectures that have been tested on glass dataset with various numbers of neurons, 6 architectures with 1 hidden layer and 1 architecture with 2 hidden layers. BP with BFGS improves the convergence of the learning process. The average improvement convergence is 98.34%. BP with BFGS is more optimal on architectures with smaller number of neurons with decreased epoch number is 94.37% with the increase of accuracy about 0.5%.

Investigating Actuation Force Fight with Asynchronous and Synchronous Redundancy Management Techniques

NASA Technical Reports Server (NTRS)

Hall, Brendan; Driscoll, Kevin; Schweiker, Kevin; Dutertre, Bruno

2013-01-01

Within distributed fault-tolerant systems the term force-fight is colloquially used to describe the level of command disagreement present at redundant actuation interfaces. This report details an investigation of force-fight using three distributed system case-study architectures. Each case study architecture is abstracted and formally modeled using the Symbolic Analysis Laboratory (SAL) tool chain from the Stanford Research Institute (SRI). We use the formal SAL models to produce k-induction based proofs of a bounded actuation agreement property. We also present a mathematically derived bound of redundant actuation agreement for sine-wave stimulus. The report documents our experiences and lessons learned developing the formal models and the associated proofs.

Magnetic Tunnel Junction Based Long-Term Short-Term Stochastic Synapse for a Spiking Neural Network with On-Chip STDP Learning

NASA Astrophysics Data System (ADS)

Srinivasan, Gopalakrishnan; Sengupta, Abhronil; Roy, Kaushik

2016-07-01

Spiking Neural Networks (SNNs) have emerged as a powerful neuromorphic computing paradigm to carry out classification and recognition tasks. Nevertheless, the general purpose computing platforms and the custom hardware architectures implemented using standard CMOS technology, have been unable to rival the power efficiency of the human brain. Hence, there is a need for novel nanoelectronic devices that can efficiently model the neurons and synapses constituting an SNN. In this work, we propose a heterostructure composed of a Magnetic Tunnel Junction (MTJ) and a heavy metal as a stochastic binary synapse. Synaptic plasticity is achieved by the stochastic switching of the MTJ conductance states, based on the temporal correlation between the spiking activities of the interconnecting neurons. Additionally, we present a significance driven long-term short-term stochastic synapse comprising two unique binary synaptic elements, in order to improve the synaptic learning efficiency. We demonstrate the efficacy of the proposed synaptic configurations and the stochastic learning algorithm on an SNN trained to classify handwritten digits from the MNIST dataset, using a device to system-level simulation framework. The power efficiency of the proposed neuromorphic system stems from the ultra-low programming energy of the spintronic synapses.

Magnetic Tunnel Junction Based Long-Term Short-Term Stochastic Synapse for a Spiking Neural Network with On-Chip STDP Learning.

PubMed

Srinivasan, Gopalakrishnan; Sengupta, Abhronil; Roy, Kaushik

2016-07-13

Spiking Neural Networks (SNNs) have emerged as a powerful neuromorphic computing paradigm to carry out classification and recognition tasks. Nevertheless, the general purpose computing platforms and the custom hardware architectures implemented using standard CMOS technology, have been unable to rival the power efficiency of the human brain. Hence, there is a need for novel nanoelectronic devices that can efficiently model the neurons and synapses constituting an SNN. In this work, we propose a heterostructure composed of a Magnetic Tunnel Junction (MTJ) and a heavy metal as a stochastic binary synapse. Synaptic plasticity is achieved by the stochastic switching of the MTJ conductance states, based on the temporal correlation between the spiking activities of the interconnecting neurons. Additionally, we present a significance driven long-term short-term stochastic synapse comprising two unique binary synaptic elements, in order to improve the synaptic learning efficiency. We demonstrate the efficacy of the proposed synaptic configurations and the stochastic learning algorithm on an SNN trained to classify handwritten digits from the MNIST dataset, using a device to system-level simulation framework. The power efficiency of the proposed neuromorphic system stems from the ultra-low programming energy of the spintronic synapses.

«

3

4

5

6

7

»

«

4

5

6

7

8

»

A deep learning framework for causal shape transformation.

PubMed

Lore, Kin Gwn; Stoecklein, Daniel; Davies, Michael; Ganapathysubramanian, Baskar; Sarkar, Soumik

2018-02-01

Recurrent neural network (RNN) and Long Short-term Memory (LSTM) networks are the common go-to architecture for exploiting sequential information where the output is dependent on a sequence of inputs. However, in most considered problems, the dependencies typically lie in the latent domain which may not be suitable for applications involving the prediction of a step-wise transformation sequence that is dependent on the previous states only in the visible domain with a known terminal state. We propose a hybrid architecture of convolution neural networks (CNN) and stacked autoencoders (SAE) to learn a sequence of causal actions that nonlinearly transform an input visual pattern or distribution into a target visual pattern or distribution with the same support and demonstrated its practicality in a real-world engineering problem involving the physics of fluids. We solved a high-dimensional one-to-many inverse mapping problem concerning microfluidic flow sculpting, where the use of deep learning methods as an inverse map is very seldom explored. This work serves as a fruitful use-case to applied scientists and engineers in how deep learning can be beneficial as a solution for high-dimensional physical problems, and potentially opening doors to impactful advance in fields such as material sciences and medical biology where multistep topological transformations is a key element. Copyright © 2017 Elsevier Ltd. All rights reserved.

The Traditional Non-Traditional Landscape Architecture Studio: Education through Service Learning in Miami, OK

ERIC Educational Resources Information Center

Loon, Leehu

2010-01-01

This research will illustrate the importance of a recent service learning project that was conducted for Miami, Oklahoma, by landscape architecture graduate students and faculty of the University of Oklahoma. Students and faculty partnered with the community to form the studio design team. Education in the landscape architecture studio at the…

Architecture Students' Perceptions of Their Learning Environment and Their Academic Performance

ERIC Educational Resources Information Center

Oluwatayo, Adedapo Adewunmi; Aderonmu, Peter A.; Aduwo, Egidario B.

2015-01-01

Scholars have agreed that the way in which students perceive their learning environments influences their academic performance. Empirical studies that focus on architecture students, however, have been very scarce. This is the gap that an attempt is filled in this study. A questionnaire survey of 273 students in a school of architecture in Nigeria…

The Hybrid Studio--Introducing Google+ as a Blended Learning Platform for Architectural Design Studio Teaching

ERIC Educational Resources Information Center

Steinø, Nicolai; Khalid, Md. Saufuddin

2017-01-01

Much architecture and design teaching is based on the studio format, where the co-presence in time and space of students, instructors and physical learning artefacts form a triangle from which the learning emerges. Yet with the advent of online communication platforms and learning management systems (LMS), there is reason to study how these…

The Contribution of Visualization to Learning Computer Architecture

ERIC Educational Resources Information Center

Yehezkel, Cecile; Ben-Ari, Mordechai; Dreyfus, Tommy

2007-01-01

This paper describes a visualization environment and associated learning activities designed to improve learning of computer architecture. The environment, EasyCPU, displays a model of the components of a computer and the dynamic processes involved in program execution. We present the results of a research program that analysed the contribution of…

Defining a Set of Architectural Requirements for Service-Oriented Mobile Learning Environments

ERIC Educational Resources Information Center

Filho, Nemésio Freitas Duarte; Barbosa, Ellen Francine

2014-01-01

Even providing several benefits and facilities with regard to teaching and learning, mobile learning environments present problems and challenges that must be investigated, especially with respect to the definition and standardization of architectural aspects. Most of these environments are still built in isolation, with particular structures and…

An economic analysis of disaggregation of space assets: Application to GPS

NASA Astrophysics Data System (ADS)

Hastings, Daniel E.; La Tour, Paul A.

2017-05-01

New ideas, technologies and architectural concepts are emerging with the potential to reshape the space enterprise. One of those new architectural concepts is the idea that rather than aggregating payloads onto large very high performance buses, space architectures should be disaggregated with smaller numbers of payloads (as small as one) per bus and the space capabilities spread across a correspondingly larger number of systems. The primary rationale is increased survivability and resilience. The concept of disaggregation is examined from an acquisition cost perspective. A mixed system dynamics and trade space exploration model is developed to look at long-term trends in the space acquisition business. The model is used to examine the question of how different disaggregated GPS architectures compare in cost to the well-known current GPS architecture. A generation-over-generation examination of policy choices is made possible through the application of soft systems modeling of experience and learning effects. The assumptions that are allowed to vary are: design lives, production quantities, non-recurring engineering and time between generations. The model shows that there is always a premium in the first generation to be paid to disaggregate the GPS payloads. However, it is possible to construct survivable architectures where the premium after two generations is relatively low.

Rasch family models in e-learning: analyzing architectural sketching with a digital pen.

PubMed

Scalise, Kathleen; Cheng, Nancy Yen-Wen; Oskui, Nargas

2009-01-01

Since architecture students studying design drawing are usually assessed qualitatively on the basis of their final products, the challenges and stages of their learning have remained masked. To clarify the challenges in design drawing, we have been using the BEAR Assessment System and Rasch family models to measure levels of understanding for individuals and groups, in order to correct pedagogical assumptions and tune teaching materials. This chapter discusses the analysis of 81 drawings created by architectural students to solve a space layout problem, collected and analyzed with digital pen-and-paper technology. The approach allows us to map developmental performance criteria and perceive achievement overlaps in learning domains assumed separate, and then re-conceptualize a three-part framework to represent learning in architectural drawing. Results and measurement evidence from the assessment and Rasch modeling are discussed.

Using an Analogical Thinking Model as an Instructional Tool to Improve Student Cognitive Ability in Architecture Design Learning Process

ERIC Educational Resources Information Center

Wu, Yun-Wu; Weng, Kuo-Hua

2013-01-01

Lack of creativity is a problem often plaguing students from design-related departments. Therefore, this study is intended to incorporate analogical thinking in the education of architecture design to enhance students' learning and their future career performance. First, this study explores the three aspects of architecture design curricula,…

Architecture and Children.

ERIC Educational Resources Information Center

Taylor, Anne; Campbell, Leslie

1988-01-01

Describes "Architecture and Children," a traveling exhibition which visually involves children in architectural principles and historic styles. States that it teaches children about architecture, and through architecture it instills the basis for aesthetic judgment. Argues that "children learn best by concrete examples of ideas, not…

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).

Using Curriculum Architecture in Workplace Learning

ERIC Educational Resources Information Center

Kaufmann, Ken

2005-01-01

While learning is often designed and executed as if it stood alone, it rarely exists in isolation. If more than one learning event is offered, a relationship between units exists and should be defined. This relationship calls for an architecture of curriculum that defines audience, content, and delivery within a context of performance. Curriculum…

Architecture of an E-Learning System with Embedded Authoring Support.

ERIC Educational Resources Information Center

Baudry, Andreas; Bungenstock, Michael; Mertsching, Barbel

This paper introduces an architecture for an e-learning system with an embedded authoring system. Based on the metaphor of a construction kit, this approach offers a general solution for specific content creation and publication. The learning resources are IMS "Content Packages" with a special structure to separate content and presentation. These…

Architectures for Distributed and Complex M-Learning Systems: Applying Intelligent Technologies

ERIC Educational Resources Information Center

Caballe, Santi, Ed.; Xhafa, Fatos, Ed.; Daradoumis, Thanasis, Ed.; Juan, Angel A., Ed.

2009-01-01

Over the last decade, the needs of educational organizations have been changing in accordance with increasingly complex pedagogical models and with the technological evolution of e-learning environments with very dynamic teaching and learning requirements. This book explores state-of-the-art software architectures and platforms used to support…

Establishment of a Digital Knowledge Conversion Architecture Design Learning with High User Acceptance

ERIC Educational Resources Information Center

Wu, Yun-Wu; Weng, Apollo; Weng, Kuo-Hua

2017-01-01

The purpose of this study is to design a knowledge conversion and management digital learning system for architecture design learning, helping students to share, extract, use and create their design knowledge through web-based interactive activities based on socialization, internalization, combination and externalization process in addition to…

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors

PubMed Central

Li, Frédéric; Nisar, Muhammad Adeel; Köping, Lukas; Grzegorzek, Marcin

2018-01-01

Getting a good feature representation of data is paramount for Human Activity Recognition (HAR) using wearable sensors. An increasing number of feature learning approaches—in particular deep-learning based—have been proposed to extract an effective feature representation by analyzing large amounts of data. However, getting an objective interpretation of their performances faces two problems: the lack of a baseline evaluation setup, which makes a strict comparison between them impossible, and the insufficiency of implementation details, which can hinder their use. In this paper, we attempt to address both issues: we firstly propose an evaluation framework allowing a rigorous comparison of features extracted by different methods, and use it to carry out extensive experiments with state-of-the-art feature learning approaches. We then provide all the codes and implementation details to make both the reproduction of the results reported in this paper and the re-use of our framework easier for other researchers. Our studies carried out on the OPPORTUNITY and UniMiB-SHAR datasets highlight the effectiveness of hybrid deep-learning architectures involving convolutional and Long-Short-Term-Memory (LSTM) to obtain features characterising both short- and long-term time dependencies in the data. PMID:29495310

Comparison of Feature Learning Methods for Human Activity Recognition Using Wearable Sensors.

PubMed

Li, Frédéric; Shirahama, Kimiaki; Nisar, Muhammad Adeel; Köping, Lukas; Grzegorzek, Marcin

2018-02-24

Getting a good feature representation of data is paramount for Human Activity Recognition (HAR) using wearable sensors. An increasing number of feature learning approaches-in particular deep-learning based-have been proposed to extract an effective feature representation by analyzing large amounts of data. However, getting an objective interpretation of their performances faces two problems: the lack of a baseline evaluation setup, which makes a strict comparison between them impossible, and the insufficiency of implementation details, which can hinder their use. In this paper, we attempt to address both issues: we firstly propose an evaluation framework allowing a rigorous comparison of features extracted by different methods, and use it to carry out extensive experiments with state-of-the-art feature learning approaches. We then provide all the codes and implementation details to make both the reproduction of the results reported in this paper and the re-use of our framework easier for other researchers. Our studies carried out on the OPPORTUNITY and UniMiB-SHAR datasets highlight the effectiveness of hybrid deep-learning architectures involving convolutional and Long-Short-Term-Memory (LSTM) to obtain features characterising both short- and long-term time dependencies in the data.

Apparatus for multiprocessor-based control of a multiagent robot

NASA Technical Reports Server (NTRS)

Peters, II, Richard Alan (Inventor)

2009-01-01

An architecture for robot intelligence enables a robot to learn new behaviors and create new behavior sequences autonomously and interact with a dynamically changing environment. Sensory information is mapped onto a Sensory Ego-Sphere (SES) that rapidly identifies important changes in the environment and functions much like short term memory. Behaviors are stored in a DBAM that creates an active map from the robot's current state to a goal state and functions much like long term memory. A dream state converts recent activities stored in the SES and creates or modifies behaviors in the DBAM.

A Collaborative Knowledge Plane for Autonomic Networks

NASA Astrophysics Data System (ADS)

Mbaye, Maïssa; Krief, Francine

Autonomic networking aims to give network components self-managing capabilities. Several autonomic architectures have been proposed. Each of these architectures includes sort of a knowledge plane which is very important to mimic an autonomic behavior. Knowledge plane has a central role for self-functions by providing suitable knowledge to equipment and needs to learn new strategies for more accuracy.However, defining knowledge plane's architecture is still a challenge for researchers. Specially, defining the way cognitive supports interact each other in knowledge plane and implementing them. Decision making process depends on these interactions between reasoning and learning parts of knowledge plane. In this paper we propose a knowledge plane's architecture based on machine learning (inductive logic programming) paradigm and situated view to deal with distributed environment. This architecture is focused on two self-functions that include all other self-functions: self-adaptation and self-organization. Study cases are given and implemented.

A comparative evaluation of supervised and unsupervised representation learning approaches for anaplastic medulloblastoma differentiation

NASA Astrophysics Data System (ADS)

Cruz-Roa, Angel; Arevalo, John; Basavanhally, Ajay; Madabhushi, Anant; González, Fabio

2015-01-01

Learning data representations directly from the data itself is an approach that has shown great success in different pattern recognition problems, outperforming state-of-the-art feature extraction schemes for different tasks in computer vision, speech recognition and natural language processing. Representation learning applies unsupervised and supervised machine learning methods to large amounts of data to find building-blocks that better represent the information in it. Digitized histopathology images represents a very good testbed for representation learning since it involves large amounts of high complex, visual data. This paper presents a comparative evaluation of different supervised and unsupervised representation learning architectures to specifically address open questions on what type of learning architectures (deep or shallow), type of learning (unsupervised or supervised) is optimal. In this paper we limit ourselves to addressing these questions in the context of distinguishing between anaplastic and non-anaplastic medulloblastomas from routine haematoxylin and eosin stained images. The unsupervised approaches evaluated were sparse autoencoders and topographic reconstruct independent component analysis, and the supervised approach was convolutional neural networks. Experimental results show that shallow architectures with more neurons are better than deeper architectures without taking into account local space invariances and that topographic constraints provide useful invariant features in scale and rotations for efficient tumor differentiation.

«

4

5

6

7

8

»

«

5

6

7

8

9

»

Modification Of Learning Rate With Lvq Model Improvement In Learning Backpropagation

NASA Astrophysics Data System (ADS)

Tata Hardinata, Jaya; Zarlis, Muhammad; Budhiarti Nababan, Erna; Hartama, Dedy; Sembiring, Rahmat W.

2017-12-01

One type of artificial neural network is a backpropagation, This algorithm trained with the network architecture used during the training as well as providing the correct output to insert a similar but not the same with the architecture in use at training.The selection of appropriate parameters also affects the outcome, value of learning rate is one of the parameters which influence the process of training, Learning rate affects the speed of learning process on the network architecture.If the learning rate is set too large, then the algorithm will become unstable and otherwise the algorithm will converge in a very long period of time.So this study was made to determine the value of learning rate on the backpropagation algorithm. LVQ models of learning rate is one of the models used in the determination of the value of the learning rate of the algorithm LVQ.By modifying this LVQ model to be applied to the backpropagation algorithm. From the experimental results known to modify the learning rate LVQ models were applied to the backpropagation algorithm learning process becomes faster (epoch less).

Strategic Architecture for E-Learning at H.P. University

ERIC Educational Resources Information Center

Sharma, Kunal; Sood, Deepak; Singh, Amarjeet; Pandit, Pallvi

2010-01-01

Purpose: The purpose of the paper is to unravel a strategic architecture for e-learning for a traditional university like Himachal Pradesh University (H.P. University) and provide guidelines as to how to carry the implementation of e-learning for the university of the future. Design/methodology/approach: Getting to the future first is not just…

The Impact of School Design and Arrangement on Learning Experiences: A Case Study of an Architecturally Significant Elementary School

ERIC Educational Resources Information Center

Churchill, Deirdre Lyne

2014-01-01

This qualitative study examined the impact of architectural design and arrangement on the learning experiences of students. Specifically, it examined how school design and arrangement foster interactions and relationships among students and adults relevant to integral learning experiences. This case study was limited to the breadth of knowledge…

A SCORM Thin Client Architecture for E-Learning Systems Based on Web Services

ERIC Educational Resources Information Center

Casella, Giovanni; Costagliola, Gennaro; Ferrucci, Filomena; Polese, Giuseppe; Scanniello, Giuseppe

2007-01-01

In this paper we propose an architecture of e-learning systems characterized by the use of Web services and a suitable middleware component. These technical infrastructures allow us to extend the system with new services as well as to integrate and reuse heterogeneous software e-learning components. Moreover, they let us better support the…

Dialogic e-Learning2learn: Creating Global Digital Networks and Educational Knowledge Building Architectures across Diversity

ERIC Educational Resources Information Center

Sorensen, Elsebeth Korsgaard

2007-01-01

Purpose: The purpose of this paper is to address the challenge and potential of online higher and continuing education, of fostering and promoting, in a global perspective across time and space, democratic values working for a better world. Design/methodology/approach: The paper presents a generalized dialogic learning architecture of networked…

An Autonomous Mobile Agent-Based Distributed Learning Architecture: A Proposal and Analytical Analysis

ERIC Educational Resources Information Center

Ahmed, Iftikhar; Sadeq, Muhammad Jafar

2006-01-01

Current distance learning systems are increasingly packing highly data-intensive contents on servers, resulting in the congestion of network and server resources at peak service times. A distributed learning system based on faded information field (FIF) architecture that employs mobile agents (MAs) has been proposed and simulated in this work. The…

Integrating Blended and Problem-Based Learning into an Architectural Housing Design Studio: A Case Study

ERIC Educational Resources Information Center

Bregger, Yasemin Alkiser

2017-01-01

This paper presents how a blended learning pedagogic model is integrated into an architectural design studio by adapting the problem-based learning process and housing issues in Istanbul Technical University (ITU), during fall 2015 and spring 2016 semesters for fourth and sixth level students. These studios collaborated with the "Introduction…

A "Knowledge Trading Game" for Collaborative Design Learning in an Architectural Design Studio

ERIC Educational Resources Information Center

Wang, Wan-Ling; Shih, Shen-Guan; Chien, Sheng-Fen

2010-01-01

Knowledge-sharing and resource exchange are the key to the success of collaborative design learning. In an architectural design studio, design knowledge entails learning efforts that need to accumulate and recombine dispersed and complementary pieces of knowledge. In this research, firstly, "Knowledge Trading Game" is proposed to be a way for…

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

An Adaptive Web-Based Support to e-Education in Robotics and Automation

NASA Astrophysics Data System (ADS)

di Giamberardino, Paolo; Temperini, Marco

The paper presents the hardware and software architecture of a remote laboratory, with robotics and automation applications, devised to support e-teaching and e-learning activities, at an undergraduate level in computer engineering. The hardware is composed by modular structures, based on the Lego Mindstorms components: they are reasonably sophisticated in terms of functions, pretty easy to use, and sufficiently affordable in terms of cost. Moreover, being the robots intrinsically modular, wrt the number and distribution of sensors and actuators, they are easily and quickly reconfigurable. A web application makes the laboratory and its robots available via internet. The software framework allows the teacher to define, for the course under her/his responsibility, a learning path made of different and differently complex exercises, graduated in terms of the "difficulty" they require to meet and of the "competence" that the solver is supposed to have shown. The learning path of exercises is adapted to the individual learner's progressively growing competence: at any moment, only a subset of the exercises is available (depending on how close their levels of competence and difficulty are to those of the exercises already solved by the learner).

A Workbench for Discovering Task-Specific Theories of Learning

DTIC Science & Technology

1989-03-03

mind (the cognitive architecture) will not be of much use to educators who wish to perform a cognitive task analysis of their subject matter before...analysis packages that can be added to a cognitive architecture, thus creating a ’workbench’ for performing cognitive task analysis . Such tools becomes...learning theories have been. Keywords: Cognitive task analysis , Instructional design, Cognitive modelling, Learning.

Integrating planning, execution, and learning

NASA Technical Reports Server (NTRS)

Kuokka, Daniel R.

1989-01-01

To achieve the goal of building an autonomous agent, the usually disjoint capabilities of planning, execution, and learning must be used together. An architecture, called MAX, within which cognitive capabilities can be purposefully and intelligently integrated is described. The architecture supports the codification of capabilities as explicit knowledge that can be reasoned about. In addition, specific problem solving, learning, and integration knowledge is developed.

Evaluating deep learning architectures for Speech Emotion Recognition.

PubMed

Fayek, Haytham M; Lech, Margaret; Cavedon, Lawrence

2017-08-01

Speech Emotion Recognition (SER) can be regarded as a static or dynamic classification problem, which makes SER an excellent test bed for investigating and comparing various deep learning architectures. We describe a frame-based formulation to SER that relies on minimal speech processing and end-to-end deep learning to model intra-utterance dynamics. We use the proposed SER system to empirically explore feed-forward and recurrent neural network architectures and their variants. Experiments conducted illuminate the advantages and limitations of these architectures in paralinguistic speech recognition and emotion recognition in particular. As a result of our exploration, we report state-of-the-art results on the IEMOCAP database for speaker-independent SER and present quantitative and qualitative assessments of the models' performances. Copyright © 2017 Elsevier Ltd. All rights reserved.

Do neural nets learn statistical laws behind natural language?

PubMed

Takahashi, Shuntaro; Tanaka-Ishii, Kumiko

2017-01-01

The performance of deep learning in natural language processing has been spectacular, but the reasons for this success remain unclear because of the inherent complexity of deep learning. This paper provides empirical evidence of its effectiveness and of a limitation of neural networks for language engineering. Precisely, we demonstrate that a neural language model based on long short-term memory (LSTM) effectively reproduces Zipf's law and Heaps' law, two representative statistical properties underlying natural language. We discuss the quality of reproducibility and the emergence of Zipf's law and Heaps' law as training progresses. We also point out that the neural language model has a limitation in reproducing long-range correlation, another statistical property of natural language. This understanding could provide a direction for improving the architectures of neural networks.

Do neural nets learn statistical laws behind natural language?

PubMed Central

Takahashi, Shuntaro

2017-01-01

The performance of deep learning in natural language processing has been spectacular, but the reasons for this success remain unclear because of the inherent complexity of deep learning. This paper provides empirical evidence of its effectiveness and of a limitation of neural networks for language engineering. Precisely, we demonstrate that a neural language model based on long short-term memory (LSTM) effectively reproduces Zipf’s law and Heaps’ law, two representative statistical properties underlying natural language. We discuss the quality of reproducibility and the emergence of Zipf’s law and Heaps’ law as training progresses. We also point out that the neural language model has a limitation in reproducing long-range correlation, another statistical property of natural language. This understanding could provide a direction for improving the architectures of neural networks. PMID:29287076

Short-Term Plasticity and Long-Term Potentiation in Magnetic Tunnel Junctions: Towards Volatile Synapses

NASA Astrophysics Data System (ADS)

Sengupta, Abhronil; Roy, Kaushik

2016-02-01

Synaptic memory is considered to be the main element responsible for learning and cognition in humans. Although traditionally nonvolatile long-term plasticity changes are implemented in nanoelectronic synapses for neuromorphic applications, recent studies in neuroscience reveal that biological synapses undergo metastable volatile strengthening followed by a long-term strengthening provided that the frequency of the input stimulus is sufficiently high. Such "memory strengthening" and "memory decay" functionalities can potentially lead to adaptive neuromorphic architectures. In this paper, we demonstrate the close resemblance of the magnetization dynamics of a magnetic tunnel junction (MTJ) to short-term plasticity and long-term potentiation observed in biological synapses. We illustrate that, in addition to the magnitude and duration of the input stimulus, the frequency of the stimulus plays a critical role in determining long-term potentiation of the MTJ. Such MTJ synaptic memory arrays can be utilized to create compact, ultrafast, and low-power intelligent neural systems.

Sharing e-Learning Experiences: A Personalised Approach

NASA Astrophysics Data System (ADS)

Clematis, Andrea; Forcheri, Paola; Ierardi, Maria Grazia; Quarati, Alfonso

A two-tier architecture is presented, based on hybrid peer-to-peer technology, aimed at providing personalized access to heterogeneous learning sources. The architecture deploys a conceptual model that is superimposed over logically and physically separated repositories. The model is based on the interactions between users and learning resources, described by means of coments. To support users to find out material satisfying their needs, mechanisms for ranking resources and for extracting personalized views of the learning space are provided.

Using Fuzzy Logic for Performance Evaluation in Reinforcement Learning

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.; Khedkar, Pratap S.

1992-01-01

Current reinforcement learning algorithms require long training periods which generally limit their applicability to small size problems. A new architecture is described which uses fuzzy rules to initialize its two neural networks: a neural network for performance evaluation and another for action selection. This architecture is applied to control of dynamic systems and it is demonstrated that it is possible to start with an approximate prior knowledge and learn to refine it through experiments using reinforcement learning.

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.

«

5

6

7

8

9

»

«

6

7

8

9

10

»

An intelligent robotic aid system for human services

NASA Technical Reports Server (NTRS)

Kawamura, K.; Bagchi, S.; Iskarous, M.; Pack, R. T.; Saad, A.

1994-01-01

The long term goal of our research at the Intelligent Robotic Laboratory at Vanderbilt University is to develop advanced intelligent robotic aid systems for human services. As a first step toward our goal, the current thrusts of our R&D are centered on the development of an intelligent robotic aid called the ISAC (Intelligent Soft Arm Control). In this paper, we describe the overall system architecture and current activities in intelligent control, adaptive/interactive control and task learning.

Solving graph data issues using a layered architecture approach with applications to web spam detection.

PubMed

Scarselli, Franco; Tsoi, Ah Chung; Hagenbuchner, Markus; Noi, Lucia Di

2013-12-01

This paper proposes the combination of two state-of-the-art algorithms for processing graph input data, viz., the probabilistic mapping graph self organizing map, an unsupervised learning approach, and the graph neural network, a supervised learning approach. We organize these two algorithms in a cascade architecture containing a probabilistic mapping graph self organizing map, and a graph neural network. We show that this combined approach helps us to limit the long-term dependency problem that exists when training the graph neural network resulting in an overall improvement in performance. This is demonstrated in an application to a benchmark problem requiring the detection of spam in a relatively large set of web sites. It is found that the proposed method produces results which reach the state of the art when compared with some of the best results obtained by others using quite different approaches. A particular strength of our method is its applicability towards any input domain which can be represented as a graph. Copyright © 2013 Elsevier Ltd. All rights reserved.

Columns in Clay

ERIC Educational Resources Information Center

Leenhouts, Robin

2010-01-01

This article describes a clay project for students studying Greece and Rome. It provides a wonderful way to learn slab construction techniques by making small clay column capitols. With this lesson, students learn architectural vocabulary and history, understand the importance of classical architectural forms and their influence on today's…

An Architecture for Case-Based Learning

ERIC Educational Resources Information Center

Cifuentes, Laurent; Mercer, Rene; Alverez, Omar; Bettati, Riccardo

2010-01-01

We report on the design, development, implementation, and evaluation of a case-based instructional environment designed for learning network engineering skills for cybersecurity. We describe the societal problem addressed, the theory-based solution, and the preliminary testing and evaluation of that solution. We identify an architecture for…

Emergent latent symbol systems in recurrent neural networks

NASA Astrophysics Data System (ADS)

Monner, Derek; Reggia, James A.

2012-12-01

Fodor and Pylyshyn [(1988). Connectionism and cognitive architecture: A critical analysis. Cognition, 28(1-2), 3-71] famously argued that neural networks cannot behave systematically short of implementing a combinatorial symbol system. A recent response from Frank et al. [(2009). Connectionist semantic systematicity. Cognition, 110(3), 358-379] claimed to have trained a neural network to behave systematically without implementing a symbol system and without any in-built predisposition towards combinatorial representations. We believe systems like theirs may in fact implement a symbol system on a deeper and more interesting level: one where the symbols are latent - not visible at the level of network structure. In order to illustrate this possibility, we demonstrate our own recurrent neural network that learns to understand sentence-level language in terms of a scene. We demonstrate our model's learned understanding by testing it on novel sentences and scenes. By paring down our model into an architecturally minimal version, we demonstrate how it supports combinatorial computation over distributed representations by using the associative memory operations of Vector Symbolic Architectures. Knowledge of the model's memory scheme gives us tools to explain its errors and construct superior future models. We show how the model designs and manipulates a latent symbol system in which the combinatorial symbols are patterns of activation distributed across the layers of a neural network, instantiating a hybrid of classical symbolic and connectionist representations that combines advantages of both.

A Machine Learning Concept for DTN Routing

NASA Technical Reports Server (NTRS)

Dudukovich, Rachel; Hylton, Alan; Papachristou, Christos

2017-01-01

This paper discusses the concept and architecture of a machine learning based router for delay tolerant space networks. The techniques of reinforcement learning and Bayesian learning are used to supplement the routing decisions of the popular Contact Graph Routing algorithm. An introduction to the concepts of Contact Graph Routing, Q-routing and Naive Bayes classification are given. The development of an architecture for a cross-layer feedback framework for DTN (Delay-Tolerant Networking) protocols is discussed. Finally, initial simulation setup and results are given.

Compressed sampling and dictionary learning framework for wavelength-division-multiplexing-based distributed fiber sensing.

PubMed

Weiss, Christian; Zoubir, Abdelhak M

2017-05-01

We propose a compressed sampling and dictionary learning framework for fiber-optic sensing using wavelength-tunable lasers. A redundant dictionary is generated from a model for the reflected sensor signal. Imperfect prior knowledge is considered in terms of uncertain local and global parameters. To estimate a sparse representation and the dictionary parameters, we present an alternating minimization algorithm that is equipped with a preprocessing routine to handle dictionary coherence. The support of the obtained sparse signal indicates the reflection delays, which can be used to measure impairments along the sensing fiber. The performance is evaluated by simulations and experimental data for a fiber sensor system with common core architecture.

Hierarchical representation and machine learning from faulty jet engine behavioral examples to detect real time abnormal conditions

NASA Technical Reports Server (NTRS)

Gupta, U. K.; Ali, M.

1988-01-01

The theoretical basis and operation of LEBEX, a machine-learning system for jet-engine performance monitoring, are described. The behavior of the engine is modeled in terms of four parameters (the rotational speeds of the high- and low-speed sections and the exhaust and combustion temperatures), and parameter variations indicating malfunction are transformed into structural representations involving instances and events. LEBEX extracts descriptors from a set of training data on normal and faulty engines, represents them hierarchically in a knowledge base, and uses them to diagnose and predict faults on a real-time basis. Diagrams of the system architecture and printouts of typical results are shown.

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.

Optimal causal inference: estimating stored information and approximating causal architecture.

PubMed

Still, Susanne; Crutchfield, James P; Ellison, Christopher J

2010-09-01

We introduce an approach to inferring the causal architecture of stochastic dynamical systems that extends rate-distortion theory to use causal shielding--a natural principle of learning. We study two distinct cases of causal inference: optimal causal filtering and optimal causal estimation. Filtering corresponds to the ideal case in which the probability distribution of measurement sequences is known, giving a principled method to approximate a system's causal structure at a desired level of representation. We show that in the limit in which a model-complexity constraint is relaxed, filtering finds the exact causal architecture of a stochastic dynamical system, known as the causal-state partition. From this, one can estimate the amount of historical information the process stores. More generally, causal filtering finds a graded model-complexity hierarchy of approximations to the causal architecture. Abrupt changes in the hierarchy, as a function of approximation, capture distinct scales of structural organization. For nonideal cases with finite data, we show how the correct number of the underlying causal states can be found by optimal causal estimation. A previously derived model-complexity control term allows us to correct for the effect of statistical fluctuations in probability estimates and thereby avoid overfitting.

Basic Learning of Form

ERIC Educational Resources Information Center

i Serrano, Magda Mària; Musquera Felip, Sílvia; Beriain Sanzol, Luis

2018-01-01

"Form is 'what', Design is 'how'" (Kahn, 1960). Learning about the formal universe and the wide range of possibilities it offers should be one of the purposes of the early subjects in architectural studies. This article aims to explain the contents of a first course of architectural design and demonstrate how, using a methodology based…

Comprehension of Architectural Construction through Multimedia Active Learning

ERIC Educational Resources Information Center

Mas, Ángeles; Blasco, Vicente; Lerma, Carlos; Angulo, Quiteria

2013-01-01

This study presents an investigation about the use of multimedia procedures applied to architectural construction teaching. We have applied current technological resources, aiming to rationalize and optimize the active learning process. The experience presented to students is very simple and yet very effective. It has consisted in a simulation of…

Designing Online Learning Communities of Practice: A Democratic Perspective

ERIC Educational Resources Information Center

Sorensen, Elsebeth Korsgaard; Murchu, Daithi O.

2004-01-01

This study addresses the problem of designing an appropriate learning space or architecture for distributed online courses using net-based communication technologies. We apply Wenger's criteria to explore, identify and discuss the design architectures of two online courses from two comparable online Master's programmes, developed and delivered in…

Structural Identification and Comparison of Intelligent Mobile Learning Environment

ERIC Educational Resources Information Center

Upadhyay, Nitin; Agarwal, Vishnu Prakash

2007-01-01

This paper proposes a methodology using graph theory, matrix algebra and permanent function to compare different architecture (structure) design of intelligent mobile learning environment. The current work deals with the development/selection of optimum architecture (structural) model of iMLE. This can be done using the criterion as discussed in…

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.

Low Data Drug Discovery with One-Shot Learning

PubMed Central

2017-01-01

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. Model.2015, 55, 263–27425635324). 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). PMID:28470045

Deep learning based classification of breast tumors with shear-wave elastography.

PubMed

Zhang, Qi; Xiao, Yang; Dai, Wei; Suo, Jingfeng; Wang, Congzhi; Shi, Jun; Zheng, Hairong

2016-12-01

This study aims to build a deep learning (DL) architecture for automated extraction of learned-from-data image features from the shear-wave elastography (SWE), and to evaluate the DL architecture in differentiation between benign and malignant breast tumors. We construct a two-layer DL architecture for SWE feature extraction, comprised of the point-wise gated Boltzmann machine (PGBM) and the restricted Boltzmann machine (RBM). The PGBM contains task-relevant and task-irrelevant hidden units, and the task-relevant units are connected to the RBM. Experimental evaluation was performed with five-fold cross validation on a set of 227 SWE images, 135 of benign tumors and 92 of malignant tumors, from 121 patients. The features learned with our DL architecture were compared with the statistical features quantifying image intensity and texture. Results showed that the DL features achieved better classification performance with an accuracy of 93.4%, a sensitivity of 88.6%, a specificity of 97.1%, and an area under the receiver operating characteristic curve of 0.947. The DL-based method integrates feature learning with feature selection on SWE. It may be potentially used in clinical computer-aided diagnosis of breast cancer. Copyright © 2016 Elsevier B.V. All rights reserved.

Building the IOOS data management subsystem

USGS Publications Warehouse

de La Beaujardière, J.; Mendelssohn, R.; Ortiz, C.; Signell, R.

2010-01-01

We discuss progress to date and plans for the Integrated Ocean Observing System (IOOS??) Data Management and Communications (DMAC) subsystem. We begin by presenting a conceptual architecture of IOOS DMAC. We describe work done as part of a 3-year pilot project known as the Data Integration Framework and the subsequent assessment of lessons learned. We present work that has been accomplished as part of the initial version of the IOOS Data Catalog. Finally, we discuss near-term plans for augmenting IOOS DMAC capabilities.

Comparison of Machine Learning methods for incipient motion in gravel bed rivers

NASA Astrophysics Data System (ADS)

Valyrakis, Manousos

2013-04-01

Soil erosion and sediment transport of natural gravel bed streams are important processes which affect both the morphology as well as the ecology of earth's surface. For gravel bed rivers at near incipient flow conditions, particle entrainment dynamics are highly intermittent. This contribution reviews the use of modern Machine Learning (ML) methods implemented for short term prediction of entrainment instances of individual grains exposed in fully developed near boundary turbulent flows. Results obtained by network architectures of variable complexity based on two different ML methods namely the Artificial Neural Network (ANN) and the Adaptive Neuro-Fuzzy Inference System (ANFIS) are compared in terms of different error and performance indices, computational efficiency and complexity as well as predictive accuracy and forecast ability. Different model architectures are trained and tested with experimental time series obtained from mobile particle flume experiments. The experimental setup consists of a Laser Doppler Velocimeter (LDV) and a laser optics system, which acquire data for the instantaneous flow and particle response respectively, synchronously. The first is used to record the flow velocity components directly upstream of the test particle, while the later tracks the particle's displacements. The lengthy experimental data sets (millions of data points) are split into the training and validation subsets used to perform the corresponding learning and testing of the models. It is demonstrated that the ANFIS hybrid model, which is based on neural learning and fuzzy inference principles, better predicts the critical flow conditions above which sediment transport is initiated. In addition, it is illustrated that empirical knowledge can be extracted, validating the theoretical assumption that particle ejections occur due to energetic turbulent flow events. Such a tool may find application in management and regulation of stream flows downstream of dams for stream restoration, implementation of sustainable practices in river and estuarine ecosystems and design of stable river bed and banks.

Evaluation of Visual Computer Simulator for Computer Architecture Education

ERIC Educational Resources Information Center

Imai, Yoshiro; Imai, Masatoshi; Moritoh, Yoshio

2013-01-01

This paper presents trial evaluation of a visual computer simulator in 2009-2011, which has been developed to play some roles of both instruction facility and learning tool simultaneously. And it illustrates an example of Computer Architecture education for University students and usage of e-Learning tool for Assembly Programming in order to…

«

6

7

8

9

10

»

«

7

8

9

10

11

»

A Socio-Cognitive Approach to Knowledge Construction in Design Studio through Blended Learning

ERIC Educational Resources Information Center

Kocaturk, Tuba

2017-01-01

This paper results from an educational research project that was undertaken by the School of Architecture, at the University of Liverpool funded by the Higher Education Academy in UK. The research explored technology driven shifts in architectural design studio education, identified their cognitive effects on design learning and developed an…

From Architectural Photogrammetry Toward Digital Architectural Heritage Education

NASA Astrophysics Data System (ADS)

Baik, A.; Alitany, A.

2018-05-01

This paper considers the potential of using the documentation approach proposed for the heritage buildings in Historic Jeddah, Saudi Arabia (as a case study) by using the close-range photogrammetry / the Architectural Photogrammetry techniques as a new academic experiment in digital architectural heritage education. Moreover, different than most of engineering educational techniques related to architecture education, this paper will be focusing on the 3-D data acquisition technology as a tool to document and to learn the principals of the digital architectural heritage documentation. The objective of this research is to integrate the 3-D modelling and visualisation knowledge for the purposes of identifying, designing and evaluating an effective engineering educational experiment. Furthermore, the students will learn and understand the characteristics of the historical building while learning more advanced 3-D modelling and visualisation techniques. It can be argued that many of these technologies alone are difficult to improve the education; therefore, it is important to integrate them in an educational framework. This should be in line with the educational ethos of the academic discipline. Recently, a number of these technologies and methods have been effectively used in education sectors and other purposes; such as in the virtual museum. However, these methods are not directly coincided with the traditional education and teaching architecture. This research will be introduced the proposed approach as a new academic experiment in the architecture education sector. The new teaching approach will be based on the Architectural Photogrammetry to provide semantically rich models. The academic experiment will require students to have suitable knowledge in both Photogrammetry applications to engage with the process.

Some Schools of Architecture Could Use a Good Architect

ERIC Educational Resources Information Center

Fisher, Thomas

2008-01-01

Like the proverbial shoemaker's child who goes barefoot, many architecture students learn the best practices of their discipline in some of the worst buildings on their campuses. The problems with the newest architecture-school buildings, says the writer, are both similar and solvable. In a new book, teams of architecture faculty members and…

Drafting. Advanced Print Reading--Electrical.

ERIC Educational Resources Information Center

Oregon State Dept. of Education, Salem.

This document is a workbook for drafting students learning advanced print reading for electricity applications. The workbook contains seven units covering the following material: architectural working drawings; architectural symbols and dimensions; basic architectural electrical symbols; wiring symbols; riser diagrams; schematic diagrams; and…

Application of the Actor-Critic Architecture to Functional Electrical Stimulation Control of a Human Arm

PubMed Central

Thomas, Philip; Branicky, Michael; van den Bogert, Antonie; Jagodnik, Kathleen

2010-01-01

Clinical tests have shown that the dynamics of a human arm, controlled using Functional Electrical Stimulation (FES), can vary significantly between and during trials. In this paper, we study the application of the actor-critic architecture, with neural networks for the both the actor and the critic, as a controller that can adapt to these changing dynamics of a human arm. Development and tests were done in simulation using a planar arm model and Hill-based muscle dynamics. We begin by training it using a Proportional Derivative (PD) controller as a supervisor. We then make clinically relevant changes to the dynamics of the arm and test the actor-critic’s ability to adapt without supervision in a reasonable number of episodes. Finally, we devise methods for achieving both rapid learning and long-term stability. PMID:20689654

Application of the Actor-Critic Architecture to Functional Electrical Stimulation Control of a Human Arm.

PubMed

Thomas, Philip; Branicky, Michael; van den Bogert, Antonie; Jagodnik, Kathleen

2009-01-01

Clinical tests have shown that the dynamics of a human arm, controlled using Functional Electrical Stimulation (FES), can vary significantly between and during trials. In this paper, we study the application of the actor-critic architecture, with neural networks for the both the actor and the critic, as a controller that can adapt to these changing dynamics of a human arm. Development and tests were done in simulation using a planar arm model and Hill-based muscle dynamics. We begin by training it using a Proportional Derivative (PD) controller as a supervisor. We then make clinically relevant changes to the dynamics of the arm and test the actor-critic's ability to adapt without supervision in a reasonable number of episodes. Finally, we devise methods for achieving both rapid learning and long-term stability.

A reinforcement learning-based architecture for fuzzy logic control

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1992-01-01

This paper introduces a new method for learning to refine a rule-based fuzzy logic controller. A reinforcement learning technique is used in conjunction with a multilayer neural network model of a fuzzy controller. The approximate reasoning based intelligent control (ARIC) architecture proposed here learns by updating its prediction of the physical system's behavior and fine tunes a control knowledge base. Its theory is related to Sutton's temporal difference (TD) method. Because ARIC has the advantage of using the control knowledge of an experienced operator and fine tuning it through the process of learning, it learns faster than systems that train networks from scratch. The approach is applied to a cart-pole balancing system.

Learning and Tuning of Fuzzy Rules

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1997-01-01

In this chapter, we review some of the current techniques for learning and tuning fuzzy rules. For clarity, we refer to the process of generating rules from data as the learning problem and distinguish it from tuning an already existing set of fuzzy rules. For learning, we touch on unsupervised learning techniques such as fuzzy c-means, fuzzy decision tree systems, fuzzy genetic algorithms, and linear fuzzy rules generation methods. For tuning, we discuss Jang's ANFIS architecture, Berenji-Khedkar's GARIC architecture and its extensions in GARIC-Q. We show that the hybrid techniques capable of learning and tuning fuzzy rules, such as CART-ANFIS, RNN-FLCS, and GARIC-RB, are desirable in development of a number of future intelligent systems.

Context Aware Ubiquitous Learning Environments for Peer-to-Peer Collaborative Learning

ERIC Educational Resources Information Center

Yang, Stephen J. H.

2006-01-01

A ubiquitous learning environment provides an interoperable, pervasive, and seamless learning architecture to connect, integrate, and share three major dimensions of learning resources: learning collaborators, learning contents, and learning services. Ubiquitous learning is characterized by providing intuitive ways for identifying right learning…

The Pedagogic Architecture of MOOC: A Research Project on Educational Courses in Spanish

ERIC Educational Resources Information Center

Fernández-Díaz, Elia; Rodríguez-Hoyos, Carlos; Salvador, Adelina Calvo

2017-01-01

This study has been carried out within the context of the ECO European Project (E-learning, Communication Open-Data: Massive Mobile, Ubiquitous, and Open Learning) which is being financed by the European Union over four years (2014-17). It analyses the pedagogic architecture of MOOC on pedagogic/educational subjects in Spanish over one academic…

Combining Self-Explaining with Computer Architecture Diagrams to Enhance the Learning of Assembly Language Programming

ERIC Educational Resources Information Center

Hung, Y.-C.

2012-01-01

This paper investigates the impact of combining self explaining (SE) with computer architecture diagrams to help novice students learn assembly language programming. Pre- and post-test scores for the experimental and control groups were compared and subjected to covariance (ANCOVA) statistical analysis. Results indicate that the SE-plus-diagram…

Critical Success Factors in Crafting Strategic Architecture for E-Learning at HP University

ERIC Educational Resources Information Center

Sharma, Kunal; Pandit, Pallvi; Pandit, Parul

2011-01-01

Purpose: The purpose of this paper is to outline the critical success factors for crafting a strategic architecture for e-learning at HP University. Design/methodology/approach: A descriptive survey type of research design was used. An empirical study was conducted on students enrolled with the International Centre for Distance and Open Learning…

Deep Learning for Extreme Weather Detection

NASA Astrophysics Data System (ADS)

Prabhat, M.; Racah, E.; Biard, J.; Liu, Y.; Mudigonda, M.; Kashinath, K.; Beckham, C.; Maharaj, T.; Kahou, S.; Pal, C.; O'Brien, T. A.; Wehner, M. F.; Kunkel, K.; Collins, W. D.

2017-12-01

We will present our latest results from the application of Deep Learning methods for detecting, localizing and segmenting extreme weather patterns in climate data. We have successfully applied supervised convolutional architectures for the binary classification tasks of detecting tropical cyclones and atmospheric rivers in centered, cropped patches. We have subsequently extended our architecture to a semi-supervised formulation, which is capable of learning a unified representation of multiple weather patterns, predicting bounding boxes and object categories, and has the capability to detect novel patterns (w/ few, or no labels). We will briefly present our efforts in scaling the semi-supervised architecture to 9600 nodes of the Cori supercomputer, obtaining 15PF performance. Time permitting, we will highlight our efforts in pixel-level segmentation of weather patterns.

Using machine learning classifiers to assist healthcare-related decisions: classification of electronic patient records.

PubMed

Pollettini, Juliana T; Panico, Sylvia R G; Daneluzzi, Julio C; Tinós, Renato; Baranauskas, José A; Macedo, Alessandra A

2012-12-01

Surveillance Levels (SLs) are categories for medical patients (used in Brazil) that represent different types of medical recommendations. SLs are defined according to risk factors and the medical and developmental history of patients. Each SL is associated with specific educational and clinical measures. The objective of the present paper was to verify computer-aided, automatic assignment of SLs. The present paper proposes a computer-aided approach for automatic recommendation of SLs. The approach is based on the classification of information from patient electronic records. For this purpose, a software architecture composed of three layers was developed. The architecture is formed by a classification layer that includes a linguistic module and machine learning classification modules. The classification layer allows for the use of different classification methods, including the use of preprocessed, normalized language data drawn from the linguistic module. We report the verification and validation of the software architecture in a Brazilian pediatric healthcare institution. The results indicate that selection of attributes can have a great effect on the performance of the system. Nonetheless, our automatic recommendation of surveillance level can still benefit from improvements in processing procedures when the linguistic module is applied prior to classification. Results from our efforts can be applied to different types of medical systems. The results of systems supported by the framework presented in this paper may be used by healthcare and governmental institutions to improve healthcare services in terms of establishing preventive measures and alerting authorities about the possibility of an epidemic.

The Emergence of Agent-Based Technology as an Architectural Component of Serious Games

NASA Technical Reports Server (NTRS)

Phillips, Mark; Scolaro, Jackie; Scolaro, Daniel

2010-01-01

The evolution of games as an alternative to traditional simulations in the military context has been gathering momentum over the past five years, even though the exploration of their use in the serious sense has been ongoing since the mid-nineties. Much of the focus has been on the aesthetics of the visuals provided by the core game engine as well as the artistry provided by talented development teams to produce not only breathtaking artwork, but highly immersive game play. Consideration of game technology is now so much a part of the modeling and simulation landscape that it is becoming difficult to distinguish traditional simulation solutions from game-based approaches. But games have yet to provide the much needed interactive free play that has been the domain of semi-autonomous forces (SAF). The component-based middleware architecture that game engines provide promises a great deal in terms of options for the integration of agent solutions to support the development of non-player characters that engage the human player without the deterministic nature of scripted behaviors. However, there are a number of hard-learned lessons on the modeling and simulation side of the equation that game developers have yet to learn, such as: correlation of heterogeneous systems, scalability of both terrain and numbers of non-player entities, and the bi-directional nature of simulation to game interaction provided by Distributed Interactive Simulation (DIS) and High Level Architecture (HLA).

RACE/A: An Architectural Account of the Interactions between Learning, Task Control, and Retrieval Dynamics

ERIC Educational Resources Information Center

van Maanen, Leendert; van Rijn, Hedderik; Taatgen, Niels

2012-01-01

This article discusses how sequential sampling models can be integrated in a cognitive architecture. The new theory Retrieval by Accumulating Evidence in an Architecture (RACE/A) combines the level of detail typically provided by sequential sampling models with the level of task complexity typically provided by cognitive architectures. We will use…

Supporting Undergraduate Computer Architecture Students Using a Visual MIPS64 CPU Simulator

ERIC Educational Resources Information Center

Patti, D.; Spadaccini, A.; Palesi, M.; Fazzino, F.; Catania, V.

2012-01-01

The topics of computer architecture are always taught using an Assembly dialect as an example. The most commonly used textbooks in this field use the MIPS64 Instruction Set Architecture (ISA) to help students in learning the fundamentals of computer architecture because of its orthogonality and its suitability for real-world applications. This…

Learning Methods for Efficient Adoption of Contemporary Technologies in Architectural Design

ERIC Educational Resources Information Center

Mahdavinejad, Mohammadjavad; Dehghani, Sohaib; Shahsavari, Fatemeh

2013-01-01

The interaction between technology and history is one of the most significant issues in achieving an efficient and progressive architecture in any era. This is a concept which stems from lesson of traditional architecture of Iran. Architecture as a part of art, has permanently been transforming just like a living organism. In fact, it has been…

Predicting Instability Timescales in Closely-Packed Planetary Systems

NASA Astrophysics Data System (ADS)

Tamayo, Daniel; Hadden, Samuel; Hussain, Naireen; Silburt, Ari; Gilbertson, Christian; Rein, Hanno; Menou, Kristen

2018-04-01

Many of the multi-planet systems discovered around other stars are maximally packed. This implies that simulations with masses or orbital parameters too far from the actual values will destabilize on short timescales; thus, long-term dynamics allows one to constrain the orbital architectures of many closely packed multi-planet systems. A central challenge in such efforts is the large computational cost of N-body simulations, which preclude a full survey of the high-dimensional parameter space of orbital architectures allowed by observations. I will present our recent successes in training machine learning models capable of reliably predicting orbital stability a million times faster than N-body simulations. By engineering dynamically relevant features that we feed to a gradient-boosted decision tree algorithm (XGBoost), we are able to achieve a precision and recall of 90% on a holdout test set of N-body simulations. This opens a wide discovery space for characterizing new exoplanet discoveries and for elucidating how orbital architectures evolve through time as the next generation of spaceborne exoplanet surveys prepare for launch this year.

Dynamic Photorefractive Memory and its Application for Opto-Electronic Neural Networks.

NASA Astrophysics Data System (ADS)

Sasaki, Hironori

This dissertation describes the analysis of the photorefractive crystal dynamics and its application for opto-electronic neural network systems. The realization of the dynamic photorefractive memory is investigated in terms of the following aspects: fast memory update, uniform grating multiplexing schedules and the prevention of the partial erasure of existing gratings. The fast memory update is realized by the selective erasure process that superimposes a new grating on the original one with an appropriate phase shift. The dynamics of the selective erasure process is analyzed using the first-order photorefractive material equations and experimentally confirmed. The effects of beam coupling and fringe bending on the selective erasure dynamics are also analyzed by numerically solving a combination of coupled wave equations and the photorefractive material equation. Incremental recording technique is proposed as a uniform grating multiplexing schedule and compared with the conventional scheduled recording technique in terms of phase distribution in the presence of an external dc electric field, as well as the image gray scale dependence. The theoretical analysis and experimental results proved the superiority of the incremental recording technique over the scheduled recording. Novel recirculating information memory architecture is proposed and experimentally demonstrated to prevent partial degradation of the existing gratings by accessing the memory. Gratings are circulated through a memory feed back loop based on the incremental recording dynamics and demonstrate robust read/write/erase capabilities. The dynamic photorefractive memory is applied to opto-electronic neural network systems. Module architecture based on the page-oriented dynamic photorefractive memory is proposed. This module architecture can implement two complementary interconnection organizations, fan-in and fan-out. The module system scalability and the learning capabilities are theoretically investigated using the photorefractive dynamics described in previous chapters of the dissertation. The implementation of the feed-forward image compression network with 900 input and 9 output neurons with 6-bit interconnection accuracy is experimentally demonstrated. Learning of the Perceptron network that determines sex based on input face images of 900 pixels is also successfully demonstrated.

«

7

8

9

10

11

»

«

8

9

10

11

12

»

A novel single neuron perceptron with universal approximation and XOR computation properties.

PubMed

Lotfi, Ehsan; Akbarzadeh-T, M-R

2014-01-01

We propose a biologically motivated brain-inspired single neuron perceptron (SNP) with universal approximation and XOR computation properties. This computational model extends the input pattern and is based on the excitatory and inhibitory learning rules inspired from neural connections in the human brain's nervous system. The resulting architecture of SNP can be trained by supervised excitatory and inhibitory online learning rules. The main features of proposed single layer perceptron are universal approximation property and low computational complexity. The method is tested on 6 UCI (University of California, Irvine) pattern recognition and classification datasets. Various comparisons with multilayer perceptron (MLP) with gradient decent backpropagation (GDBP) learning algorithm indicate the superiority of the approach in terms of higher accuracy, lower time, and spatial complexity, as well as faster training. Hence, we believe the proposed approach can be generally applicable to various problems such as in pattern recognition and classification.

Memristive Mixed-Signal Neuromorphic Systems: Energy-Efficient Learning at the Circuit-Level

DOE PAGES

Chakma, Gangotree; Adnan, Md Musabbir; Wyer, Austin R.; ...

2017-11-23

Neuromorphic computing is non-von Neumann computer architecture for the post Moore’s law era of computing. Since a main focus of the post Moore’s law era is energy-efficient computing with fewer resources and less area, neuromorphic computing contributes effectively in this research. Here in this paper, we present a memristive neuromorphic system for improved power and area efficiency. Our particular mixed-signal approach implements neural networks with spiking events in a synchronous way. Moreover, the use of nano-scale memristive devices saves both area and power in the system. We also provide device-level considerations that make the system more energy-efficient. The proposed systemmore » additionally includes synchronous digital long term plasticity, an online learning methodology that helps the system train the neural networks during the operation phase and improves the efficiency in learning considering the power consumption and area overhead.« less

Memristive Mixed-Signal Neuromorphic Systems: Energy-Efficient Learning at the Circuit-Level

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

Chakma, Gangotree; Adnan, Md Musabbir; Wyer, Austin R.

Neuromorphic computing is non-von Neumann computer architecture for the post Moore’s law era of computing. Since a main focus of the post Moore’s law era is energy-efficient computing with fewer resources and less area, neuromorphic computing contributes effectively in this research. Here in this paper, we present a memristive neuromorphic system for improved power and area efficiency. Our particular mixed-signal approach implements neural networks with spiking events in a synchronous way. Moreover, the use of nano-scale memristive devices saves both area and power in the system. We also provide device-level considerations that make the system more energy-efficient. The proposed systemmore » additionally includes synchronous digital long term plasticity, an online learning methodology that helps the system train the neural networks during the operation phase and improves the efficiency in learning considering the power consumption and area overhead.« less

Temporal sequence learning in winner-take-all networks of spiking neurons demonstrated in a brain-based device.

PubMed

McKinstry, Jeffrey L; Edelman, Gerald M

2013-01-01

Animal behavior often involves a temporally ordered sequence of actions learned from experience. Here we describe simulations of interconnected networks of spiking neurons that learn to generate patterns of activity in correct temporal order. The simulation consists of large-scale networks of thousands of excitatory and inhibitory neurons that exhibit short-term synaptic plasticity and spike-timing dependent synaptic plasticity. The neural architecture within each area is arranged to evoke winner-take-all (WTA) patterns of neural activity that persist for tens of milliseconds. In order to generate and switch between consecutive firing patterns in correct temporal order, a reentrant exchange of signals between these areas was necessary. To demonstrate the capacity of this arrangement, we used the simulation to train a brain-based device responding to visual input by autonomously generating temporal sequences of motor actions.

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.

A Study of Complex Deep Learning Networks on High Performance, Neuromorphic, and Quantum Computers

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

Potok, Thomas E; Schuman, Catherine D; Young, Steven R

Current Deep Learning models use highly optimized convolutional neural networks (CNN) trained on large graphical processing units (GPU)-based computers with a fairly simple layered network topology, i.e., highly connected layers, without intra-layer connections. Complex topologies have been proposed, but are intractable to train on current systems. Building the topologies of the deep learning network requires hand tuning, and implementing the network in hardware is expensive in both cost and power. In this paper, we evaluate deep learning models using three different computing architectures to address these problems: quantum computing to train complex topologies, high performance computing (HPC) to automatically determinemore » network topology, and neuromorphic computing for a low-power hardware implementation. Due to input size limitations of current quantum computers we use the MNIST dataset for our evaluation. The results show the possibility of using the three architectures in tandem to explore complex deep learning networks that are untrainable using a von Neumann architecture. We show that a quantum computer can find high quality values of intra-layer connections and weights, while yielding a tractable time result as the complexity of the network increases; a high performance computer can find optimal layer-based topologies; and a neuromorphic computer can represent the complex topology and weights derived from the other architectures in low power memristive hardware. This represents a new capability that is not feasible with current von Neumann architecture. It potentially enables the ability to solve very complicated problems unsolvable with current computing technologies.« less

Sustainable Learning.

ERIC Educational Resources Information Center

Hoekstra, Joel

2001-01-01

Shows how architectural design can merge ecological living and learning as illustrated by the Wolf Ridge's new Environmental Learning Center in Finland, Minnesota. Photos and design details are provided. (GR)

Humanoids Learning to Walk: A Natural CPG-Actor-Critic Architecture.

PubMed

Li, Cai; Lowe, Robert; Ziemke, Tom

2013-01-01

The identification of learning mechanisms for locomotion has been the subject of much research for some time but many challenges remain. Dynamic systems theory (DST) offers a novel approach to humanoid learning through environmental interaction. Reinforcement learning (RL) has offered a promising method to adaptively link the dynamic system to the environment it interacts with via a reward-based value system. In this paper, we propose a model that integrates the above perspectives and applies it to the case of a humanoid (NAO) robot learning to walk the ability of which emerges from its value-based interaction with the environment. In the model, a simplified central pattern generator (CPG) architecture inspired by neuroscientific research and DST is integrated with an actor-critic approach to RL (cpg-actor-critic). In the cpg-actor-critic architecture, least-square-temporal-difference based learning converges to the optimal solution quickly by using natural gradient learning and balancing exploration and exploitation. Futhermore, rather than using a traditional (designer-specified) reward it uses a dynamic value function as a stability indicator that adapts to the environment. The results obtained are analyzed using a novel DST-based embodied cognition approach. Learning to walk, from this perspective, is a process of integrating levels of sensorimotor activity and value.

Humanoids Learning to Walk: A Natural CPG-Actor-Critic Architecture

PubMed Central

Li, Cai; Lowe, Robert; Ziemke, Tom

2013-01-01

The identification of learning mechanisms for locomotion has been the subject of much research for some time but many challenges remain. Dynamic systems theory (DST) offers a novel approach to humanoid learning through environmental interaction. Reinforcement learning (RL) has offered a promising method to adaptively link the dynamic system to the environment it interacts with via a reward-based value system. In this paper, we propose a model that integrates the above perspectives and applies it to the case of a humanoid (NAO) robot learning to walk the ability of which emerges from its value-based interaction with the environment. In the model, a simplified central pattern generator (CPG) architecture inspired by neuroscientific research and DST is integrated with an actor-critic approach to RL (cpg-actor-critic). In the cpg-actor-critic architecture, least-square-temporal-difference based learning converges to the optimal solution quickly by using natural gradient learning and balancing exploration and exploitation. Futhermore, rather than using a traditional (designer-specified) reward it uses a dynamic value function as a stability indicator that adapts to the environment. The results obtained are analyzed using a novel DST-based embodied cognition approach. Learning to walk, from this perspective, is a process of integrating levels of sensorimotor activity and value. PMID:23675345

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.

Space and Architecture's Current Line of Research? A Lunar Architecture Workshop With An Architectural Agenda.

NASA Astrophysics Data System (ADS)

Solomon, D.; van Dijk, A.

The "2002 ESA Lunar Architecture Workshop" (June 3-16) ESTEC, Noordwijk, NL and V2_Lab, Rotterdam, NL) is the first-of-its-kind workshop for exploring the design of extra-terrestrial (infra) structures for human exploration of the Moon and Earth-like planets introducing 'architecture's current line of research', and adopting an architec- tural criteria. The workshop intends to inspire, engage and challenge 30-40 European masters students from the fields of aerospace engineering, civil engineering, archi- tecture, and art to design, validate and build models of (infra) structures for Lunar exploration. The workshop also aims to open up new physical and conceptual terrain for an architectural agenda within the field of space exploration. A sound introduc- tion to the issues, conditions, resources, technologies, and architectural strategies will initiate the workshop participants into the context of lunar architecture scenarios. In my paper and presentation about the development of the ideology behind this work- shop, I will comment on the following questions: * Can the contemporary architectural agenda offer solutions that affect the scope of space exploration? It certainly has had an impression on urbanization and colonization of previously sparsely populated parts of Earth. * Does the current line of research in architecture offer any useful strategies for com- bining scientific interests, commercial opportunity, and public space? What can be learned from 'state of the art' architecture that blends commercial and public pro- grammes within one location? * Should commercial 'colonisation' projects in space be required to provide public space in a location where all humans present are likely to be there in a commercial context? Is the wave in Koolhaas' new Prada flagship store just a gesture to public space, or does this new concept in architecture and shopping evolve the public space? * What can we learn about designing (infra-) structures on the Moon or any other space context that will be useful on Earth on a conceptual and practical level? * In what ways could architecture's field of reference offer building on the Moon (and other celestial bodies) a paradigm shift? 1 In addition to their models and designs, workshop participants will begin authoring a design recommendation for the building of (infra-) structures and habitats on celestial bodies in particular the Moon and Mars. The design recommendation, a substantiated aesthetic code of conduct (not legally binding) will address long term planning and incorporate issues of sustainability, durability, bio-diversity, infrastructure, CHANGE, and techniques that lend themselves to Earth-bound applications. It will also address the cultural implications of architectural design might have within the context of space exploration. The design recommendation will ultimately be presented for peer review to both the space and architecture communities. What would the endorsement from the architectural community of such a document mean to the space community? The Lunar Architecture Workshop is conceptualised, produced and organised by(in alphabetical order): Alexander van Dijk, Art Race in Space, Barbara Imhof; ES- CAPE*spHERE, Vienna, University of Technology, Institute for Design and Building Construction, Vienna, Bernard Foing; ESA SMART1 Project Scientist, Susmita Mo- hanty; MoonFront, LLC, Hans Schartner' Vienna University of Technology, Institute for Design and Building Construction, Debra Solomon; Art Race in Space, Dutch Art Institute, Paul van Susante; Lunar Explorers Society. Workshop locations: ESTEC, Noordwijk, NL and V2_Lab, Rotterdam, NL Workshop dates: June 3-16, 2002 (a Call for Participation will be made in March -April 2002.) 2

An architecture for designing fuzzy logic controllers using neural networks

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1991-01-01

Described here is an architecture for designing fuzzy controllers through a hierarchical process of control rule acquisition and by using special classes of neural network learning techniques. A new method for learning to refine a fuzzy logic controller is introduced. A reinforcement learning technique is used in conjunction with a multi-layer neural network model of a fuzzy controller. The model learns by updating its prediction of the plant's behavior and is related to the Sutton's Temporal Difference (TD) method. The method proposed here has the advantage of using the control knowledge of an experienced operator and fine-tuning it through the process of learning. The approach is applied to a cart-pole balancing system.

A "Language Lab" for Architectural Design.

ERIC Educational Resources Information Center

Mackenzie, Arch; And Others

This paper discusses a "language lab" strategy in which traditional studio learning may be supplemented by language lessons using computer graphics techniques to teach architectural grammar, a body of elements and principles that govern the design of buildings belonging to a particular architectural theory or style. Two methods of…

A knowledge-base generating hierarchical fuzzy-neural controller.

PubMed

Kandadai, R M; Tien, J M

1997-01-01

We present an innovative fuzzy-neural architecture that is able to automatically generate a knowledge base, in an extractable form, for use in hierarchical knowledge-based controllers. The knowledge base is in the form of a linguistic rule base appropriate for a fuzzy inference system. First, we modify Berenji and Khedkar's (1992) GARIC architecture to enable it to automatically generate a knowledge base; a pseudosupervised learning scheme using reinforcement learning and error backpropagation is employed. Next, we further extend this architecture to a hierarchical controller that is able to generate its own knowledge base. Example applications are provided to underscore its viability.

Multilayer Extreme Learning Machine With Subnetwork Nodes for Representation Learning.

PubMed

Yang, Yimin; Wu, Q M Jonathan

2016-11-01

The extreme learning machine (ELM), which was originally proposed for "generalized" single-hidden layer feedforward neural networks, provides efficient unified learning solutions for the applications of clustering, regression, and classification. It presents competitive accuracy with superb efficiency in many applications. However, ELM with subnetwork nodes architecture has not attracted much research attentions. Recently, many methods have been proposed for supervised/unsupervised dimension reduction or representation learning, but these methods normally only work for one type of problem. This paper studies the general architecture of multilayer ELM (ML-ELM) with subnetwork nodes, showing that: 1) the proposed method provides a representation learning platform with unsupervised/supervised and compressed/sparse representation learning and 2) experimental results on ten image datasets and 16 classification datasets show that, compared to other conventional feature learning methods, the proposed ML-ELM with subnetwork nodes performs competitively or much better than other feature learning methods.

Functional expansion representations of artificial neural networks

NASA Technical Reports Server (NTRS)

Gray, W. Steven

1992-01-01

In the past few years, significant interest has developed in using artificial neural networks to model and control nonlinear dynamical systems. While there exists many proposed schemes for accomplishing this and a wealth of supporting empirical results, most approaches to date tend to be ad hoc in nature and rely mainly on heuristic justifications. The purpose of this project was to further develop some analytical tools for representing nonlinear discrete-time input-output systems, which when applied to neural networks would give insight on architecture selection, pruning strategies, and learning algorithms. A long term goal is to determine in what sense, if any, a neural network can be used as a universal approximator for nonliner input-output maps with memory (i.e., realized by a dynamical system). This property is well known for the case of static or memoryless input-output maps. The general architecture under consideration in this project was a single-input, single-output recurrent feedforward network.

Flipped Learning as a Paradigm Shift in Architectural Education

ERIC Educational Resources Information Center

Elrayies, Ghada Mohammad

2017-01-01

The target of Education for Sustainable Development is to make people creative and lifelong learners. Over the past years, architectural education has faced challenges of embedding innovation and creativity into its programs. That calls the graduates to be more skilled in the human dimensions of professional practice. So, architectural education…

Does Supporting Multiple Student Strategies Lead to Greater Learning and Motivation? Investigating a Source of Complexity in the Architecture of Intelligent Tutoring Systems

ERIC Educational Resources Information Center

Waalkens, Maaike; Aleven, Vincent; Taatgen, Niels

2013-01-01

Intelligent tutoring systems (ITS) support students in learning a complex problem-solving skill. One feature that makes an ITS architecturally complex, and hard to build, is support for strategy freedom, that is, the ability to let students pursue multiple solution strategies within a given problem. But does greater freedom mean that students…

Readiness for interprofessional learning: a cross-faculty comparison between architecture and occupational therapy students.

PubMed

Larkin, Helen; Hitch, Danielle; Watchorn, Valerie; Ang, Susan; Stagnitti, Karen

2013-09-01

Health and wellbeing includes a need for built environments to accommodate and be inclusive of the broadest range of people and a corresponding need to ensure graduates are ready to engage in this field of interprofessional and inter-industry practise. All too often, interprofessional education in higher education is neglected with a tendency towards educational silos, particularly at a cross-faculty level. This paper reports on an initiative that embedded universal design practice education into the curricula of first year architecture and third year occupational therapy students and evaluated the impact on students' readiness for interprofessional learning. The Readiness for Interprofessional Learning Scale (RIPLS) was given to students at the beginning and end of the semester during which students participated in a variety of online and face-to-face curriculum initiatives. Results showed that at the beginning of semester, occupational therapy students were significantly more positive about interprofessional learning than their architecture counterparts. Post-results showed that this trend continued but that occupational therapy students became less positive on some items after the interprofessional learning experience. This study provides insights into the interprofessional learning experiences of a group of students who have not previously been studied within the available literature.

Jupiter Europa Orbiter Architecture Definition Process

NASA Technical Reports Server (NTRS)

Rasmussen, Robert; Shishko, Robert

2011-01-01

The proposed Jupiter Europa Orbiter mission, planned for launch in 2020, is using a new architectural process and framework tool to drive its model-based systems engineering effort. The process focuses on getting the architecture right before writing requirements and developing a point design. A new architecture framework tool provides for the structured entry and retrieval of architecture artifacts based on an emerging architecture meta-model. This paper describes the relationships among these artifacts and how they are used in the systems engineering effort. Some early lessons learned are discussed.

«

8

9

10

11

12

»

«

9

10

11

12

13

»

Architectural Terms for Educational Planners.

ERIC Educational Resources Information Center

1997

This booklet is designed to facilitate open, clear communication between educational facility planners and the architects hired to oversee building design and construction. It provides a list of architectural, electrical, plumbing, and topographical symbols; a glossary of architectural terms; and a list of public agencies and relevant codes and…

Underground Architecture and Layout for the Belgian High-Level and Long-Lived Intermediate-Level Radioactive Waste Disposal Facility- 12116

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

Van Cotthem, Alain; Van Humbeeck, Hughes; Biurrun, Enrique

The underground architecture and layout of the proposed Belgian high-level (HLW) and long-lived, intermediate-level radioactive wastes (ILW-LL) disposal system (repository) is mainly based on lessons learned during the development and 30-year-long operation of an underground research laboratory (URL) ('HADES') located adjacent to the city of Mol at a depth of 225 m in a 100-m-thick, Tertiary clay formation; the Boom clay. The following main operational and safety challenges are addressed in the proposed architecture and layout: 1. Following excavation, the underground openings needed to be promptly supported to minimize the extent of the excavation damaged zone (EDZ). 2. The sizemore » and unsupported stand-up time at tunnel crossings/intersections also needed to be minimized to minimize the extent of the related EDZ. 3. Steel components had to be minimized to limit the related long-term (post-closure) corrosion and hydrogen production. 4. The shafts and all equipment had to go down through a 180-m-thick aquifer and handle up to 65-Ton payloads. 5. The shaft seals had to be placed in the underlying clay layer. The currently proposed layout minimizes the excavated volume based on strict long-term-safety criteria and optimizes operational safety. Operational safety is further enhanced by a remote-controlled waste-package-handling system transporting the waste packages from their respective surface location down to their respective disposal location with no intermediate operation. The related on-site preparation and thenceforth use of cement-based, waste package- transportation containers are integral operational-safety components. In addition to strengthening the waste packages and providing radiation protection, these containers also provide long-term corrosion protection of the internal 'primary' steel packages. (authors)« less

Neural architecture design based on extreme learning machine.

PubMed

Bueno-Crespo, Andrés; García-Laencina, Pedro J; Sancho-Gómez, José-Luis

2013-12-01

Selection of the optimal neural architecture to solve a pattern classification problem entails to choose the relevant input units, the number of hidden neurons and its corresponding interconnection weights. This problem has been widely studied in many research works but their solutions usually involve excessive computational cost in most of the problems and they do not provide a unique solution. This paper proposes a new technique to efficiently design the MultiLayer Perceptron (MLP) architecture for classification using the Extreme Learning Machine (ELM) algorithm. The proposed method provides a high generalization capability and a unique solution for the architecture design. Moreover, the selected final network only retains those input connections that are relevant for the classification task. Experimental results show these advantages. Copyright © 2013 Elsevier Ltd. All rights reserved.

Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP.

PubMed

Shim, Yoonsik; Philippides, Andrew; Staras, Kevin; Husbands, Phil

2016-10-01

We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

Unsupervised Learning in an Ensemble of Spiking Neural Networks Mediated by ITDP

PubMed Central

Staras, Kevin

2016-01-01

We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture. PMID:27760125

A Service Oriented Architecture to Integrate Mobile Assessment in Learning Management Systems

ERIC Educational Resources Information Center

Riad, A. M.; El-Ghareeb, H. A.

2008-01-01

Mobile Learning (M-Learning) is an approach to E-Learning that utilizes mobile devices. Learning Management System (LMS) should enable M-Learning. Unfortunately, M-Learning is not the same at each educational institution. Assessment is one of the learning activities that can be achieved electronically and via mobile device. Mobile assessment…

BlueSky Cloud Framework: An E-Learning Framework Embracing Cloud Computing

NASA Astrophysics Data System (ADS)

Dong, Bo; Zheng, Qinghua; Qiao, Mu; Shu, Jian; Yang, Jie

Currently, E-Learning has grown into a widely accepted way of learning. With the huge growth of users, services, education contents and resources, E-Learning systems are facing challenges of optimizing resource allocations, dealing with dynamic concurrency demands, handling rapid storage growth requirements and cost controlling. In this paper, an E-Learning framework based on cloud computing is presented, namely BlueSky cloud framework. Particularly, the architecture and core components of BlueSky cloud framework are introduced. In BlueSky cloud framework, physical machines are virtualized, and allocated on demand for E-Learning systems. Moreover, BlueSky cloud framework combines with traditional middleware functions (such as load balancing and data caching) to serve for E-Learning systems as a general architecture. It delivers reliable, scalable and cost-efficient services to E-Learning systems, and E-Learning organizations can establish systems through these services in a simple way. BlueSky cloud framework solves the challenges faced by E-Learning, and improves the performance, availability and scalability of E-Learning systems.

''Beauty of Wholeness and Beauty of Partiality.'' New Terms Defining the Concept of Beauty in Architecture in Terms of Sustainability and Computer Aided Design

ERIC Educational Resources Information Center

Farid, Ayman A.; Zaghloul, Weaam M.; Dewidar, Khaled M.

2014-01-01

The great shift in sustainability and computer aided design in the field of architecture caused a remarkable change in the architecture philosophy, new aspects of beauty and aesthetic values are being introduced, and traditional definitions for beauty cannot fully cover this aspects, which causes a gap between; new architecture works criticism and…

Long-term knowledge acquisition using contextual information in a memory-inspired robot architecture

NASA Astrophysics Data System (ADS)

Pratama, Ferdian; Mastrogiovanni, Fulvio; Lee, Soon Geul; Chong, Nak Young

2017-03-01

In this paper, we present a novel cognitive framework allowing a robot to form memories of relevant traits of its perceptions and to recall them when necessary. The framework is based on two main principles: on the one hand, we propose an architecture inspired by current knowledge in human memory organisation; on the other hand, we integrate such an architecture with the notion of context, which is used to modulate the knowledge acquisition process when consolidating memories and forming new ones, as well as with the notion of familiarity, which is employed to retrieve proper memories given relevant cues. Although much research has been carried out, which exploits Machine Learning approaches to provide robots with internal models of their environment (including objects and occurring events therein), we argue that such approaches may not be the right direction to follow if a long-term, continuous knowledge acquisition is to be achieved. As a case study scenario, we focus on both robot-environment and human-robot interaction processes. In case of robot-environment interaction, a robot performs pick and place movements using the objects in the workspace, at the same time observing their displacement on a table in front of it, and progressively forms memories defined as relevant cues (e.g. colour, shape or relative position) in a context-aware fashion. As far as human-robot interaction is concerned, the robot can recall specific snapshots representing past events using both sensory information and contextual cues upon request by humans.

Learning in the machine: The symmetries of the deep learning channel.

PubMed

Baldi, Pierre; Sadowski, Peter; Lu, Zhiqin

2017-11-01

In a physical neural system, learning rules must be local both in space and time. In order for learning to occur, non-local information must be communicated to the deep synapses through a communication channel, the deep learning channel. We identify several possible architectures for this learning channel (Bidirectional, Conjoined, Twin, Distinct) and six symmetry challenges: (1) symmetry of architectures; (2) symmetry of weights; (3) symmetry of neurons; (4) symmetry of derivatives; (5) symmetry of processing; and (6) symmetry of learning rules. Random backpropagation (RBP) addresses the second and third symmetry, and some of its variations, such as skipped RBP (SRBP) address the first and the fourth symmetry. Here we address the last two desirable symmetries showing through simulations that they can be achieved and that the learning channel is particularly robust to symmetry variations. Specifically, random backpropagation and its variations can be performed with the same non-linear neurons used in the main input-output forward channel, and the connections in the learning channel can be adapted using the same algorithm used in the forward channel, removing the need for any specialized hardware in the learning channel. Finally, we provide mathematical results in simple cases showing that the learning equations in the forward and backward channels converge to fixed points, for almost any initial conditions. In symmetric architectures, if the weights in both channels are small at initialization, adaptation in both channels leads to weights that are essentially symmetric during and after learning. Biological connections are discussed. Copyright © 2017 Elsevier Ltd. All rights reserved.

Adaptive WTA with an analog VLSI neuromorphic learning chip.

PubMed

Häfliger, Philipp

2007-03-01

In this paper, we demonstrate how a particular spike-based learning rule (where exact temporal relations between input and output spikes of a spiking model neuron determine the changes of the synaptic weights) can be tuned to express rate-based classical Hebbian learning behavior (where the average input and output spike rates are sufficient to describe the synaptic changes). This shift in behavior is controlled by the input statistic and by a single time constant. The learning rule has been implemented in a neuromorphic very large scale integration (VLSI) chip as part of a neurally inspired spike signal image processing system. The latter is the result of the European Union research project Convolution AER Vision Architecture for Real-Time (CAVIAR). Since it is implemented as a spike-based learning rule (which is most convenient in the overall spike-based system), even if it is tuned to show rate behavior, no explicit long-term average signals are computed on the chip. We show the rule's rate-based Hebbian learning ability in a classification task in both simulation and chip experiment, first with artificial stimuli and then with sensor input from the CAVIAR system.

Unsupervised active learning based on hierarchical graph-theoretic clustering.

PubMed

Hu, Weiming; Hu, Wei; Xie, Nianhua; Maybank, Steve

2009-10-01

Most existing active learning approaches are supervised. Supervised active learning has the following problems: inefficiency in dealing with the semantic gap between the distribution of samples in the feature space and their labels, lack of ability in selecting new samples that belong to new categories that have not yet appeared in the training samples, and lack of adaptability to changes in the semantic interpretation of sample categories. To tackle these problems, we propose an unsupervised active learning framework based on hierarchical graph-theoretic clustering. In the framework, two promising graph-theoretic clustering algorithms, namely, dominant-set clustering and spectral clustering, are combined in a hierarchical fashion. Our framework has some advantages, such as ease of implementation, flexibility in architecture, and adaptability to changes in the labeling. Evaluations on data sets for network intrusion detection, image classification, and video classification have demonstrated that our active learning framework can effectively reduce the workload of manual classification while maintaining a high accuracy of automatic classification. It is shown that, overall, our framework outperforms the support-vector-machine-based supervised active learning, particularly in terms of dealing much more efficiently with new samples whose categories have not yet appeared in the training samples.

Hidden Realities inside PBL Design Processes: Is Consensus Design an Impossible Clash of Interest between the Individual and the Collective, and Is Architecture Its First Victim?

ERIC Educational Resources Information Center

Pihl, Ole

2015-01-01

How do architecture students experience the contradictions between the individual and the group at the Department of Architecture and Design of Aalborg University? The Problem-Based Learning model has been extensively applied to the department's degree programs in coherence with the Integrated Design Process, but is a group-based architecture and…

A Ground Systems Architecture Transition for a Distributed Operations System

NASA Technical Reports Server (NTRS)

Sellers, Donna; Pitts, Lee; Bryant, Barry

2003-01-01

The Marshall Space Flight Center (MSFC) Ground Systems Department (GSD) recently undertook an architecture change in the product line that serves the ISS program. As a result, the architecture tradeoffs between data system product lines that serve remote users versus those that serve control center flight control teams were explored extensively. This paper describes the resulting architecture that will be used in the International Space Station (ISS) payloads program, and the resulting functional breakdown of the products that support this architecture. It also describes the lessons learned from the path that was followed, as a migration of products cause the need to reevaluate the allocation of functions across the architecture. The result is a set of innovative ground system solutions that is scalable so it can support facilities of wide-ranging sizes, from a small site up to large control centers. Effective use of system automation, custom components, design optimization for data management, data storage, data transmissions, and advanced local and wide area networking architectures, plus the effective use of Commercial-Off-The-Shelf (COTS) products, provides flexible Remote Ground System options that can be tailored to the needs of each user. This paper offers a description of the efficiency and effectiveness of the Ground Systems architectural options that have been implemented, and includes successful implementation examples and lessons learned.

Deep learning architectures for multi-label classification of intelligent health risk prediction.

PubMed

Maxwell, Andrew; Li, Runzhi; Yang, Bei; Weng, Heng; Ou, Aihua; Hong, Huixiao; Zhou, Zhaoxian; Gong, Ping; Zhang, Chaoyang

2017-12-28

Multi-label classification of data remains to be a challenging problem. Because of the complexity of the data, it is sometimes difficult to infer information about classes that are not mutually exclusive. For medical data, patients could have symptoms of multiple different diseases at the same time and it is important to develop tools that help to identify problems early. Intelligent health risk prediction models built with deep learning architectures offer a powerful tool for physicians to identify patterns in patient data that indicate risks associated with certain types of chronic diseases. Physical examination records of 110,300 anonymous patients were used to predict diabetes, hypertension, fatty liver, a combination of these three chronic diseases, and the absence of disease (8 classes in total). The dataset was split into training (90%) and testing (10%) sub-datasets. Ten-fold cross validation was used to evaluate prediction accuracy with metrics such as precision, recall, and F-score. Deep Learning (DL) architectures were compared with standard and state-of-the-art multi-label classification methods. Preliminary results suggest that Deep Neural Networks (DNN), a DL architecture, when applied to multi-label classification of chronic diseases, produced accuracy that was comparable to that of common methods such as Support Vector Machines. We have implemented DNNs to handle both problem transformation and algorithm adaption type multi-label methods and compare both to see which is preferable. Deep Learning architectures have the potential of inferring more information about the patterns of physical examination data than common classification methods. The advanced techniques of Deep Learning can be used to identify the significance of different features from physical examination data as well as to learn the contributions of each feature that impact a patient's risk for chronic diseases. However, accurate prediction of chronic disease risks remains a challenging problem that warrants further studies.

Detail in architecture: Between arts & crafts

NASA Astrophysics Data System (ADS)

Dulencin, Juraj

2016-06-01

Architectural detail represents an important part of architecture. Not only can it be used as an identifier of a specific building but at the same time enhances the experience of the realized project. Within it lie the signs of a great architect and clues to understanding his or her way of thinking. It is therefore the central topic of a seminar offered to architecture students at the Brno University of Technology. During the course of the semester-long class the students acquaint themselves with atypical architectural details of domestic and international architects by learning to read them, understand them and subsequently draw them by creating architectural blueprints. In other words, by general analysis of a detail the students learn theoretical thinking of its architect who, depending on the nature of the design, had to incorporate a variety of techniques and crafts. Students apply this analytical part to their own architectural detail design. The methodology of the seminar consists of experiential learning by project management and is complemented by a series of lectures discussing a diversity of details as well as materials and technologies required to implement it. The architectural detail design is also part of students' bachelors thesis, therefore, the realistic nature of their blueprints can be verified in the production process of its physical counterpart. Based on their own documentation the students choose the most suitable manufacturing process whether it is supplied by a specific technology or a craftsman. Students actively participate in the production and correct their design proposals in real scale with the actual material. A student, as a future architect, stands somewhere between a client and an artisan, materializes his or her idea and adjusts the manufacturing process so that the final detail fulfills aesthetic consistency and is in harmony with its initial concept. One of the very important aspects of the design is its economic cost, an actual price of real implementation. The detail determines not only the physical expression, it becomes the characteristic feature from which the rest of the building is derived. This course motivates students to surpass mere technical calculations learned from books towards sophistication and refinement, pragmatism and experimentation, and encourages a shift from feasibility to perfection.

Writing as a Tool in Teaching Sketching: Implications for Architectural Design Education

ERIC Educational Resources Information Center

Soygenis, Sema; Soygenis, Murat; Erktin, Emine

2010-01-01

This article discusses the process of a study designed to develop university students' sketching skills in schools of architecture. Acknowledging the relationship between cognition and writing, it aims to investigate the role of writing in learning sketching among architecture students and to examine how students regulate their thoughts by writing…

Learning in the "Real" World: Encounters with Radical Architectures (1960s-1970s)

ERIC Educational Resources Information Center

Doucet, Isabelle

2017-01-01

Throughout the 1960s and 1970s architectural education saw to the emergence of radical attempts to reconnect pedagogy with "the real world" and to forge greater social responsibility in architecture. From this epoch of important political, social, and environmental action, this article discusses three "encounters" between…

Bilateral Learning and Teaching in Chinese-Australian Arts and Architecture

ERIC Educational Resources Information Center

Joubert, Lindy; Whitford, Steven

2006-01-01

A collaborative design-based, cross-cultural exchange between the Chinese School of Architecture, Tsinghua University of Beijing, and the Faculty of Architecture, Building, and Planning at the University of Melbourne is the case study presented in this article. Two design studios were conducted: one in the Master of Urban Design program, and the…

Logs Analysis of Adapted Pedagogical Scenarios Generated by a Simulation Serious Game Architecture

ERIC Educational Resources Information Center

Callies, Sophie; Gravel, Mathieu; Beaudry, Eric; Basque, Josianne

2017-01-01

This paper presents an architecture designed for simulation serious games, which automatically generates game-based scenarios adapted to learner's learning progression. We present three central modules of the architecture: (1) the learner model, (2) the adaptation module and (3) the logs module. The learner model estimates the progression of the…

«

9

10

11

12

13

»

«

10

11

12

13

14

»

Mathematical Aspects of Educating Architecture Designers: A College Study

ERIC Educational Resources Information Center

Verner, I. M.; Maor, S.

2005-01-01

This paper considers a second-year Mathematical Aspects in Architectural Design course, which relies on a first-year mathematics course and offers mathematical learning as part of hands-on practice in architecture design studio. The 16-hour course consisted of seminar presentations of mathematics concepts, their application to covering the plane…

STGT program: Ada coding and architecture lessons learned

NASA Technical Reports Server (NTRS)

Usavage, Paul; Nagurney, Don

1992-01-01

STGT (Second TDRSS Ground Terminal) is currently halfway through the System Integration Test phase (Level 4 Testing). To date, many software architecture and Ada language issues have been encountered and solved. This paper, which is the transcript of a presentation at the 3 Dec. meeting, attempts to define these lessons plus others learned regarding software project management and risk management issues, training, performance, reuse, and reliability. Observations are included regarding the use of particular Ada coding constructs, software architecture trade-offs during the prototyping, development and testing stages of the project, and dangers inherent in parallel or concurrent systems, software, hardware, and operations engineering.

Design and Implementation of C-iLearning: A Cloud-Based Intelligent Learning System

ERIC Educational Resources Information Center

Xiao, Jun; Wang, Minjuan; Wang, Lamei; Zhu, Xiaoxiao

2013-01-01

The gradual development of intelligent learning (iLearning) systems has prompted the changes of teaching and learning. This paper presents the architecture of an intelligent learning (iLearning) system built upon the recursive iLearning model and the key technologies associated with this model. Based on this model and the technical structure of a…

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.

Machine learning and predictive data analytics enabling metrology and process control in IC fabrication

NASA Astrophysics Data System (ADS)

Rana, Narender; Zhang, Yunlin; Wall, Donald; Dirahoui, Bachir; Bailey, Todd C.

2015-03-01

Integrate circuit (IC) technology is going through multiple changes in terms of patterning techniques (multiple patterning, EUV and DSA), device architectures (FinFET, nanowire, graphene) and patterning scale (few nanometers). These changes require tight controls on processes and measurements to achieve the required device performance, and challenge the metrology and process control in terms of capability and quality. Multivariate data with complex nonlinear trends and correlations generally cannot be described well by mathematical or parametric models but can be relatively easily learned by computing machines and used to predict or extrapolate. This paper introduces the predictive metrology approach which has been applied to three different applications. Machine learning and predictive analytics have been leveraged to accurately predict dimensions of EUV resist patterns down to 18 nm half pitch leveraging resist shrinkage patterns. These patterns could not be directly and accurately measured due to metrology tool limitations. Machine learning has also been applied to predict the electrical performance early in the process pipeline for deep trench capacitance and metal line resistance. As the wafer goes through various processes its associated cost multiplies. It may take days to weeks to get the electrical performance readout. Predicting the electrical performance early on can be very valuable in enabling timely actionable decision such as rework, scrap, feedforward, feedback predicted information or information derived from prediction to improve or monitor processes. This paper provides a general overview of machine learning and advanced analytics application in the advanced semiconductor development and manufacturing.

Life and Death of a Neuron

MedlinePlus

... free mailed brochure Table of Contents Introduction The Architecture of the Neuron Birth Migration Differentiation Death Hope ... generated neurons in learning and memory. Neuron The Architecture of the Neuron The central nervous system (which ...

In-situ Resource Utilization (ISRU) to Support the Lunar Outpost and the Rationale for Precursor Missions

NASA Technical Reports Server (NTRS)

Simon, Thomas M.

2008-01-01

One of the ways that the Constellation Program can differ from Apollo is to employ a live-off-the-land or In-Situ Resource Utilization (ISRU) supported architecture. The options considered over the past decades for using indigenous materials have varied considerably in terms of what resources to attempt to acquire, how much to acquire, and what the motivations are to acquiring these resources. The latest NASA concepts for supporting the lunar outpost have considered many of these plans and compared these options to customers requirements and desires. Depending on the architecture employed, ISRU technologies can make a significant contribution towards a sustainable and affordable lunar outpost. While extensive ground testing will reduce some mission risk, one or more flight demonstrations prior to the first crew's arrival will build confidence and increase the chance that outpost architects will include ISRU as part of the early outpost architecture. This presentation includes some of the options for using ISRU that are under consideration for the lunar outpost, the precursor missions that would support these applications, and a notional timeline to allow the lessons learned from the precursor missions to support outpost hardware designs.

Efficient Online Learning Algorithms Based on LSTM Neural Networks.

PubMed

Ergen, Tolga; Kozat, Suleyman Serdar

2017-09-13

We investigate online nonlinear regression and introduce novel regression structures based on the long short term memory (LSTM) networks. For the introduced structures, we also provide highly efficient and effective online training methods. To train these novel LSTM-based structures, we put the underlying architecture in a state space form and introduce highly efficient and effective particle filtering (PF)-based updates. We also provide stochastic gradient descent and extended Kalman filter-based updates. Our PF-based training method guarantees convergence to the optimal parameter estimation in the mean square error sense provided that we have a sufficient number of particles and satisfy certain technical conditions. More importantly, we achieve this performance with a computational complexity in the order of the first-order gradient-based methods by controlling the number of particles. Since our approach is generic, we also introduce a gated recurrent unit (GRU)-based approach by directly replacing the LSTM architecture with the GRU architecture, where we demonstrate the superiority of our LSTM-based approach in the sequential prediction task via different real life data sets. In addition, the experimental results illustrate significant performance improvements achieved by the introduced algorithms with respect to the conventional methods over several different benchmark real life data sets.

Mars Reconnaissance Orbiter In-flight Anomalies and Lessons Learned: An Update

NASA Technical Reports Server (NTRS)

Bayer, Todd J.

2008-01-01

The Mars Reconnaissance Orbiter mission has as its primary objectives: advance our understanding of the current Mars climate, the processes that have formed and modified the surface of the planet and the extent to which water has played a role in surface processes; identify sites of possible aqueous activity indicating environments that may have been or are conducive to biological activity; and thus identify and characterize sites for future landed missions; and provide forward and return relay services for current and future Mars landed assets. MRO's crucial role in the long term strategy for Mars exploration requires a high level of reliability during its 5.4 year mission. This requires an architecture which incorporates extensive redundancy and cross-strapping. Because of the distances and hence light-times involved, the spacecraft itself must be able to utilize this redundancy in responding to time-critical failures. For cases where fault protection is unable to recognize a potentially threatening condition, either due to known limitations or software flaws, intervention by ground operations is required. These aspects of MRO's design were discussed in a previous paper [Ref. 1]. This paper provides an update to the original paper, describing MRO's significant in-flight anomalies over the past year, with lessons learned for redundancy and fault protection architectures and for ground operations.

Robotic action acquisition with cognitive biases in coarse-grained state space.

PubMed

Uragami, Daisuke; Kohno, Yu; Takahashi, Tatsuji

2016-07-01

Some of the authors have previously proposed a cognitively inspired reinforcement learning architecture (LS-Q) that mimics cognitive biases in humans. LS-Q adaptively learns under uniform, coarse-grained state division and performs well without parameter tuning in a giant-swing robot task. However, these results were shown only in simulations. In this study, we test the validity of the LS-Q implemented in a robot in a real environment. In addition, we analyze the learning process to elucidate the mechanism by which the LS-Q adaptively learns under the partially observable environment. We argue that the LS-Q may be a versatile reinforcement learning architecture, which is, despite its simplicity, easily applicable and does not require well-prepared settings. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Music Technology Competencies for Education: A Proposal for a Pedagogical Architecture for Distance Learning

ERIC Educational Resources Information Center

Rosas, Fátima Weber; Rocha Machado, Leticia; Behar, Patricia Alejandra

2016-01-01

This article proposes a pedagogical architecture (PA) focused on the development of competencies for music technology in education. This PA used free Web 3.0 technologies, mainly those related to production and musical composition. The pedagogical architecture is geared for teachers and those pursing a teaching degree, working in distance…

An Architecture for Online Laboratory E-Learning System

ERIC Educational Resources Information Center

Duan, Bing; Hosseini, Habib Mir M.; Ling, Keck Voon; Gay, Robert Kheng Leng

2006-01-01

Internet-based learning systems, or e-learning, are widely available in institutes, universities, and industrial companies, hosting regular or continuous education programs. The dream of teaching and learning from anywhere and at anytime becomes a reality due to the construction of e-learning infrastructure. Traditional teaching materials and…

Semi-supervised tracking of extreme weather events in global spatio-temporal climate datasets

NASA Astrophysics Data System (ADS)

Kim, S. K.; Prabhat, M.; Williams, D. N.

2017-12-01

Deep neural networks have been successfully applied to solve problem to detect extreme weather events in large scale climate datasets and attend superior performance that overshadows all previous hand-crafted methods. Recent work has shown that multichannel spatiotemporal encoder-decoder CNN architecture is able to localize events in semi-supervised bounding box. Motivated by this work, we propose new learning metric based on Variational Auto-Encoders (VAE) and Long-Short-Term-Memory (LSTM) to track extreme weather events in spatio-temporal dataset. We consider spatio-temporal object tracking problems as learning probabilistic distribution of continuous latent features of auto-encoder using stochastic variational inference. For this, we assume that our datasets are i.i.d and latent features is able to be modeled by Gaussian distribution. In proposed metric, we first train VAE to generate approximate posterior given multichannel climate input with an extreme climate event at fixed time. Then, we predict bounding box, location and class of extreme climate events using convolutional layers given input concatenating three features including embedding, sampled mean and standard deviation. Lastly, we train LSTM with concatenated input to learn timely information of dataset by recurrently feeding output back to next time-step's input of VAE. Our contribution is two-fold. First, we show the first semi-supervised end-to-end architecture based on VAE to track extreme weather events which can apply to massive scaled unlabeled climate datasets. Second, the information of timely movement of events is considered for bounding box prediction using LSTM which can improve accuracy of localization. To our knowledge, this technique has not been explored neither in climate community or in Machine Learning community.

A Cognitive Neural Architecture Able to Learn and Communicate through Natural Language.

PubMed

Golosio, Bruno; Cangelosi, Angelo; Gamotina, Olesya; Masala, Giovanni Luca

2015-01-01

Communicative interactions involve a kind of procedural knowledge that is used by the human brain for processing verbal and nonverbal inputs and for language production. Although considerable work has been done on modeling human language abilities, it has been difficult to bring them together to a comprehensive tabula rasa system compatible with current knowledge of how verbal information is processed in the brain. This work presents a cognitive system, entirely based on a large-scale neural architecture, which was developed to shed light on the procedural knowledge involved in language elaboration. The main component of this system is the central executive, which is a supervising system that coordinates the other components of the working memory. In our model, the central executive is a neural network that takes as input the neural activation states of the short-term memory and yields as output mental actions, which control the flow of information among the working memory components through neural gating mechanisms. The proposed system is capable of learning to communicate through natural language starting from tabula rasa, without any a priori knowledge of the structure of phrases, meaning of words, role of the different classes of words, only by interacting with a human through a text-based interface, using an open-ended incremental learning process. It is able to learn nouns, verbs, adjectives, pronouns and other word classes, and to use them in expressive language. The model was validated on a corpus of 1587 input sentences, based on literature on early language assessment, at the level of about 4-years old child, and produced 521 output sentences, expressing a broad range of language processing functionalities.

A deep learning framework to discern and count microscopic nematode eggs.

PubMed

Akintayo, Adedotun; Tylka, Gregory L; Singh, Asheesh K; Ganapathysubramanian, Baskar; Singh, Arti; Sarkar, Soumik

2018-06-14

In order to identify and control the menace of destructive pests via microscopic image-based identification state-of-the art deep learning architecture is demonstrated on the parasitic worm, the soybean cyst nematode (SCN), Heterodera glycines. Soybean yield loss is negatively correlated with the density of SCN eggs that are present in the soil. While there has been progress in automating extraction of egg-filled cysts and eggs from soil samples counting SCN eggs obtained from soil samples using computer vision techniques has proven to be an extremely difficult challenge. Here we show that a deep learning architecture developed for rare object identification in clutter-filled images can identify and count the SCN eggs. The architecture is trained with expert-labeled data to effectively build a machine learning model for quantifying SCN eggs via microscopic image analysis. We show dramatic improvements in the quantification time of eggs while maintaining human-level accuracy and avoiding inter-rater and intra-rater variabilities. The nematode eggs are correctly identified even in complex, debris-filled images that are often difficult for experts to identify quickly. Our results illustrate the remarkable promise of applying deep learning approaches to phenotyping for pest assessment and management.

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.

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 classifier systems for single and multiple mobile robots in unstructured environments

NASA Astrophysics Data System (ADS)

Bay, John S.

1995-12-01

The learning classifier system (LCS) is a learning production system that generates behavioral rules via an underlying discovery mechanism. The LCS architecture operates similarly to a blackboard architecture; i.e., by posted-message communications. But in the LCS, the message board is wiped clean at every time interval, thereby requiring no persistent shared resource. In this paper, we adapt the LCS to the problem of mobile robot navigation in completely unstructured environments. We consider the model of the robot itself, including its sensor and actuator structures, to be part of this environment, in addition to the world-model that includes a goal and obstacles at unknown locations. This requires a robot to learn its own I/O characteristics in addition to solving its navigation problem, but results in a learning controller that is equally applicable, unaltered, in robots with a wide variety of kinematic structures and sensing capabilities. We show the effectiveness of this LCS-based controller through both simulation and experimental trials with a small robot. We then propose a new architecture, the Distributed Learning Classifier System (DLCS), which generalizes the message-passing behavior of the LCS from internal messages within a single agent to broadcast massages among multiple agents. This communications mode requires little bandwidth and is easily implemented with inexpensive, off-the-shelf hardware. The DLCS is shown to have potential application as a learning controller for multiple intelligent agents.

Machine learning for real time remote detection

NASA Astrophysics Data System (ADS)

Labbé, Benjamin; Fournier, Jérôme; Henaff, Gilles; Bascle, Bénédicte; Canu, Stéphane

2010-10-01

Infrared systems are key to providing enhanced capability to military forces such as automatic control of threats and prevention from air, naval and ground attacks. Key requirements for such a system to produce operational benefits are real-time processing as well as high efficiency in terms of detection and false alarm rate. These are serious issues since the system must deal with a large number of objects and categories to be recognized (small vehicles, armored vehicles, planes, buildings, etc.). Statistical learning based algorithms are promising candidates to meet these requirements when using selected discriminant features and real-time implementation. This paper proposes a new decision architecture benefiting from recent advances in machine learning by using an effective method for level set estimation. While building decision function, the proposed approach performs variable selection based on a discriminative criterion. Moreover, the use of level set makes it possible to manage rejection of unknown or ambiguous objects thus preserving the false alarm rate. Experimental evidences reported on real world infrared images demonstrate the validity of our approach.

Learning in Artificial Neural Systems

NASA Technical Reports Server (NTRS)

Matheus, Christopher J.; Hohensee, William E.

1987-01-01

This paper presents an overview and analysis of learning in Artificial Neural Systems (ANS's). It begins with a general introduction to neural networks and connectionist approaches to information processing. The basis for learning in ANS's is then described, and compared with classical Machine learning. While similar in some ways, ANS learning deviates from tradition in its dependence on the modification of individual weights to bring about changes in a knowledge representation distributed across connections in a network. This unique form of learning is analyzed from two aspects: the selection of an appropriate network architecture for representing the problem, and the choice of a suitable learning rule capable of reproducing the desired function within the given network. The various network architectures are classified, and then identified with explicit restrictions on the types of functions they are capable of representing. The learning rules, i.e., algorithms that specify how the network weights are modified, are similarly taxonomized, and where possible, the limitations inherent to specific classes of rules are outlined.

«

10

11

12

13

14

»

«

11

12

13

14

15

»

Auto-Associative Recurrent Neural Networks and Long Term Dependencies in Novelty Detection for Audio Surveillance Applications

NASA Astrophysics Data System (ADS)

Rossi, A.; Montefoschi, F.; Rizzo, A.; Diligenti, M.; Festucci, C.

2017-10-01

Machine Learning applied to Automatic Audio Surveillance has been attracting increasing attention in recent years. In spite of several investigations based on a large number of different approaches, little attention had been paid to the environmental temporal evolution of the input signal. In this work, we propose an exploration in this direction comparing the temporal correlations extracted at the feature level with the one learned by a representational structure. To this aim we analysed the prediction performances of a Recurrent Neural Network architecture varying the length of the processed input sequence and the size of the time window used in the feature extraction. Results corroborated the hypothesis that sequential models work better when dealing with data characterized by temporal order. However, so far the optimization of the temporal dimension remains an open issue.

Boosted ARTMAP: modifications to fuzzy ARTMAP motivated by boosting theory.

PubMed

Verzi, Stephen J; Heileman, Gregory L; Georgiopoulos, Michael

2006-05-01

In this paper, several modifications to the Fuzzy ARTMAP neural network architecture are proposed for conducting classification in complex, possibly noisy, environments. The goal of these modifications is to improve upon the generalization performance of Fuzzy ART-based neural networks, such as Fuzzy ARTMAP, in these situations. One of the major difficulties of employing Fuzzy ARTMAP on such learning problems involves over-fitting of the training data. Structural risk minimization is a machine-learning framework that addresses the issue of over-fitting by providing a backbone for analysis as well as an impetus for the design of better learning algorithms. The theory of structural risk minimization reveals a trade-off between training error and classifier complexity in reducing generalization error, which will be exploited in the learning algorithms proposed in this paper. Boosted ART extends Fuzzy ART by allowing the spatial extent of each cluster formed to be adjusted independently. Boosted ARTMAP generalizes upon Fuzzy ARTMAP by allowing non-zero training error in an effort to reduce the hypothesis complexity and hence improve overall generalization performance. Although Boosted ARTMAP is strictly speaking not a boosting algorithm, the changes it encompasses were motivated by the goals that one strives to achieve when employing boosting. Boosted ARTMAP is an on-line learner, it does not require excessive parameter tuning to operate, and it reduces precisely to Fuzzy ARTMAP for particular parameter values. Another architecture described in this paper is Structural Boosted ARTMAP, which uses both Boosted ART and Boosted ARTMAP to perform structural risk minimization learning. Structural Boosted ARTMAP will allow comparison of the capabilities of off-line versus on-line learning as well as empirical risk minimization versus structural risk minimization using Fuzzy ARTMAP-based neural network architectures. Both empirical and theoretical results are presented to enhance the understanding of these architectures.

Meta-Design and the Triple Learning Organization in Architectural Design Process

NASA Astrophysics Data System (ADS)

Barelkowski, Robert

2017-10-01

The paper delves into the improvement of Meta-Design methodology being the result of implementation of triple learning organization. Grown from the concept of reflective practice, it offers an opportunity to segregate and hierarchize both criteria and knowledge management and at least twofold application. It induces constant feedback loops recharging the basic level of “design” with second level of “learning from design” and third level of “learning from learning”. While learning from design reflects the absorption of knowledge, structuralization of skills, management of information, learning from learning gives deeper understanding and provides axiological perspective which is necessary when combining cultural, social, and abstract conceptual problems. The second level involves multidisciplinary applications imported from many engineering disciplines, technical sciences, but also psychological background, or social environment. The third level confronts these applications with their respective sciences (wide extra-architectural knowledge) and axiological issues. This distinction may be represented in difference between e.g. purposeful, systemic use of participatory design which again generates experience-by-doing versus use of disciplinary knowledge starting from its theoretical framework, then narrowed down to be relevant to particular design task. The paper discusses the application in two cases: awarded competition proposal of Digital Arts Museum in Madrid and BAIRI university building. Both cases summarize the effects of implementation and expose the impact of triple-loop knowledge circles onto design, teaching the architect or helping them to learn how to manage information flows and how to accommodate paradigm shifts in the architectural design process.

Neural networks in chemistry

NASA Astrophysics Data System (ADS)

Zupan, Jure

1995-04-01

All problems that in some way are linked to handling of multi-variate experiments versus multi-variate responses can be approached by the group of methods that has recently became known as the artificial neural network (ANN) techniques. In this lecture, the types of the problems that can be solved by ANN techniques rather than the ANN techniques themselves will be addressed first. This issue is rather important due to the fact that the ANN techniques can be used for a very broad range of problems and choosing the wrong method can often result in either a failure to produce an effective solution or in a very time consuming and ineffective handling. Among the types of problems that can be solved by different ANN techniques the classification, mapping, look-up table, and modelling will be emphasized and discussed. Because all mentioned methods can be solved by different standard techniques, special emphasis will be paid to stress the advantages and drawbacks when employing different ANN techniques. Due to the fact that the range of possible use of ANN is so broad, even a very specific problem can be solved by many different ANN architectures or even using different learning strategies within ANN. In the second part the main learning strategies and corresponding choices of ANN architectures will be discussed. In this part the parameters and some guidelines how to select the method and the design of the ANNs will be shown on the examples of reported ANN applications in chemistry. The ANN learning strategies discussed will be back-propagation of errors, the Kohonen, and the counter propagation learning. The potential user of ANN should first, consider the problem, second, he must inspect the availability of data and the data themselves to decide for which ANN method they are best suited. In this respect, the amount of data, the dimensionality of the measurement space, the form of data (alphanumeric entries, binary, real, or even mixed forms of data) are crucial. After considering all this factors, the determination of the appropriate neural network architecture can be made. Additionally, the selection the optimal ANN involves the determination of specific internal parameters like the learning rate, the momentum term, the neighbourhood function, the time dependent decrease of corrections, etc. Even after all these decisions have been made the learning procedure itself is not a straightforward task. Here, the division of the entire ensemble of data into three data sets: training, controlling and the test set are crucial. This problem is addressed as well.

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.

DeepX: Deep Learning Accelerator for Restricted Boltzmann Machine Artificial Neural Networks.

PubMed

Kim, Lok-Won

2018-05-01

Although there have been many decades of research and commercial presence on high performance general purpose processors, there are still many applications that require fully customized hardware architectures for further computational acceleration. Recently, deep learning has been successfully used to learn in a wide variety of applications, but their heavy computation demand has considerably limited their practical applications. This paper proposes a fully pipelined acceleration architecture to alleviate high computational demand of an artificial neural network (ANN) which is restricted Boltzmann machine (RBM) ANNs. The implemented RBM ANN accelerator (integrating network size, using 128 input cases per batch, and running at a 303-MHz clock frequency) integrated in a state-of-the art field-programmable gate array (FPGA) (Xilinx Virtex 7 XC7V-2000T) provides a computational performance of 301-billion connection-updates-per-second and about 193 times higher performance than a software solution running on general purpose processors. Most importantly, the architecture enables over 4 times (12 times in batch learning) higher performance compared with a previous work when both are implemented in an FPGA device (XC2VP70).

Electrical and computer architecture of an autonomous Mars sample return rover prototype

NASA Astrophysics Data System (ADS)

Leslie, Caleb Thomas

Space truly is the final frontier. As man looks to explore beyond the confines of our planet, we use the lessons learned from traveling to the Moon and orbiting in the International Space Station, and we set our sights upon Mars. For decades, Martian probes consisting of orbiters, landers, and even robotic rovers have been sent to study Mars. Their discoveries have yielded a wealth of new scientific knowledge regarding the Martian environment and the secrets it holds. Armed with this knowledge, NASA and others have begun preparations to send humans to Mars with the ultimate goal of colonization and permanent human habitation. The ultimate success of any long term manned mission to Mars will require in situ resource utilization techniques and technologies to both support their stay and make a return trip to Earth viable. A sample return mission to Mars will play a pivotal role in developing these necessary technologies to ensure such an endeavor to be a successful one. This thesis describes an electrical and computer architecture for autonomous robotic applications. The architecture is one that is modular, scalable, and adaptable. These traits are achieved by maximizing commonality and reusability within modules that can be added, removed, or reconfigured within the system. This architecture, called the Modular Architecture for Autonomous Robotic Systems (MAARS), was implemented on the University of Alabama's Collection and Extraction Rover for Extraterrestrial Samples (CERES). The CERES rover competed in the 2016 NASA Sample Return Robot Challenge where robots were tasked with autonomously finding, collecting, and returning samples to the landing site.

Autonomous self-configuration of artificial neural networks for data classification or system control

NASA Astrophysics Data System (ADS)

Fink, Wolfgang

2009-05-01

Artificial neural networks (ANNs) are powerful methods for the classification of multi-dimensional data as well as for the control of dynamic systems. In general terms, ANNs consist of neurons that are, e.g., arranged in layers and interconnected by real-valued or binary neural couplings or weights. ANNs try mimicking the processing taking place in biological brains. The classification and generalization capabilities of ANNs are given by the interconnection architecture and the coupling strengths. To perform a certain classification or control task with a particular ANN architecture (i.e., number of neurons, number of layers, etc.), the inter-neuron couplings and their accordant coupling strengths must be determined (1) either by a priori design (i.e., manually) or (2) using training algorithms such as error back-propagation. The more complex the classification or control task, the less obvious it is how to determine an a priori design of an ANN, and, as a consequence, the architecture choice becomes somewhat arbitrary. Furthermore, rather than being able to determine for a given architecture directly the corresponding coupling strengths necessary to perform the classification or control task, these have to be obtained/learned through training of the ANN on test data. We report on the use of a Stochastic Optimization Framework (SOF; Fink, SPIE 2008) for the autonomous self-configuration of Artificial Neural Networks (i.e., the determination of number of hidden layers, number of neurons per hidden layer, interconnections between neurons, and respective coupling strengths) for performing classification or control tasks. This may provide an approach towards cognizant and self-adapting computing architectures and systems.

Freight data architecture business process, logical data model, and physical data model.

DOT National Transportation Integrated Search

2014-09-01

This document summarizes the study teams efforts to establish data-sharing partnerships : and relay the lessons learned. In addition, it provides information on a prototype freight data : architecture and supporting description and specifications ...

Service Oriented Robotic Architecture for Space Robotics: Design, Testing, and Lessons Learned

NASA Technical Reports Server (NTRS)

Fluckiger, Lorenzo Jean Marc E; Utz, Hans Heinrich

2013-01-01

This paper presents the lessons learned from six years of experiments with planetary rover prototypes running the Service Oriented Robotic Architecture (SORA) developed by the Intelligent Robotics Group (IRG) at the NASA Ames Research Center. SORA relies on proven software engineering methods and technologies applied to space robotics. Based on a Service Oriented Architecture and robust middleware, SORA encompasses on-board robot control and a full suite of software tools necessary for remotely operated exploration missions. SORA has been eld tested in numerous scenarios of robotic lunar and planetary exploration. The experiments conducted by IRG with SORA exercise a large set of the constraints encountered in space applications: remote robotic assets, ight relevant science instruments, distributed operations, high network latencies and unreliable or intermittent communication links. In this paper, we present the results of these eld tests in regard to the developed architecture, and discuss its bene ts and limitations.

Learning, memory, and the role of neural network architecture.

PubMed

Hermundstad, Ann M; Brown, Kevin S; Bassett, Danielle S; Carlson, Jean M

2011-06-01

The performance of information processing systems, from artificial neural networks to natural neuronal ensembles, depends heavily on the underlying system architecture. In this study, we compare the performance of parallel and layered network architectures during sequential tasks that require both acquisition and retention of information, thereby identifying tradeoffs between learning and memory processes. During the task of supervised, sequential function approximation, networks produce and adapt representations of external information. Performance is evaluated by statistically analyzing the error in these representations while varying the initial network state, the structure of the external information, and the time given to learn the information. We link performance to complexity in network architecture by characterizing local error landscape curvature. We find that variations in error landscape structure give rise to tradeoffs in performance; these include the ability of the network to maximize accuracy versus minimize inaccuracy and produce specific versus generalizable representations of information. Parallel networks generate smooth error landscapes with deep, narrow minima, enabling them to find highly specific representations given sufficient time. While accurate, however, these representations are difficult to generalize. In contrast, layered networks generate rough error landscapes with a variety of local minima, allowing them to quickly find coarse representations. Although less accurate, these representations are easily adaptable. The presence of measurable performance tradeoffs in both layered and parallel networks has implications for understanding the behavior of a wide variety of natural and artificial learning systems.

All-memristive neuromorphic computing with level-tuned neurons

NASA Astrophysics Data System (ADS)

Pantazi, Angeliki; Woźniak, Stanisław; Tuma, Tomas; Eleftheriou, Evangelos

2016-09-01

In the new era of cognitive computing, systems will be able to learn and interact with the environment in ways that will drastically enhance the capabilities of current processors, especially in extracting knowledge from vast amount of data obtained from many sources. Brain-inspired neuromorphic computing systems increasingly attract research interest as an alternative to the classical von Neumann processor architecture, mainly because of the coexistence of memory and processing units. In these systems, the basic components are neurons interconnected by synapses. The neurons, based on their nonlinear dynamics, generate spikes that provide the main communication mechanism. The computational tasks are distributed across the neural network, where synapses implement both the memory and the computational units, by means of learning mechanisms such as spike-timing-dependent plasticity. In this work, we present an all-memristive neuromorphic architecture comprising neurons and synapses realized by using the physical properties and state dynamics of phase-change memristors. The architecture employs a novel concept of interconnecting the neurons in the same layer, resulting in level-tuned neuronal characteristics that preferentially process input information. We demonstrate the proposed architecture in the tasks of unsupervised learning and detection of multiple temporal correlations in parallel input streams. The efficiency of the neuromorphic architecture along with the homogenous neuro-synaptic dynamics implemented with nanoscale phase-change memristors represent a significant step towards the development of ultrahigh-density neuromorphic co-processors.

All-memristive neuromorphic computing with level-tuned neurons.

PubMed

Pantazi, Angeliki; Woźniak, Stanisław; Tuma, Tomas; Eleftheriou, Evangelos

2016-09-02

In the new era of cognitive computing, systems will be able to learn and interact with the environment in ways that will drastically enhance the capabilities of current processors, especially in extracting knowledge from vast amount of data obtained from many sources. Brain-inspired neuromorphic computing systems increasingly attract research interest as an alternative to the classical von Neumann processor architecture, mainly because of the coexistence of memory and processing units. In these systems, the basic components are neurons interconnected by synapses. The neurons, based on their nonlinear dynamics, generate spikes that provide the main communication mechanism. The computational tasks are distributed across the neural network, where synapses implement both the memory and the computational units, by means of learning mechanisms such as spike-timing-dependent plasticity. In this work, we present an all-memristive neuromorphic architecture comprising neurons and synapses realized by using the physical properties and state dynamics of phase-change memristors. The architecture employs a novel concept of interconnecting the neurons in the same layer, resulting in level-tuned neuronal characteristics that preferentially process input information. We demonstrate the proposed architecture in the tasks of unsupervised learning and detection of multiple temporal correlations in parallel input streams. The efficiency of the neuromorphic architecture along with the homogenous neuro-synaptic dynamics implemented with nanoscale phase-change memristors represent a significant step towards the development of ultrahigh-density neuromorphic co-processors.

The Architect, the Museum, and the School: Working Together to Incorporate Architecture and Built Environment Education into the Curriculum

ERIC Educational Resources Information Center

Chalas, Agnieszka

2015-01-01

This article documents an innovative project at the Canadian Centre for Architecture (CCA) that placed teaching architects in six underprivileged elementary schools in Montreal in an effort to both improve the status of architectural education in schools and support teachers with integrating museum learning into the classroom. Throughout the…

A Biologically Plausible Action Selection System for Cognitive Architectures: Implications of Basal Ganglia Anatomy for Learning and Decision-Making Models

ERIC Educational Resources Information Center

Stocco, Andrea

2018-01-01

Several attempts have been made previously to provide a biological grounding for cognitive architectures by relating their components to the computations of specific brain circuits. Often, the architecture's action selection system is identified with the basal ganglia. However, this identification overlooks one of the most important features of…

Assessment Focus in Studio: What Is Most Prominent in Architecture, Art and Design?

ERIC Educational Resources Information Center

de La Harpe, Barbara; Peterson, J. Fiona; Frankham, Noel; Zehner, Robert; Neale, Douglas; Musgrave, Elizabeth; McDermott, Ruth

2009-01-01

What can be learned about assessment from what educators in the creative practices focus their studio publications on? What should form the focus of assessment in architecture, art and design studios? In this article we draw on 118 journal articles on studio published over the last decade in three disciplines; architecture, art and design to…

From E-Learning Space to E-Learning Place

ERIC Educational Resources Information Center

Wahlstedt, Ari; Pekkola, Samuli; Niemela, Marketta

2008-01-01

In this paper, it is argued that e-learning environments are currently more like "buildings", i.e., learning spaces, rather than "schools", i.e., places for learning. The concepts originated from architecture and urban design, where they are used both to distinguish static spaces from inhabited places, and more importantly, as design objectives.…

Distributed Learning Metadata Standards

ERIC Educational Resources Information Center

McClelland, Marilyn

2004-01-01

Significant economies can be achieved in distributed learning systems architected with a focus on interoperability and reuse. The key building blocks of an efficient distributed learning architecture are the use of standards and XML technologies. The goal of plug and play capability among various components of a distributed learning system…

Participative Knowledge Production of Learning Objects for E-Books.

ERIC Educational Resources Information Center

Dodero, Juan Manuel; Aedo, Ignacio; Diaz, Paloma

2002-01-01

Defines a learning object as any digital resource that can be reused to support learning and thus considers electronic books as learning objects. Highlights include knowledge management; participative knowledge production, i.e. authoring electronic books by a distributed group of authors; participative knowledge production architecture; and…

A Long Short-Term Memory deep learning network for the prediction of epileptic seizures using EEG signals.

PubMed

Tsiouris, Κostas Μ; Pezoulas, Vasileios C; Zervakis, Michalis; Konitsiotis, Spiros; Koutsouris, Dimitrios D; Fotiadis, Dimitrios I

2018-05-17

The electroencephalogram (EEG) is the most prominent means to study epilepsy and capture changes in electrical brain activity that could declare an imminent seizure. In this work, Long Short-Term Memory (LSTM) networks are introduced in epileptic seizure prediction using EEG signals, expanding the use of deep learning algorithms with convolutional neural networks (CNN). A pre-analysis is initially performed to find the optimal architecture of the LSTM network by testing several modules and layers of memory units. Based on these results, a two-layer LSTM network is selected to evaluate seizure prediction performance using four different lengths of preictal windows, ranging from 15 min to 2 h. The LSTM model exploits a wide range of features extracted prior to classification, including time and frequency domain features, between EEG channels cross-correlation and graph theoretic features. The evaluation is performed using long-term EEG recordings from the open CHB-MIT Scalp EEG database, suggest that the proposed methodology is able to predict all 185 seizures, providing high rates of seizure prediction sensitivity and low false prediction rates (FPR) of 0.11-0.02 false alarms per hour, depending on the duration of the preictal window. The proposed LSTM-based methodology delivers a significant increase in seizure prediction performance compared to both traditional machine learning techniques and convolutional neural networks that have been previously evaluated in the literature. Copyright © 2018 Elsevier Ltd. All rights reserved.

«

11

12

13

14

15

»

«

12

13

14

15

16

»

Toward Self-Referential Autonomous Learning of Object and Situation Models.

PubMed

Damerow, Florian; Knoblauch, Andreas; Körner, Ursula; Eggert, Julian; Körner, Edgar

2016-01-01

Most current approaches to scene understanding lack the capability to adapt object and situation models to behavioral needs not anticipated by the human system designer. Here, we give a detailed description of a system architecture for self-referential autonomous learning which enables the refinement of object and situation models during operation in order to optimize behavior. This includes structural learning of hierarchical models for situations and behaviors that is triggered by a mismatch between expected and actual action outcome. Besides proposing architectural concepts, we also describe a first implementation of our system within a simulated traffic scenario to demonstrate the feasibility of our approach.

Layered Learning in Multi-Agent Systems

DTIC Science & Technology

1998-12-15

project almost from the beginning has tirelessly experimented with different robot architectures, always managing to pull things together and create...TEAM MEMBER AGENT ARCHITECTURE I " ! Midfielder, Left : • i ) ( ^ J Goalie , Center Home Coordinates Home Range Max Range Figure

A Novel Robot System Integrating Biological and Mechanical Intelligence Based on Dissociated Neural Network-Controlled Closed-Loop Environment.

PubMed

Li, Yongcheng; Sun, Rong; Wang, Yuechao; Li, Hongyi; Zheng, Xiongfei

2016-01-01

We propose the architecture of a novel robot system merging biological and artificial intelligence based on a neural controller connected to an external agent. We initially built a framework that connected the dissociated neural network to a mobile robot system to implement a realistic vehicle. The mobile robot system characterized by a camera and two-wheeled robot was designed to execute the target-searching task. We modified a software architecture and developed a home-made stimulation generator to build a bi-directional connection between the biological and the artificial components via simple binomial coding/decoding schemes. In this paper, we utilized a specific hierarchical dissociated neural network for the first time as the neural controller. Based on our work, neural cultures were successfully employed to control an artificial agent resulting in high performance. Surprisingly, under the tetanus stimulus training, the robot performed better and better with the increasement of training cycle because of the short-term plasticity of neural network (a kind of reinforced learning). Comparing to the work previously reported, we adopted an effective experimental proposal (i.e. increasing the training cycle) to make sure of the occurrence of the short-term plasticity, and preliminarily demonstrated that the improvement of the robot's performance could be caused independently by the plasticity development of dissociated neural network. This new framework may provide some possible solutions for the learning abilities of intelligent robots by the engineering application of the plasticity processing of neural networks, also for the development of theoretical inspiration for the next generation neuro-prostheses on the basis of the bi-directional exchange of information within the hierarchical neural networks.

A Novel Robot System Integrating Biological and Mechanical Intelligence Based on Dissociated Neural Network-Controlled Closed-Loop Environment

PubMed Central

Wang, Yuechao; Li, Hongyi; Zheng, Xiongfei

2016-01-01

We propose the architecture of a novel robot system merging biological and artificial intelligence based on a neural controller connected to an external agent. We initially built a framework that connected the dissociated neural network to a mobile robot system to implement a realistic vehicle. The mobile robot system characterized by a camera and two-wheeled robot was designed to execute the target-searching task. We modified a software architecture and developed a home-made stimulation generator to build a bi-directional connection between the biological and the artificial components via simple binomial coding/decoding schemes. In this paper, we utilized a specific hierarchical dissociated neural network for the first time as the neural controller. Based on our work, neural cultures were successfully employed to control an artificial agent resulting in high performance. Surprisingly, under the tetanus stimulus training, the robot performed better and better with the increasement of training cycle because of the short-term plasticity of neural network (a kind of reinforced learning). Comparing to the work previously reported, we adopted an effective experimental proposal (i.e. increasing the training cycle) to make sure of the occurrence of the short-term plasticity, and preliminarily demonstrated that the improvement of the robot’s performance could be caused independently by the plasticity development of dissociated neural network. This new framework may provide some possible solutions for the learning abilities of intelligent robots by the engineering application of the plasticity processing of neural networks, also for the development of theoretical inspiration for the next generation neuro-prostheses on the basis of the bi-directional exchange of information within the hierarchical neural networks. PMID:27806074

Lessons Learned while Exploring Cloud-Native Architectures for NASA EOSDIS Applications and Systems

NASA Astrophysics Data System (ADS)

Pilone, D.

2016-12-01

As new, high data rate missions begin collecting data, the NASA's Earth Observing System Data and Information System (EOSDIS) archive is projected to grow roughly 20x to over 300PBs by 2025. To prepare for the dramatic increase in data and enable broad scientific inquiry into larger time series and datasets, NASA has been exploring the impact of applying cloud technologies throughout EOSDIS. In this talk we will provide an overview of NASA's prototyping and lessons learned in applying cloud architectures to: Highly scalable and extensible ingest and archive of EOSDIS data Going "all-in" on cloud based application architectures including "serverless" data processing pipelines and evaluating approaches to vendor-lock in Rethinking data distribution and approaches to analysis in a cloud environment Incorporating and enforcing security controls while minimizing the barrier for research efforts to deploy to NASA compliant, operational environments. NASA's Earth Observing System (EOS) is a coordinated series of satellites for long term global observations. NASA's Earth Observing System Data and Information System (EOSDIS) is a multi-petabyte-scale archive of environmental data that supports global climate change research by providing end-to-end services from EOS instrument data collection to science data processing to full access to EOS and other earth science data. On a daily basis, the EOSDIS ingests, processes, archives and distributes over 3 terabytes of data from NASA's Earth Science missions representing over 6000 data products ranging from various types of science disciplines. EOSDIS has continually evolved to improve the discoverability, accessibility, and usability of high-impact NASA data spanning the multi-petabyte-scale archive of Earth science data products.

Architectures for Developing Multiuser, Immersive Learning Scenarios

ERIC Educational Resources Information Center

Nadolski, Rob J.; Hummel, Hans G. K.; Slootmaker, Aad; van der Vegt, Wim

2012-01-01

Multiuser immersive learning scenarios hold strong potential for lifelong learning as they can support the acquisition of higher order skills in an effective, efficient, and attractive way. Existing virtual worlds, game development platforms, and game engines only partly cater for the proliferation of such learning scenarios as they are often…

Architecture for Building Conversational Agents that Support Collaborative Learning

ERIC Educational Resources Information Center

Kumar, R.; Rose, C. P.

2011-01-01

Tutorial Dialog Systems that employ Conversational Agents (CAs) to deliver instructional content to learners in one-on-one tutoring settings have been shown to be effective in multiple learning domains by multiple research groups. Our work focuses on extending this successful learning technology to collaborative learning settings involving two or…

Learning Dispositions and the Role of Mutual Engagement: Factors for Consideration in Educational Settings

ERIC Educational Resources Information Center

Duncan, Judith; Jones, Carolyn; Carr, Margaret

2008-01-01

This article describes an emerging theoretical framework for examining relationships between learning dispositions and learning architecture. Three domains of learning dispositions--resilience, reciprocity and imagination--are discussed in relation to the structures and processes of early childhood education settings and new entrant classrooms.…

Refining the Ares V Design to Carry Out NASA's Exploration Initiative

NASA Technical Reports Server (NTRS)

Creech, Steve

2008-01-01

NASA's Ares V cargo launch vehicle is part of an overall architecture for u.S. space exploration that will span decades. The Ares V, together with the Ares I crew launch vehicle, Orion crew exploration vehicle and Altair lunar lander, will carry out the national policy goals of retiring the Space Shuttle, completing the International Space Station program, and expanding exploration of the Moon as a steps toward eventual human exploration of Mars. The Ares fleet (Figure 1) is the product of the Exploration Systems Architecture study which, in the wake of the Columbia accident, recommended separating crew from cargo transportation. Both vehicles are undergoing rigorous systems design to maximize safety, reliability, and operability. They take advantage of the best technical and operational lessons learned from the Apollo, Space Shuttle and more recent programs. NASA also seeks to maximize commonality between the crew and cargo vehicles in an effort to simplify and reduce operational costs for sustainable, long-term exploration.

Mobile robot navigation modulated by artificial emotions.

PubMed

Lee-Johnson, C P; Carnegie, D A

2010-04-01

For artificial intelligence research to progress beyond the highly specialized task-dependent implementations achievable today, researchers may need to incorporate aspects of biological behavior that have not traditionally been associated with intelligence. Affective processes such as emotions may be crucial to the generalized intelligence possessed by humans and animals. A number of robots and autonomous agents have been created that can emulate human emotions, but the majority of this research focuses on the social domain. In contrast, we have developed a hybrid reactive/deliberative architecture that incorporates artificial emotions to improve the general adaptive performance of a mobile robot for a navigation task. Emotions are active on multiple architectural levels, modulating the robot's decisions and actions to suit the context of its situation. Reactive emotions interact with the robot's control system, altering its parameters in response to appraisals from short-term sensor data. Deliberative emotions are learned associations that bias path planning in response to eliciting objects or events. Quantitative results are presented that demonstrate situations in which each artificial emotion can be beneficial to performance.

Activity-dependent synaptic plasticity of a chalcogenide electronic synapse for neuromorphic systems.

PubMed

Li, Yi; Zhong, Yingpeng; Zhang, Jinjian; Xu, Lei; Wang, Qing; Sun, Huajun; Tong, Hao; Cheng, Xiaoming; Miao, Xiangshui

2014-05-09

Nanoscale inorganic electronic synapses or synaptic devices, which are capable of emulating the functions of biological synapses of brain neuronal systems, are regarded as the basic building blocks for beyond-Von Neumann computing architecture, combining information storage and processing. Here, we demonstrate a Ag/AgInSbTe/Ag structure for chalcogenide memristor-based electronic synapses. The memristive characteristics with reproducible gradual resistance tuning are utilised to mimic the activity-dependent synaptic plasticity that serves as the basis of memory and learning. Bidirectional long-term Hebbian plasticity modulation is implemented by the coactivity of pre- and postsynaptic spikes, and the sign and degree are affected by assorted factors including the temporal difference, spike rate and voltage. Moreover, synaptic saturation is observed to be an adjustment of Hebbian rules to stabilise the growth of synaptic weights. Our results may contribute to the development of highly functional plastic electronic synapses and the further construction of next-generation parallel neuromorphic computing architecture.

Sculpting the Intrinsic Modular Organization of Spontaneous Brain Activity by Art.

PubMed

Lin, Chia-Shu; Liu, Yong; Huang, Wei-Yuan; Lu, Chia-Feng; Teng, Shin; Ju, Tzong-Ching; He, Yong; Wu, Yu-Te; Jiang, Tianzi; Hsieh, Jen-Chuen

2013-01-01

Artistic training is a complex learning that requires the meticulous orchestration of sophisticated polysensory, motor, cognitive, and emotional elements of mental capacity to harvest an aesthetic creation. In this study, we investigated the architecture of the resting-state functional connectivity networks from professional painters, dancers and pianists. Using a graph-based network analysis, we focused on the art-related changes of modular organization and functional hubs in the resting-state functional connectivity network. We report that the brain architecture of artists consists of a hierarchical modular organization where art-unique and artistic form-specific brain states collectively mirror the mind states of virtuosos. We show that even in the resting state, this type of extraordinary and long-lasting training can macroscopically imprint a neural network system of spontaneous activity in which the related brain regions become functionally and topologically modularized in both domain-general and domain-specific manners. The attuned modularity reflects a resilient plasticity nurtured by long-term experience.

Sculpting the Intrinsic Modular Organization of Spontaneous Brain Activity by Art

PubMed Central

Lin, Chia-Shu; Liu, Yong; Huang, Wei-Yuan; Lu, Chia-Feng; Teng, Shin; Ju, Tzong-Ching; He, Yong; Wu, Yu-Te; Jiang, Tianzi; Hsieh, Jen-Chuen

2013-01-01

Artistic training is a complex learning that requires the meticulous orchestration of sophisticated polysensory, motor, cognitive, and emotional elements of mental capacity to harvest an aesthetic creation. In this study, we investigated the architecture of the resting-state functional connectivity networks from professional painters, dancers and pianists. Using a graph-based network analysis, we focused on the art-related changes of modular organization and functional hubs in the resting-state functional connectivity network. We report that the brain architecture of artists consists of a hierarchical modular organization where art-unique and artistic form-specific brain states collectively mirror the mind states of virtuosos. We show that even in the resting state, this type of extraordinary and long-lasting training can macroscopically imprint a neural network system of spontaneous activity in which the related brain regions become functionally and topologically modularized in both domain-general and domain-specific manners. The attuned modularity reflects a resilient plasticity nurtured by long-term experience. PMID:23840527

Design of a biochemical circuit motif for learning linear functions

PubMed Central

Lakin, Matthew R.; Minnich, Amanda; Lane, Terran; Stefanovic, Darko

2014-01-01

Learning and adaptive behaviour are fundamental biological processes. A key goal in the field of bioengineering is to develop biochemical circuit architectures with the ability to adapt to dynamic chemical environments. Here, we present a novel design for a biomolecular circuit capable of supervised learning of linear functions, using a model based on chemical reactions catalysed by DNAzymes. To achieve this, we propose a novel mechanism of maintaining and modifying internal state in biochemical systems, thereby advancing the state of the art in biomolecular circuit architecture. We use simulations to demonstrate that the circuit is capable of learning behaviour and assess its asymptotic learning performance, scalability and robustness to noise. Such circuits show great potential for building autonomous in vivo nanomedical devices. While such a biochemical system can tell us a great deal about the fundamentals of learning in living systems and may have broad applications in biomedicine (e.g. autonomous and adaptive drugs), it also offers some intriguing challenges and surprising behaviours from a machine learning perspective. PMID:25401175

Design of a biochemical circuit motif for learning linear functions.

PubMed

Lakin, Matthew R; Minnich, Amanda; Lane, Terran; Stefanovic, Darko

2014-12-06

Learning and adaptive behaviour are fundamental biological processes. A key goal in the field of bioengineering is to develop biochemical circuit architectures with the ability to adapt to dynamic chemical environments. Here, we present a novel design for a biomolecular circuit capable of supervised learning of linear functions, using a model based on chemical reactions catalysed by DNAzymes. To achieve this, we propose a novel mechanism of maintaining and modifying internal state in biochemical systems, thereby advancing the state of the art in biomolecular circuit architecture. We use simulations to demonstrate that the circuit is capable of learning behaviour and assess its asymptotic learning performance, scalability and robustness to noise. Such circuits show great potential for building autonomous in vivo nanomedical devices. While such a biochemical system can tell us a great deal about the fundamentals of learning in living systems and may have broad applications in biomedicine (e.g. autonomous and adaptive drugs), it also offers some intriguing challenges and surprising behaviours from a machine learning perspective.

Lessons Learned while Exploring Cloud-Native Architectures for NASA EOSDIS Applications and Systems

NASA Technical Reports Server (NTRS)

Pilone, Dan

2016-01-01

As new, high data rate missions begin collecting data, the NASAs Earth Observing System Data and Information System (EOSDIS) archive is projected to grow roughly 20x to over 300PBs by 2025. To prepare for the dramatic increase in data and enable broad scientific inquiry into larger time series and datasets, NASA has been exploring the impact of applying cloud technologies throughout EOSDIS. In this talk we will provide an overview of NASAs prototyping and lessons learned in applying cloud architectures.

Structure identification in fuzzy inference using reinforcement learning

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.; Khedkar, Pratap

1993-01-01

In our previous work on the GARIC architecture, we have shown that the system can start with surface structure of the knowledge base (i.e., the linguistic expression of the rules) and learn the deep structure (i.e., the fuzzy membership functions of the labels used in the rules) by using reinforcement learning. Assuming the surface structure, GARIC refines the fuzzy membership functions used in the consequents of the rules using a gradient descent procedure. This hybrid fuzzy logic and reinforcement learning approach can learn to balance a cart-pole system and to backup a truck to its docking location after a few trials. In this paper, we discuss how to do structure identification using reinforcement learning in fuzzy inference systems. This involves identifying both surface as well as deep structure of the knowledge base. The term set of fuzzy linguistic labels used in describing the values of each control variable must be derived. In this process, splitting a label refers to creating new labels which are more granular than the original label and merging two labels creates a more general label. Splitting and merging of labels directly transform the structure of the action selection network used in GARIC by increasing or decreasing the number of hidden layer nodes.

Challenges for Deploying Man-Portable Robots into Hostile Environments

DTIC Science & Technology

2000-11-01

video, JAUGS , MDARS 1. BACKGROUND In modern-day warfare the most likely battlefield is an urban environment, which poses many threats to today’s...teleoperation, reconnaissance, surveillance, digital video, JAUGS , MDARS 15. SUBJECT TERMS 16. SECURITY CLASSIFICATION OF: 17. LIMITATION OF ABSTRACT 18...Architecture (MRHA) and the Joint Architecture for Unmanned Ground Systems ( JAUGS ). The hybrid architecture is termed SMART for Small Robotic Technology. It

Healthy eating design guidelines for school architecture.

PubMed

Huang, Terry T-K; Sorensen, Dina; Davis, Steven; Frerichs, Leah; Brittin, Jeri; Celentano, Joseph; Callahan, Kelly; Trowbridge, Matthew J

2013-01-01

We developed a new tool, Healthy Eating Design Guidelines for School Architecture, to provide practitioners in architecture and public health with a practical set of spatially organized and theory-based strategies for making school environments more conducive to learning about and practicing healthy eating by optimizing physical resources and learning spaces. The design guidelines, developed through multidisciplinary collaboration, cover 10 domains of the school food environment (eg, cafeteria, kitchen, garden) and 5 core healthy eating design principles. A school redesign project in Dillwyn, Virginia, used the tool to improve the schools' ability to adopt a healthy nutrition curriculum and promote healthy eating. The new tool, now in a pilot version, is expected to evolve as its components are tested and evaluated through public health and design research.

Short-term total sleep deprivation alters delay-conditioned memory in the rat.

PubMed

Tripathi, Shweta; Jha, Sushil K

2016-06-01

Short-term sleep deprivation soon after training may impair memory consolidation. Also, a particular sleep stage or its components increase after learning some tasks, such as negative and positive reinforcement tasks, avoidance tasks, and spatial learning tasks, and so forth. It suggests that discrete memory types may require specific sleep stage or its components for their optimal processing. The classical conditioning paradigms are widely used to study learning and memory but the role of sleep in a complex conditioned learning is unclear. Here, we have investigated the effects of short-term sleep deprivation on the consolidation of delay-conditioned memory and the changes in sleep architecture after conditioning. Rats were trained for the delay-conditioned task (for conditioning, house-light [conditioned stimulus] was paired with fruit juice [unconditioned stimulus]). Animals were divided into 3 groups: (a) sleep deprived (SD); (b) nonsleep deprived (NSD); and (c) stress control (SC) groups. Two-way ANOVA revealed a significant interaction between groups and days (training and testing) during the conditioned stimulus-unconditioned stimulus presentation. Further, Tukey post hoc comparison revealed that the NSD and SC animals exhibited significant increase in performances during testing. The SD animals, however, performed significantly less during testing. Further, we observed that wakefulness and NREM sleep did not change after training and testing. Interestingly, REM sleep increased significantly on both days compared to baseline more specifically during the initial 4-hr time window after conditioning. Our results suggest that the consolidation of delay-conditioned memory is sleep-dependent and requires augmented REM sleep during an explicit time window soon after training. (PsycINFO Database Record (c) 2016 APA, all rights reserved).

«

12

13

14

15

16

»

«

13

14

15

16

17

»

An Autonomous Mobile Agent-Based Distributed Learning Architecture-A Proposal and Analytical Analysis

ERIC Educational Resources Information Center

Sadiig, I. Ahmed M. J.

2005-01-01

The traditional learning paradigm involving face-to-face interaction with students is shifting to highly data-intensive electronic learning with the advances in Information and Communication Technology. An important component of the e-learning process is the delivery of the learning contents to their intended audience over a network. A distributed…

Computer Architects.

ERIC Educational Resources Information Center

Betts, Janelle Lyon

2001-01-01

Describes a high school art assignment in which students utilize Appleworks or Claris Works to design their own house, after learning about architectural styles and how to use the computer program. States that the project develops student computer skills and increases student knowledge about architecture. (CMK)

Nonvolatile Memory Materials for Neuromorphic Intelligent Machines.

PubMed

Jeong, Doo Seok; Hwang, Cheol Seong

2018-04-18

Recent progress in deep learning extends the capability of artificial intelligence to various practical tasks, making the deep neural network (DNN) an extremely versatile hypothesis. While such DNN is virtually built on contemporary data centers of the von Neumann architecture, physical (in part) DNN of non-von Neumann architecture, also known as neuromorphic computing, can remarkably improve learning and inference efficiency. Particularly, resistance-based nonvolatile random access memory (NVRAM) highlights its handy and efficient application to the multiply-accumulate (MAC) operation in an analog manner. Here, an overview is given of the available types of resistance-based NVRAMs and their technological maturity from the material- and device-points of view. Examples within the strategy are subsequently addressed in comparison with their benchmarks (virtual DNN in deep learning). A spiking neural network (SNN) is another type of neural network that is more biologically plausible than the DNN. The successful incorporation of resistance-based NVRAM in SNN-based neuromorphic computing offers an efficient solution to the MAC operation and spike timing-based learning in nature. This strategy is exemplified from a material perspective. Intelligent machines are categorized according to their architecture and learning type. Also, the functionality and usefulness of NVRAM-based neuromorphic computing are addressed. © 2018 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

A Systems Approach to Developing an Affordable Space Ground Transportation Architecture using a Commonality Approach

NASA Technical Reports Server (NTRS)

Garcia, Jerry L.; McCleskey, Carey M.; Bollo, Timothy R.; Rhodes, Russel E.; Robinson, John W.

2012-01-01

This paper presents a structured approach for achieving a compatible Ground System (GS) and Flight System (FS) architecture that is affordable, productive and sustainable. This paper is an extension of the paper titled "Approach to an Affordable and Productive Space Transportation System" by McCleskey et al. This paper integrates systems engineering concepts and operationally efficient propulsion system concepts into a structured framework for achieving GS and FS compatibility in the mid-term and long-term time frames. It also presents a functional and quantitative relationship for assessing system compatibility called the Architecture Complexity Index (ACI). This paper: (1) focuses on systems engineering fundamentals as it applies to improving GS and FS compatibility; (2) establishes mid-term and long-term spaceport goals; (3) presents an overview of transitioning a spaceport to an airport model; (4) establishes a framework for defining a ground system architecture; (5) presents the ACI concept; (6) demonstrates the approach by presenting a comparison of different GS architectures; and (7) presents a discussion on the benefits of using this approach with a focus on commonality.

A shared synapse architecture for efficient FPGA implementation of autoencoders.

PubMed

Suzuki, Akihiro; Morie, Takashi; Tamukoh, Hakaru

2018-01-01

This paper proposes a shared synapse architecture for autoencoders (AEs), and implements an AE with the proposed architecture as a digital circuit on a field-programmable gate array (FPGA). In the proposed architecture, the values of the synapse weights are shared between the synapses of an input and a hidden layer, and between the synapses of a hidden and an output layer. This architecture utilizes less of the limited resources of an FPGA than an architecture which does not share the synapse weights, and reduces the amount of synapse modules used by half. For the proposed circuit to be implemented into various types of AEs, it utilizes three kinds of parameters; one to change the number of layers' units, one to change the bit width of an internal value, and a learning rate. By altering a network configuration using these parameters, the proposed architecture can be used to construct a stacked AE. The proposed circuits are logically synthesized, and the number of their resources is determined. Our experimental results show that single and stacked AE circuits utilizing the proposed shared synapse architecture operate as regular AEs and as regular stacked AEs. The scalability of the proposed circuit and the relationship between the bit widths and the learning results are also determined. The clock cycles of the proposed circuits are formulated, and this formula is used to estimate the theoretical performance of the circuit when the circuit is used to construct arbitrary networks.

A shared synapse architecture for efficient FPGA implementation of autoencoders

PubMed Central

Morie, Takashi; Tamukoh, Hakaru

2018-01-01

This paper proposes a shared synapse architecture for autoencoders (AEs), and implements an AE with the proposed architecture as a digital circuit on a field-programmable gate array (FPGA). In the proposed architecture, the values of the synapse weights are shared between the synapses of an input and a hidden layer, and between the synapses of a hidden and an output layer. This architecture utilizes less of the limited resources of an FPGA than an architecture which does not share the synapse weights, and reduces the amount of synapse modules used by half. For the proposed circuit to be implemented into various types of AEs, it utilizes three kinds of parameters; one to change the number of layers’ units, one to change the bit width of an internal value, and a learning rate. By altering a network configuration using these parameters, the proposed architecture can be used to construct a stacked AE. The proposed circuits are logically synthesized, and the number of their resources is determined. Our experimental results show that single and stacked AE circuits utilizing the proposed shared synapse architecture operate as regular AEs and as regular stacked AEs. The scalability of the proposed circuit and the relationship between the bit widths and the learning results are also determined. The clock cycles of the proposed circuits are formulated, and this formula is used to estimate the theoretical performance of the circuit when the circuit is used to construct arbitrary networks. PMID:29543909

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

Application of Tessellation in Architectural Geometry Design

NASA Astrophysics Data System (ADS)

Chang, Wei

2018-06-01

Tessellation plays a significant role in architectural geometry design, which is widely used both through history of architecture and in modern architectural design with the help of computer technology. Tessellation has been found since the birth of civilization. In terms of dimensions, there are two- dimensional tessellations and three-dimensional tessellations; in terms of symmetry, there are periodic tessellations and aperiodic tessellations. Besides, some special types of tessellations such as Voronoi Tessellation and Delaunay Triangles are also included. Both Geometry and Crystallography, the latter of which is the basic theory of three-dimensional tessellations, need to be studied. In history, tessellation was applied into skins or decorations in architecture. The development of Computer technology enables tessellation to be more powerful, as seen in surface control, surface display and structure design, etc. Therefore, research on the application of tessellation in architectural geometry design is of great necessity in architecture studies.

Culture in the mind's mirror: how anthropology and neuroscience can inform a model of the neural substrate for cultural imitative learning.

PubMed

Losin, Elizabeth A Reynolds; Dapretto, Mirella; Iacoboni, Marco

2009-01-01

Cultural neuroscience, the study of how cultural experience shapes the brain, is an emerging subdiscipline in the neurosciences. Yet, a foundational question to the study of culture and the brain remains neglected by neuroscientific inquiry: "How does cultural information get into the brain in the first place?" Fortunately, the tools needed to explore the neural architecture of cultural learning - anthropological theories and cognitive neuroscience methodologies - already exist; they are merely separated by disciplinary boundaries. Here we review anthropological theories of cultural learning derived from fieldwork and modeling; since cultural learning theory suggests that sophisticated imitation abilities are at the core of human cultural learning, we focus our review on cultural imitative learning. Accordingly we proceed to discuss the neural underpinnings of imitation and other mechanisms important for cultural learning: learning biases, mental state attribution, and reinforcement learning. Using cultural neuroscience theory and cognitive neuroscience research as our guides, we then propose a preliminary model of the neural architecture of cultural learning. Finally, we discuss future studies needed to test this model and fully explore and explain the neural underpinnings of cultural imitative learning.

An Efficient Hardware Circuit for Spike Sorting Based on Competitive Learning Networks.

PubMed

Chen, Huan-Yuan; Chen, Chih-Chang; Hwang, Wen-Jyi

2017-09-28

This study aims to present an effective VLSI circuit for multi-channel spike sorting. The circuit supports the spike detection, feature extraction and classification operations. The detection circuit is implemented in accordance with the nonlinear energy operator algorithm. Both the peak detection and area computation operations are adopted for the realization of the hardware architecture for feature extraction. The resulting feature vectors are classified by a circuit for competitive learning (CL) neural networks. The CL circuit supports both online training and classification. In the proposed architecture, all the channels share the same detection, feature extraction, learning and classification circuits for a low area cost hardware implementation. The clock-gating technique is also employed for reducing the power dissipation. To evaluate the performance of the architecture, an application-specific integrated circuit (ASIC) implementation is presented. Experimental results demonstrate that the proposed circuit exhibits the advantages of a low chip area, a low power dissipation and a high classification success rate for spike sorting.

An Efficient Hardware Circuit for Spike Sorting Based on Competitive Learning Networks

PubMed Central

Chen, Huan-Yuan; Chen, Chih-Chang

2017-01-01

This study aims to present an effective VLSI circuit for multi-channel spike sorting. The circuit supports the spike detection, feature extraction and classification operations. The detection circuit is implemented in accordance with the nonlinear energy operator algorithm. Both the peak detection and area computation operations are adopted for the realization of the hardware architecture for feature extraction. The resulting feature vectors are classified by a circuit for competitive learning (CL) neural networks. The CL circuit supports both online training and classification. In the proposed architecture, all the channels share the same detection, feature extraction, learning and classification circuits for a low area cost hardware implementation. The clock-gating technique is also employed for reducing the power dissipation. To evaluate the performance of the architecture, an application-specific integrated circuit (ASIC) implementation is presented. Experimental results demonstrate that the proposed circuit exhibits the advantages of a low chip area, a low power dissipation and a high classification success rate for spike sorting. PMID:28956859

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 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.

Predicate calculus for an architecture of multiple neural networks

NASA Astrophysics Data System (ADS)

Consoli, Robert H.

1990-08-01

Future projects with neural networks will require multiple individual network components. Current efforts along these lines are ad hoc. This paper relates the neural network to a classical device and derives a multi-part architecture from that model. Further it provides a Predicate Calculus variant for describing the location and nature of the trainings and suggests Resolution Refutation as a method for determining the performance of the system as well as the location of needed trainings for specific proofs. 2. THE NEURAL NETWORK AND A CLASSICAL DEVICE Recently investigators have been making reports about architectures of multiple neural networksL234. These efforts are appearing at an early stage in neural network investigations they are characterized by architectures suggested directly by the problem space. Touretzky and Hinton suggest an architecture for processing logical statements1 the design of this architecture arises from the syntax of a restricted class of logical expressions and exhibits syntactic limitations. In similar fashion a multiple neural netword arises out of a control problem2 from the sequence learning problem3 and from the domain of machine learning. 4 But a general theory of multiple neural devices is missing. More general attempts to relate single or multiple neural networks to classical computing devices are not common although an attempt is made to relate single neural devices to a Turing machines and Sun et a!. develop a multiple neural architecture that performs pattern classification.

Connected commercial vehicles-integrated truck project : driver clinics, performance tests, and lessons learned.

DOT National Transportation Integrated Search

2002-04-01

The National ITS Architecture Mission Definition includes the system level concepts and requirements that document the fundamental needs which will be fulfilled by a successful ITS architecture. It provides a representation of the system that is usef...

Mario Becomes Cognitive.

PubMed

Schrodt, Fabian; Kneissler, Jan; Ehrenfeld, Stephan; Butz, Martin V

2017-04-01

In line with Allen Newell's challenge to develop complete cognitive architectures, and motivated by a recent proposal for a unifying subsymbolic computational theory of cognition, we introduce the cognitive control architecture SEMLINCS. SEMLINCS models the development of an embodied cognitive agent that learns discrete production rule-like structures from its own, autonomously gathered, continuous sensorimotor experiences. Moreover, the agent uses the developing knowledge to plan and control environmental interactions in a versatile, goal-directed, and self-motivated manner. Thus, in contrast to several well-known symbolic cognitive architectures, SEMLINCS is not provided with production rules and the involved symbols, but it learns them. In this paper, the actual implementation of SEMLINCS causes learning and self-motivated, autonomous behavioral control of the game figure Mario in a clone of the computer game Super Mario Bros. Our evaluations highlight the successful development of behavioral versatility as well as the learning of suitable production rules and the involved symbols from sensorimotor experiences. Moreover, knowledge- and motivation-dependent individualizations of the agents' behavioral tendencies are shown. Finally, interaction sequences can be planned on the sensorimotor-grounded production rule level. Current limitations directly point toward the need for several further enhancements, which may be integrated into SEMLINCS in the near future. Overall, SEMLINCS may be viewed as an architecture that allows the functional and computational modeling of embodied cognitive development, whereby the current main focus lies on the development of production rules from sensorimotor experiences. Copyright © 2017 Cognitive Science Society, Inc.

Distance-Learning for Advanced Military Education: Using Wargame Simulation Course as an Example

ERIC Educational Resources Information Center

Keh, Huan-Chao; Wang, Kuei-Min; Wai, Shu-Shen; Huang, Jiung-yao; Hui, Lin; Wu, Ji-Jen

2008-01-01

Distance learning in advanced military education can assist officers around the world to become more skilled and qualified for future challenges. Through well-chosen technology, the efficiency of distance-learning can be improved significantly. In this paper we present the architecture of Advanced Military Education-Distance Learning (AME-DL)…

Adding Learning to Knowledge-Based Systems: Taking the "Artificial" Out of AI

Treesearch

Daniel L. Schmoldt

1997-01-01

Both, knowledge-based systems (KBS) development and maintenance require time-consuming analysis of domain knowledge. Where example cases exist, KBS can be built, and later updated, by incorporating learning capabilities into their architecture. This applies to both supervised and unsupervised learning scenarios. In this paper, the important issues for learning systems-...

Virtual Learning Spaces in the Web: An Agent-Based Architecture of Personalized Collaborative Learning Environment.

ERIC Educational Resources Information Center

Nunez Esquer, Gustavo; Sheremetov, Leonid

This paper reports on the results and future research work within the paradigm of Configurable Collaborative Distance Learning, called Espacios Virtuales de Apredizaje (EVA). The paper focuses on: (1) description of the main concepts, including virtual learning spaces for knowledge, collaboration, consulting, and experimentation, a…

«

13

14

15

16

17

»

«

14

15

16

17

18

»

Architecture and Children: Learning Environments and Design Education.

ERIC Educational Resources Information Center

Taylor, Anne, Ed.; Muhlberger, Joe, Ed.

1998-01-01

This issue addresses (1) growing international interest in learning environments and their effects on behavior, and (2) design education, an integrated model for visual-spatial lifelong learning. It focuses on this new and emerging integrated field which integrates elements in education, new learning environment design, and the use of more two-…

Fully Convolutional Architecture for Low-Dose CT Image Noise Reduction

NASA Astrophysics Data System (ADS)

Badretale, S.; Shaker, F.; Babyn, P.; Alirezaie, J.

2017-10-01

One of the critical topics in medical low-dose Computed Tomography (CT) imaging is how best to maintain image quality. As the quality of images decreases with lowering the X-ray radiation dose, improving image quality is extremely important and challenging. We have proposed a novel approach to denoise low-dose CT images. Our algorithm learns directly from an end-to-end mapping from the low-dose Computed Tomography images for denoising the normal-dose CT images. Our method is based on a deep convolutional neural network with rectified linear units. By learning various low-level to high-level features from a low-dose image the proposed algorithm is capable of creating a high-quality denoised image. We demonstrate the superiority of our technique by comparing the results with two other state-of-the-art methods in terms of the peak signal to noise ratio, root mean square error, and a structural similarity index.

A Passive Learning Sensor Architecture for Multimodal Image Labeling: An Application for Social Robots.

PubMed

Gutiérrez, Marco A; Manso, Luis J; Pandya, Harit; Núñez, Pedro

2017-02-11

Object detection and classification have countless applications in human-robot interacting systems. It is a necessary skill for autonomous robots that perform tasks in household scenarios. Despite the great advances in deep learning and computer vision, social robots performing non-trivial tasks usually spend most of their time finding and modeling objects. Working in real scenarios means dealing with constant environment changes and relatively low-quality sensor data due to the distance at which objects are often found. Ambient intelligence systems equipped with different sensors can also benefit from the ability to find objects, enabling them to inform humans about their location. For these applications to succeed, systems need to detect the objects that may potentially contain other objects, working with relatively low-resolution sensor data. A passive learning architecture for sensors has been designed in order to take advantage of multimodal information, obtained using an RGB-D camera and trained semantic language models. The main contribution of the architecture lies in the improvement of the performance of the sensor under conditions of low resolution and high light variations using a combination of image labeling and word semantics. The tests performed on each of the stages of the architecture compare this solution with current research labeling techniques for the application of an autonomous social robot working in an apartment. The results obtained demonstrate that the proposed sensor architecture outperforms state-of-the-art approaches.

Neurally and mathematically motivated architecture for language and thought.

PubMed

Perlovsky, L I; Ilin, R

2010-01-01

Neural structures of interaction between thinking and language are unknown. This paper suggests a possible architecture motivated by neural and mathematical considerations. A mathematical requirement of computability imposes significant constraints on possible architectures consistent with brain neural structure and with a wealth of psychological knowledge. How language interacts with cognition. Do we think with words, or is thinking independent from language with words being just labels for decisions? Why is language learned by the age of 5 or 7, but acquisition of knowledge represented by learning to use this language knowledge takes a lifetime? This paper discusses hierarchical aspects of language and thought and argues that high level abstract thinking is impossible without language. We discuss a mathematical technique that can model the joint language-thought architecture, while overcoming previously encountered difficulties of computability. This architecture explains a contradiction between human ability for rational thoughtful decisions and irrationality of human thinking revealed by Tversky and Kahneman; a crucial role in this contradiction might be played by language. The proposed model resolves long-standing issues: how the brain learns correct words-object associations; why animals do not talk and think like people. We propose the role played by language emotionality in its interaction with thought. We relate the mathematical model to Humboldt's "firmness" of languages; and discuss possible influence of language grammar on its emotionality. Psychological and brain imaging experiments related to the proposed model are discussed. Future theoretical and experimental research is outlined.

Neurally and Mathematically Motivated Architecture for Language and Thought

PubMed Central

Perlovsky, L.I; Ilin, R

2010-01-01

Neural structures of interaction between thinking and language are unknown. This paper suggests a possible architecture motivated by neural and mathematical considerations. A mathematical requirement of computability imposes significant constraints on possible architectures consistent with brain neural structure and with a wealth of psychological knowledge. How language interacts with cognition. Do we think with words, or is thinking independent from language with words being just labels for decisions? Why is language learned by the age of 5 or 7, but acquisition of knowledge represented by learning to use this language knowledge takes a lifetime? This paper discusses hierarchical aspects of language and thought and argues that high level abstract thinking is impossible without language. We discuss a mathematical technique that can model the joint language-thought architecture, while overcoming previously encountered difficulties of computability. This architecture explains a contradiction between human ability for rational thoughtful decisions and irrationality of human thinking revealed by Tversky and Kahneman; a crucial role in this contradiction might be played by language. The proposed model resolves long-standing issues: how the brain learns correct words-object associations; why animals do not talk and think like people. We propose the role played by language emotionality in its interaction with thought. We relate the mathematical model to Humboldt’s “firmness” of languages; and discuss possible influence of language grammar on its emotionality. Psychological and brain imaging experiments related to the proposed model are discussed. Future theoretical and experimental research is outlined. PMID:21673788

Dissociations among judgments do not reflect cognitive priority: an associative explanation of memory for frequency information in contingency learning.

PubMed

Vadillo, Miguel A; Luque, David

2013-03-01

Previous research on causal learning has usually made strong claims about the relative complexity and temporal priority of some processes over others based on evidence about dissociations between several types of judgments. In particular, it has been argued that the dissociation between causal judgments and trial-type frequency information is incompatible with the general cognitive architecture proposed by associative models. In contrast with this view, we conduct an associative analysis of this process showing that this need not be the case. We conclude that any attempt to gain a better insight on the cognitive architecture involved in contingency learning cannot rely solely on data about these dissociations.

Lessons learned: from dye-sensitized solar cells to all-solid-state hybrid devices.

PubMed

Docampo, Pablo; Guldin, Stefan; Leijtens, Tomas; Noel, Nakita K; Steiner, Ullrich; Snaith, Henry J

2014-06-25

The field of solution-processed photovoltaic cells is currently in its second spring. The dye-sensitized solar cell is a widely studied and longstanding candidate for future energy generation. Recently, inorganic absorber-based devices have reached new record efficiencies, with the benefits of all-solid-state devices. In this rapidly changing environment, this review sheds light on recent developments in all-solid-state solar cells in terms of electrode architecture, alternative sensitizers, and hole-transporting materials. These concepts are of general applicability to many next-generation device platforms. © 2014 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Subliminal words durably affect neuronal activity.

PubMed

Gaillard, Raphaël; Cohen, Laurent; Adam, Claude; Clemenceau, Stéphane; Hasboun, Dominique; Baulac, Michel; Willer, Jean-Claude; Dehaene, Stanislas; Naccache, Lionel

2007-10-08

Unconscious mental representations elicited by subliminal stimuli are marked by their fleeting lifetimes, usually below 1 s. Can such evanescent subliminal stimuli, nevertheless, lead to long-lasting learning? To date, evidence suggesting a long-term influence of briefly perceived stimuli on behaviour or brain activity is scarce and questionable. In this study, we used intracranial recordings to provide the first direct demonstration that unconsciously perceived subliminal words could exert long-lasting effects on neuronal signals. When repeating subliminal words over long interstimulus intervals, we observed electrophysiological repetition effects. These unconscious repetition effects suggest that the single presentation of a masked word can durably affect neural architecture.

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.

The Effect of Incorporating Good Learners' Ratings in e-Learning Content-Based Recommender System

ERIC Educational Resources Information Center

Ghauth, Khairil Imran; Abdullah, Nor Aniza

2011-01-01

One of the anticipated challenges of today's e-learning is to solve the problem of recommending from a large number of learning materials. In this study, we introduce a novel architecture for an e-learning recommender system. More specifically, this paper comprises the following phases i) to propose an e-learning recommender system based on…

A Successful Component Architecture for Interoperable and Evolvable Ground Data Systems

NASA Technical Reports Server (NTRS)

Smith, Danford S.; Bristow, John O.; Wilmot, Jonathan

2006-01-01

The National Aeronautics and Space Administration (NASA) Goddard Space Flight Center (GSFC) has adopted an open architecture approach for satellite control centers and is now realizing benefits beyond those originally envisioned. The Goddard Mission Services Evolution Center (GMSEC) architecture utilizes standardized interfaces and a middleware software bus to allow functional components to be easily integrated. This paper presents the GMSEC architectural goals and concepts, the capabilities enabled and the benefits realized by adopting this framework approach. NASA experiences with applying the GMSEC architecture on multiple missions are discussed. The paper concludes with a summary of lessons learned, future directions for GMSEC and the possible applications beyond NASA GSFC.

Machine Learning for the Knowledge Plane

DTIC Science & Technology

2006-06-01

this idea is to combine techniques from machine learning with new architectural concepts in networking to make the internet self-aware and self...work on the machine learning portion of the Knowledge Plane. This consisted of three components: (a) we wrote a document formulating the various

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.

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.

Mediating human stem cell behaviour via defined fibrous architectures by melt electrospinning writing.

PubMed

Eichholz, Kian F; Hoey, David A

2018-05-29

The architecture within which cells reside is key to mediating their specific functions within the body. In this study, we use melt electrospinning writing (MEW) to fabricate cell micro-environments with various fibrous architectures to study their effect on human stem cell behaviour. We designed, built and optimised a MEW apparatus and used it to fabricate four different platform designs of 10.4±2μm fibre diameter, with angles between fibres on adjacent layers of 90°, 45°, 10° and R (random). Mechanical characterisation was conducted via tensile testing, and human skeletal stem cells (hSSCs) were seeded to scaffolds to study the effect of architecture on cell morphology and mechanosensing (nuclear YAP). Cell morphology was significantly altered between groups, with cells on 90° scaffolds having a lower aspect ratio, greater spreading, greater cytoskeletal tension and nuclear YAP expression. Long term cell culture studies were then conducted to determine the differentiation potential of scaffolds in terms of alkaline phosphatase activity, collagen and mineral production. Across these studies, an increased cell spreading in 3-dimensions is seen with decreasing alignment of architecture correlated with enhanced osteogenesis. This study therefore highlights the critical role of fibrous architecture in regulating stem cell behaviour with implications for tissue engineering and disease progression. This is the first study which has investigated the effect of controlled fibrous architectures fabricated via melt electrospinning writing on cell behaviour and differentiation. After optimising the process and characterising scaffolds via SEM and tensile testing, cells were seeded to fibrous scaffolds with various micro-architectures and studied in terms of cell morphology. Nuclear YAP expression was further investigated as a marker of cell shape, cytoskeletal tension and differentiation potential. In agreement with these early markers, long term cell culture studies revealed for the first time that a 90° fibrous architecture is optimal for the osteogenic differentiation of skeletal stem cells. This is the first study to investigate the effect of controlled fibrous material architectures fabricated via melt electrospinning writing on cell shape, mechanosignalling and differentiation. After optimising the biofabrication process and characterising scaffolds via SEM and tensile testing, cells were seeded to fibrous scaffolds with various micro-architectures and studied in terms of cell shape. Nuclear YAP expression was further investigated as a marker of cytoskeletal tension and differentiation potential. In agreement with these early markers, long term cell culture studies revealed for the first time that a 90° fibrous architecture is optimal for the osteogenic differentiation of skeletal stem cells, by driving a spread morphology and nuclear translocation of YAP in 3 dimensions . Copyright © 2018 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

Artificial Neural Networks for differential diagnosis of breast lesions in MR-Mammography: a systematic approach addressing the influence of network architecture on diagnostic performance using a large clinical database.

PubMed

Dietzel, Matthias; Baltzer, Pascal A T; Dietzel, Andreas; Zoubi, Ramy; Gröschel, Tobias; Burmeister, Hartmut P; Bogdan, Martin; Kaiser, Werner A

2012-07-01

Differential diagnosis of lesions in MR-Mammography (MRM) remains a complex task. The aim of this MRM study was to design and to test robustness of Artificial Neural Network architectures to predict malignancy using a large clinical database. For this IRB-approved investigation standardized protocols and study design were applied (T1w-FLASH; 0.1 mmol/kgBW Gd-DTPA; T2w-TSE; histological verification after MRM). All lesions were evaluated by two experienced (>500 MRM) radiologists in consensus. In every lesion, 18 previously published descriptors were assessed and documented in the database. An Artificial Neural Network (ANN) was developed to process this database (The-MathWorks/Inc., feed-forward-architecture/resilient back-propagation-algorithm). All 18 descriptors were set as input variables, whereas histological results (malignant vs. benign) was defined as classification variable. Initially, the ANN was optimized in terms of "Training Epochs" (TE), "Hidden Layers" (HL), "Learning Rate" (LR) and "Neurons" (N). Robustness of the ANN was addressed by repeated evaluation cycles (n: 9) with receiver operating characteristics (ROC) analysis of the results applying 4-fold Cross Validation. The best network architecture was identified comparing the corresponding Area under the ROC curve (AUC). Histopathology revealed 436 benign and 648 malignant lesions. Enhancing the level of complexity could not increase diagnostic accuracy of the network (P: n.s.). The optimized ANN architecture (TE: 20, HL: 1, N: 5, LR: 1.2) was accurate (mean-AUC 0.888; P: <0.001) and robust (CI: 0.885-0.892; range: 0.880-0.898). The optimized neural network showed robust performance and high diagnostic accuracy for prediction of malignancy on unknown data. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

A Conceptual Architecture for National Biosurveillance: Moving Beyond Situational Awareness to Enable Digital Detection of Emerging Threats.

PubMed

Velsko, Stephan; Bates, Thomas

2016-01-01

Despite numerous calls for improvement, the US biosurveillance enterprise remains a patchwork of uncoordinated systems that fail to take advantage of the rapid progress in information processing, communication, and analytics made in the past decade. By synthesizing components from the extensive biosurveillance literature, we propose a conceptual framework for a national biosurveillance architecture and provide suggestions for implementation. The framework differs from the current federal biosurveillance development pathway in that it is not focused on systems useful for "situational awareness" but is instead focused on the long-term goal of having true warning capabilities. Therefore, a guiding design objective is the ability to digitally detect emerging threats that span jurisdictional boundaries, because attempting to solve the most challenging biosurveillance problem first provides the strongest foundation to meet simpler surveillance objectives. Core components of the vision are: (1) a whole-of-government approach to support currently disparate federal surveillance efforts that have a common data need, including those for food safety, vaccine and medical product safety, and infectious disease surveillance; (2) an information architecture that enables secure national access to electronic health records, yet does not require that data be sent to a centralized location for surveillance analysis; (3) an inference architecture that leverages advances in "big data" analytics and learning inference engines-a significant departure from the statistical process control paradigm that underpins nearly all current syndromic surveillance systems; and (4) an organizational architecture with a governance model aimed at establishing national biosurveillance as a critical part of the US national infrastructure. Although it will take many years to implement, and a national campaign of education and debate to acquire public buy-in for such a comprehensive system, the potential benefits warrant increased consideration by the US government.

Efficient self-organizing multilayer neural network for nonlinear system modeling.

PubMed

Han, Hong-Gui; Wang, Li-Dan; Qiao, Jun-Fei

2013-07-01

It has been shown extensively that the dynamic behaviors of a neural system are strongly influenced by the network architecture and learning process. To establish an artificial neural network (ANN) with self-organizing architecture and suitable learning algorithm for nonlinear system modeling, an automatic axon-neural network (AANN) is investigated in the following respects. First, the network architecture is constructed automatically to change both the number of hidden neurons and topologies of the neural network during the training process. The approach introduced in adaptive connecting-and-pruning algorithm (ACP) is a type of mixed mode operation, which is equivalent to pruning or adding the connecting of the neurons, as well as inserting some required neurons directly. Secondly, the weights are adjusted, using a feedforward computation (FC) to obtain the information for the gradient during learning computation. Unlike most of the previous studies, AANN is able to self-organize the architecture and weights, and to improve the network performances. Also, the proposed AANN has been tested on a number of benchmark problems, ranging from nonlinear function approximating to nonlinear systems modeling. The experimental results show that AANN can have better performances than that of some existing neural networks. Crown Copyright © 2013. Published by Elsevier Ltd. All rights reserved.

Fully parallel write/read in resistive synaptic array for accelerating on-chip learning

NASA Astrophysics Data System (ADS)

Gao, Ligang; Wang, I.-Ting; Chen, Pai-Yu; Vrudhula, Sarma; Seo, Jae-sun; Cao, Yu; Hou, Tuo-Hung; Yu, Shimeng

2015-11-01

A neuro-inspired computing paradigm beyond the von Neumann architecture is emerging and it generally takes advantage of massive parallelism and is aimed at complex tasks that involve intelligence and learning. The cross-point array architecture with synaptic devices has been proposed for on-chip implementation of the weighted sum and weight update in the learning algorithms. In this work, forming-free, silicon-process-compatible Ta/TaO x /TiO2/Ti synaptic devices are fabricated, in which >200 levels of conductance states could be continuously tuned by identical programming pulses. In order to demonstrate the advantages of parallelism of the cross-point array architecture, a novel fully parallel write scheme is designed and experimentally demonstrated in a small-scale crossbar array to accelerate the weight update in the training process, at a speed that is independent of the array size. Compared to the conventional row-by-row write scheme, it achieves >30× speed-up and >30× improvement in energy efficiency as projected in a large-scale array. If realistic synaptic device characteristics such as device variations are taken into an array-level simulation, the proposed array architecture is able to achieve ∼95% recognition accuracy of MNIST handwritten digits, which is close to the accuracy achieved by software using the ideal sparse coding algorithm.

Architecture, Design, Implementatio

DTIC Science & Technology

2003-05-01

The terms architecture , design , and implementation are typically used informally in partitioning software specifications into three coarse strata of...we formalize the Intension and the Locality criteria, which imply that the distinction between architecture , design , and implementation is

«

14

15

16

17

18

»

«

15

16

17

18

19

»

Touring by Design: Using Information Architecture To Create a Virtual Library Tour.

ERIC Educational Resources Information Center

Kittelson, Pat; Jones, Sarah

2002-01-01

Describes the development of a Web-based virtual tour of the University of Otago (New Zealand) science library. Highlights include information literacy learning outcomes; information architecture, including information organization and navigation; integrating the tour into course work; and evaluation results. (LRW)

Trends and New Directions in Software Architecture

DTIC Science & Technology

2014-10-10

frameworks  Open source  Cloud strategies  NoSQL  Machine Learning  MDD  Incremental approaches  Dashboards  Distributed development...complexity grows  NoSQL Models are not created equal 2014 Our Current Research  Lightweight Evaluation and Architecture Prototyping for Big Data

Learning Outcomes in Affective Domain within Contemporary Architectural Curricula

ERIC Educational Resources Information Center

Savic, Marko; Kashef, Mohamad

2013-01-01

Contemporary architectural education has shifted from the traditional focus on providing students with specific knowledge and skill sets or "inputs" to outcome based, student-centred educational approach. Within the outcome based model, students' performance is assessed against measureable objectives that relate acquired knowledge…

Impact on Learning Awards, 2001.

ERIC Educational Resources Information Center

School Planning & Management, 2001

2001-01-01

Recognizes 14 architectural firms for their innovative designs, which helped solve real-world problems in K-12 school facilities. Designs for retrofits, safety and security, and specialized learning environments are profiled and critiqued. (GR)

Healthy Eating Design Guidelines for School Architecture

PubMed Central

Huang, Terry T-K; Sorensen, Dina; Davis, Steven; Frerichs, Leah; Brittin, Jeri; Celentano, Joseph; Callahan, Kelly

2013-01-01

We developed a new tool, Healthy Eating Design Guidelines for School Architecture, to provide practitioners in architecture and public health with a practical set of spatially organized and theory-based strategies for making school environments more conducive to learning about and practicing healthy eating by optimizing physical resources and learning spaces. The design guidelines, developed through multidisciplinary collaboration, cover 10 domains of the school food environment (eg, cafeteria, kitchen, garden) and 5 core healthy eating design principles. A school redesign project in Dillwyn, Virginia, used the tool to improve the schools’ ability to adopt a healthy nutrition curriculum and promote healthy eating. The new tool, now in a pilot version, is expected to evolve as its components are tested and evaluated through public health and design research. PMID:23449281

Architecture & Environment

ERIC Educational Resources Information Center

Erickson, Mary; Delahunt, Michael

2010-01-01

Most art teachers would agree that architecture is an important form of visual art, but they do not always include it in their curriculums. In this article, the authors share core ideas from "Architecture and Environment," a teaching resource that they developed out of a long-term interest in teaching architecture and their fascination with the…

The Basal Ganglia and Adaptive Motor Control

NASA Astrophysics Data System (ADS)

Graybiel, Ann M.; Aosaki, Toshihiko; Flaherty, Alice W.; Kimura, Minoru

1994-09-01

The basal ganglia are neural structures within the motor and cognitive control circuits in the mammalian forebrain and are interconnected with the neocortex by multiple loops. Dysfunction in these parallel loops caused by damage to the striatum results in major defects in voluntary movement, exemplified in Parkinson's disease and Huntington's disease. These parallel loops have a distributed modular architecture resembling local expert architectures of computational learning models. During sensorimotor learning, such distributed networks may be coordinated by widely spaced striatal interneurons that acquire response properties on the basis of experienced reward.

Learning and Skills: Opportunities or Threats for Disabled Learners? FEDA Responds.

ERIC Educational Resources Information Center

Mace, Jackie, Ed.

Challenges will be created by proposed changes to post-school education and training for people with learning difficulties and disabilities. Two important bills have been proposed. The Learning and Skills Bill (LSB) changes the whole architecture of the post-school education and training sector. LSB sets up the Learning and Skills Council (LSC)…

A Learning Architecture: How School Leaders Can Design for Learning Social Justice

ERIC Educational Resources Information Center

Scanlan, Martin

2013-01-01

Purpose: The field of socially just educational leadership focuses on reducing inequities within schools. The purpose of this article is to illustrate how one strand of social learning theory, communities of practice, can serve as a powerful tool for analyzing learning within a school ostensibly pursuing social justice. The author employs a core…

Remote Memory and Cortical Synaptic Plasticity Require Neuronal CCCTC-Binding Factor (CTCF).

PubMed

Kim, Somi; Yu, Nam-Kyung; Shim, Kyu-Won; Kim, Ji-Il; Kim, Hyopil; Han, Dae Hee; Choi, Ja Eun; Lee, Seung-Woo; Choi, Dong Il; Kim, Myung Won; Lee, Dong-Sung; Lee, Kyungmin; Galjart, Niels; Lee, Yong-Seok; Lee, Jae-Hyung; Kaang, Bong-Kiun

2018-05-30

The molecular mechanism of long-term memory has been extensively studied in the context of the hippocampus-dependent recent memory examined within several days. However, months-old remote memory maintained in the cortex for long-term has not been investigated much at the molecular level yet. Various epigenetic mechanisms are known to be important for long-term memory, but how the 3D chromatin architecture and its regulator molecules contribute to neuronal plasticity and systems consolidation is still largely unknown. CCCTC-binding factor (CTCF) is an 11-zinc finger protein well known for its role as a genome architecture molecule. Male conditional knock-out mice in which CTCF is lost in excitatory neurons during adulthood showed normal recent memory in the contextual fear conditioning and spatial water maze tasks. However, they showed remarkable impairments in remote memory in both tasks. Underlying the remote memory-specific phenotypes, we observed that female CTCF conditional knock-out mice exhibit disrupted cortical LTP, but not hippocampal LTP. Similarly, we observed that CTCF deletion in inhibitory neurons caused partial impairment of remote memory. Through RNA sequencing, we observed that CTCF knockdown in cortical neuron culture caused altered expression of genes that are highly involved in cell adhesion, synaptic plasticity, and memory. These results suggest that remote memory storage in the cortex requires CTCF-mediated gene regulation in neurons, whereas recent memory formation in the hippocampus does not. SIGNIFICANCE STATEMENT CCCTC-binding factor (CTCF) is a well-known 3D genome architectural protein that regulates gene expression. Here, we use two different CTCF conditional knock-out mouse lines and reveal, for the first time, that CTCF is critically involved in the regulation of remote memory. We also show that CTCF is necessary for appropriate expression of genes, many of which we found to be involved in the learning- and memory-related processes. Our study provides behavioral and physiological evidence for the involvement of CTCF-mediated gene regulation in the remote long-term memory and elucidates our understanding of systems consolidation mechanisms. Copyright © 2018 the authors 0270-6474/18/385042-11$15.00/0.

On learning navigation behaviors for small mobile robots with reservoir computing architectures.

PubMed

Antonelo, Eric Aislan; Schrauwen, Benjamin

2015-04-01

This paper proposes a general reservoir computing (RC) learning framework that can be used to learn navigation behaviors for mobile robots in simple and complex unknown partially observable environments. RC provides an efficient way to train recurrent neural networks by letting the recurrent part of the network (called reservoir) be fixed while only a linear readout output layer is trained. The proposed RC framework builds upon the notion of navigation attractor or behavior that can be embedded in the high-dimensional space of the reservoir after learning. The learning of multiple behaviors is possible because the dynamic robot behavior, consisting of a sensory-motor sequence, can be linearly discriminated in the high-dimensional nonlinear space of the dynamic reservoir. Three learning approaches for navigation behaviors are shown in this paper. The first approach learns multiple behaviors based on the examples of navigation behaviors generated by a supervisor, while the second approach learns goal-directed navigation behaviors based only on rewards. The third approach learns complex goal-directed behaviors, in a supervised way, using a hierarchical architecture whose internal predictions of contextual switches guide the sequence of basic navigation behaviors toward the goal.

Architecture and Development: Two Case Studies

ERIC Educational Resources Information Center

Bechhoefer, William B.

1975-01-01

An American Fulbright lecturer finds lessons learned about the growth of architectural education in Tunisia and Afghanistan relevant for other developing nations. He emphasizes the responsibility that accompanies the imposition of a foreign system: recognition of local variations from the model and evaluation of programs and curriculum responsive…

Building Technological Capability within Satellite Programs in Developing Countries

NASA Astrophysics Data System (ADS)

Wood, Danielle Renee

Global participation in space activity is growing as satellite technology matures and spreads. Countries in Africa, Asia and Latin America are creating or reinvigorating national satellite programs. These countries are building local capability in space through technological learning. They sometimes pursue this via collaborative satellite development projects with foreign firms that provide training. This phenomenon of collaborative satellite development projects is poorly understood by researchers of technological learning and technology transfer. The approach has potential to facilitate learning, but there are also challenges due to misaligned incentives and the tacit nature of the technology. Perspectives from literature on Technological Learning, Technology Transfer, Complex Product Systems and Product Delivery provide useful but incomplete insight for decision makers in such projects. This work seeks a deeper understanding of capability building through collaborative technology projects by conceiving of the projects as complex, socio-technical systems with architectures. The architecture of a system is the assignment of form to execute a function along a series of dimensions. The research questions explore the architecture of collaborative satellite projects, the nature of capability building during such projects, and the relationship between architecture and capability building. The research design uses inductive, exploratory case studies to investigate six collaborative satellite development projects. Data collection harnesses international field work driven by interviews, observation, and documents. The data analysis develops structured narratives, architectural comparison and capability building assessment. The architectural comparison reveals substantial variation in project implementation, especially in the areas of project initiation, technical specifications of the satellite, training approaches and the supplier selection process. The individual capability building assessment shows that most trainee engineers gradually progressed from no experience with satellites through theoretical training to supervised experience; a minority achieved independent experience. At the organizational level, the emerging space organizations achieved high levels of autonomy in project definition and satellite operation, but they were dependent on foreign firms for satellite design, manufacture, test and launch. The case studies can be summarized by three archetypal projects defined as "Politically Pushed," "Structured," and "Risk Taking." Countries in the case studies tended to start in a Politically Pushed mode, and then moved into either Structured or Risk Taking mode. Decision makers in emerging satellite programs can use the results of this dissertation to consider the broad set of architectural options for capability building. Future work will continue to probe how specific architectural decisions impact capability building outcomes in satellite projects and other technologies. (Copies available exclusively from MIT Libraries, libraries.mit.edu/docs - docs@mit.edu)

Agent Collaborative Target Localization and Classification in Wireless Sensor Networks

PubMed Central

Wang, Xue; Bi, Dao-wei; Ding, Liang; Wang, Sheng

2007-01-01

Wireless sensor networks (WSNs) are autonomous networks that have been frequently deployed to collaboratively perform target localization and classification tasks. Their autonomous and collaborative features resemble the characteristics of agents. Such similarities inspire the development of heterogeneous agent architecture for WSN in this paper. The proposed agent architecture views WSN as multi-agent systems and mobile agents are employed to reduce in-network communication. According to the architecture, an energy based acoustic localization algorithm is proposed. In localization, estimate of target location is obtained by steepest descent search. The search algorithm adapts to measurement environments by dynamically adjusting its termination condition. With the agent architecture, target classification is accomplished by distributed support vector machine (SVM). Mobile agents are employed for feature extraction and distributed SVM learning to reduce communication load. Desirable learning performance is guaranteed by combining support vectors and convex hull vectors. Fusion algorithms are designed to merge SVM classification decisions made from various modalities. Real world experiments with MICAz sensor nodes are conducted for vehicle localization and classification. Experimental results show the proposed agent architecture remarkably facilitates WSN designs and algorithm implementation. The localization and classification algorithms also prove to be accurate and energy efficient.

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.

Optoelectronic analogs of self-programming neural nets - Architecture and methodologies for implementing fast stochastic learning by simulated annealing

NASA Technical Reports Server (NTRS)

Farhat, Nabil H.

1987-01-01

Self-organization and learning is a distinctive feature of neural nets and processors that sets them apart from conventional approaches to signal processing. It leads to self-programmability which alleviates the problem of programming complexity in artificial neural nets. In this paper architectures for partitioning an optoelectronic analog of a neural net into distinct layers with prescribed interconnectivity pattern to enable stochastic learning by simulated annealing in the context of a Boltzmann machine are presented. Stochastic learning is of interest because of its relevance to the role of noise in biological neural nets. Practical considerations and methodologies for appreciably accelerating stochastic learning in such a multilayered net are described. These include the use of parallel optical computing of the global energy of the net, the use of fast nonvolatile programmable spatial light modulators to realize fast plasticity, optical generation of random number arrays, and an adaptive noisy thresholding scheme that also makes stochastic learning more biologically plausible. The findings reported predict optoelectronic chips that can be used in the realization of optical learning machines.

Deep Multi-Task Learning for Tree Genera Classification

NASA Astrophysics Data System (ADS)

Ko, C.; Kang, J.; Sohn, G.

2018-05-01

The goal for our paper is to classify tree genera using airborne Light Detection and Ranging (LiDAR) data with Convolution Neural Network (CNN) - Multi-task Network (MTN) implementation. Unlike Single-task Network (STN) where only one task is assigned to the learning outcome, MTN is a deep learning architect for learning a main task (classification of tree genera) with other tasks (in our study, classification of coniferous and deciduous) simultaneously, with shared classification features. The main contribution of this paper is to improve classification accuracy from CNN-STN to CNN-MTN. This is achieved by introducing a concurrence loss (Lcd) to the designed MTN. This term regulates the overall network performance by minimizing the inconsistencies between the two tasks. Results show that we can increase the classification accuracy from 88.7 % to 91.0 % (from STN to MTN). The second goal of this paper is to solve the problem of small training sample size by multiple-view data generation. The motivation of this goal is to address one of the most common problems in implementing deep learning architecture, the insufficient number of training data. We address this problem by simulating training dataset with multiple-view approach. The promising results from this paper are providing a basis for classifying a larger number of dataset and number of classes in the future.

Humanoid infers Archimedes' principle: understanding physical relations and object affordances through cumulative learning experiences.

PubMed

Bhat, Ajaz Ahmad; Mohan, Vishwanathan; Sandini, Giulio; Morasso, Pietro

2016-07-01

Emerging studies indicate that several species such as corvids, apes and children solve 'The Crow and the Pitcher' task (from Aesop's Fables) in diverse conditions. Hidden beneath this fascinating paradigm is a fundamental question: by cumulatively interacting with different objects, how can an agent abstract the underlying cause-effect relations to predict and creatively exploit potential affordances of novel objects in the context of sought goals? Re-enacting this Aesop's Fable task on a humanoid within an open-ended 'learning-prediction-abstraction' loop, we address this problem and (i) present a brain-guided neural framework that emulates rapid one-shot encoding of ongoing experiences into a long-term memory and (ii) propose four task-agnostic learning rules (elimination, growth, uncertainty and status quo) that correlate predictions from remembered past experiences with the unfolding present situation to gradually abstract the underlying causal relations. Driven by the proposed architecture, the ensuing robot behaviours illustrated causal learning and anticipation similar to natural agents. Results further demonstrate that by cumulatively interacting with few objects, the predictions of the robot in case of novel objects converge close to the physical law, i.e. the Archimedes principle: this being independent of both the objects explored during learning and the order of their cumulative exploration. © 2016 The Author(s).

On the sample complexity of learning for networks of spiking neurons with nonlinear synaptic interactions.

PubMed

Schmitt, Michael

2004-09-01

We study networks of spiking neurons that use the timing of pulses to encode information. Nonlinear interactions model the spatial groupings of synapses on the neural dendrites and describe the computations performed at local branches. Within a theoretical framework of learning we analyze the question of how many training examples these networks must receive to be able to generalize well. Bounds for this sample complexity of learning can be obtained in terms of a combinatorial parameter known as the pseudodimension. This dimension characterizes the computational richness of a neural network and is given in terms of the number of network parameters. Two types of feedforward architectures are considered: constant-depth networks and networks of unconstrained depth. We derive asymptotically tight bounds for each of these network types. Constant depth networks are shown to have an almost linear pseudodimension, whereas the pseudodimension of general networks is quadratic. Networks of spiking neurons that use temporal coding are becoming increasingly more important in practical tasks such as computer vision, speech recognition, and motor control. The question of how well these networks generalize from a given set of training examples is a central issue for their successful application as adaptive systems. The results show that, although coding and computation in these networks is quite different and in many cases more powerful, their generalization capabilities are at least as good as those of traditional neural network models.

A neuro-fuzzy architecture for real-time applications

NASA Technical Reports Server (NTRS)

Ramamoorthy, P. A.; Huang, Song

1992-01-01

Neural networks and fuzzy expert systems perform the same task of functional mapping using entirely different approaches. Each approach has certain unique features. The ability to learn specific input-output mappings from large input/output data possibly corrupted by noise and the ability to adapt or continue learning are some important features of neural networks. Fuzzy expert systems are known for their ability to deal with fuzzy information and incomplete/imprecise data in a structured, logical way. Since both of these techniques implement the same task (that of functional mapping--we regard 'inferencing' as one specific category under this class), a fusion of the two concepts that retains their unique features while overcoming their individual drawbacks will have excellent applications in the real world. In this paper, we arrive at a new architecture by fusing the two concepts. The architecture has the trainability/adaptibility (based on input/output observations) property of the neural networks and the architectural features that are unique to fuzzy expert systems. It also does not require specific information such as fuzzy rules, defuzzification procedure used, etc., though any such information can be integrated into the architecture. We show that this architecture can provide better performance than is possible from a single two or three layer feedforward neural network. Further, we show that this new architecture can be used as an efficient vehicle for hardware implementation of complex fuzzy expert systems for real-time applications. A numerical example is provided to show the potential of this approach.

«

15

16

17

18

19

»

«

16

17

18

19

20

»

Ontology-Based Learner Categorization through Case Based Reasoning and Fuzzy Logic

ERIC Educational Resources Information Center

Sarwar, Sohail; García-Castro, Raul; Qayyum, Zia Ul; Safyan, Muhammad; Munir, Rana Faisal

2017-01-01

Learner categorization has a pivotal role in making e-learning systems a success. However, learner characteristics exploited at abstract level of granularity by contemporary techniques cannot categorize the learners effectively. In this paper, an architecture of e-learning framework has been presented that exploits the machine learning based…

A New Architecture for Learning

ERIC Educational Resources Information Center

Abel, Rob; Brown, Malcolm; Suess, Jack

2013-01-01

Higher education, is entering a period in which it is the "connections" between everything and everyone that are of importance. This development is most conspicuous in teaching and learning and is enabled by information technology, social media, and mobile devices. This advent of "connected learning" is having an impact on all…

Creating an Organic Knowledge-Building Environment within an Asynchronous Distributed Learning Context.

ERIC Educational Resources Information Center

Moller, Leslie; Prestera, Gustavo E.; Harvey, Douglas; Downs-Keller, Margaret; McCausland, Jo-Ann

2002-01-01

Discusses organic architecture and suggests that learning environments should be designed and constructed using an organic approach, so that learning is not viewed as a distinct human activity but incorporated into everyday performance. Highlights include an organic knowledge-building model; information objects; scaffolding; discourse action…

Learning to Draw through Digital Modelling

ERIC Educational Resources Information Center

Temple, Stephen

2016-01-01

The education of architectural designers begins by learning drawing and digital modelling following the notion that students learn these new modes as instruments of thinking in design process. Curricular arguments persist about which mode should follow the other. Difficulties occur when one mode replaces the other. Students uninitiated to design…

Presenting an Approach for Conducting Knowledge Architecture within Large-Scale Organizations

PubMed Central

Varaee, Touraj; Habibi, Jafar; Mohaghar, Ali

2015-01-01

Knowledge architecture (KA) establishes the basic groundwork for the successful implementation of a short-term or long-term knowledge management (KM) program. An example of KA is the design of a prototype before a new vehicle is manufactured. Due to a transformation to large-scale organizations, the traditional architecture of organizations is undergoing fundamental changes. This paper explores the main strengths and weaknesses in the field of KA within large-scale organizations and provides a suitable methodology and supervising framework to overcome specific limitations. This objective was achieved by applying and updating the concepts from the Zachman information architectural framework and the information architectural methodology of enterprise architecture planning (EAP). The proposed solution may be beneficial for architects in knowledge-related areas to successfully accomplish KM within large-scale organizations. The research method is descriptive; its validity is confirmed by performing a case study and polling the opinions of KA experts. PMID:25993414

A Novel Byte-Substitution Architecture for the AES Cryptosystem.

PubMed

Hossain, Fakir Sharif; Ali, Md Liakot

2015-01-01

The performance of Advanced Encryption Standard (AES) mainly depends on speed, area and power. The S-box represents an important factor that affects the performance of AES on each of these factors. A number of techniques have been presented in the literature, which have attempted to improve the performance of the S-box byte-substitution. This paper proposes a new S-box architecture, defining it as ultra low power, robustly parallel and highly efficient in terms of area. The architecture is discussed for both CMOS and FPGA platforms, and the pipelined architecture of the proposed S-box is presented for further time savings and higher throughput along with higher hardware resources utilization. A performance analysis and comparison of the proposed architecture is also conducted with those achieved by the existing techniques. The results of the comparison verify the outperformance of the proposed architecture in terms of power, delay and size.

A Novel Byte-Substitution Architecture for the AES Cryptosystem

PubMed Central

Hossain, Fakir Sharif; Ali, Md. Liakot

2015-01-01

The performance of Advanced Encryption Standard (AES) mainly depends on speed, area and power. The S-box represents an important factor that affects the performance of AES on each of these factors. A number of techniques have been presented in the literature, which have attempted to improve the performance of the S-box byte-substitution. This paper proposes a new S-box architecture, defining it as ultra low power, robustly parallel and highly efficient in terms of area. The architecture is discussed for both CMOS and FPGA platforms, and the pipelined architecture of the proposed S-box is presented for further time savings and higher throughput along with higher hardware resources utilization. A performance analysis and comparison of the proposed architecture is also conducted with those achieved by the existing techniques. The results of the comparison verify the outperformance of the proposed architecture in terms of power, delay and size. PMID:26491967

Presenting an Approach for Conducting Knowledge Architecture within Large-Scale Organizations.

PubMed

Varaee, Touraj; Habibi, Jafar; Mohaghar, Ali

2015-01-01

Knowledge architecture (KA) establishes the basic groundwork for the successful implementation of a short-term or long-term knowledge management (KM) program. An example of KA is the design of a prototype before a new vehicle is manufactured. Due to a transformation to large-scale organizations, the traditional architecture of organizations is undergoing fundamental changes. This paper explores the main strengths and weaknesses in the field of KA within large-scale organizations and provides a suitable methodology and supervising framework to overcome specific limitations. This objective was achieved by applying and updating the concepts from the Zachman information architectural framework and the information architectural methodology of enterprise architecture planning (EAP). The proposed solution may be beneficial for architects in knowledge-related areas to successfully accomplish KM within large-scale organizations. The research method is descriptive; its validity is confirmed by performing a case study and polling the opinions of KA experts.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction.

PubMed

Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

2017-04-10

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.

Triangular Quantum Loop Topography for Machine Learning

NASA Astrophysics Data System (ADS)

Zhang, Yi; Kim, Eun-Ah

Despite rapidly growing interest in harnessing machine learning in the study of quantum many-body systems there has been little success in training neural networks to identify topological phases. The key challenge is in efficiently extracting essential information from the many-body Hamiltonian or wave function and turning the information into an image that can be fed into a neural network. When targeting topological phases, this task becomes particularly challenging as topological phases are defined in terms of non-local properties. Here we introduce triangular quantum loop (TQL) topography: a procedure of constructing a multi-dimensional image from the ''sample'' Hamiltonian or wave function using two-point functions that form triangles. Feeding the TQL topography to a fully-connected neural network with a single hidden layer, we demonstrate that the architecture can be effectively trained to distinguish Chern insulator and fractional Chern insulator from trivial insulators with high fidelity. Given the versatility of the TQL topography procedure that can handle different lattice geometries, disorder, interaction and even degeneracy our work paves the route towards powerful applications of machine learning in the study of topological quantum matters.

Neuromimetic Circuits with Synaptic Devices Based on Strongly Correlated Electron Systems

NASA Astrophysics Data System (ADS)

Ha, Sieu D.; Shi, Jian; Meroz, Yasmine; Mahadevan, L.; Ramanathan, Shriram

2014-12-01

Strongly correlated electron systems such as the rare-earth nickelates (R NiO3 , R denotes a rare-earth element) can exhibit synapselike continuous long-term potentiation and depression when gated with ionic liquids; exploiting the extreme sensitivity of coupled charge, spin, orbital, and lattice degrees of freedom to stoichiometry. We present experimental real-time, device-level classical conditioning and unlearning using nickelate-based synaptic devices in an electronic circuit compatible with both excitatory and inhibitory neurons. We establish a physical model for the device behavior based on electric-field-driven coupled ionic-electronic diffusion that can be utilized for design of more complex systems. We use the model to simulate a variety of associate and nonassociative learning mechanisms, as well as a feedforward recurrent network for storing memory. Our circuit intuitively parallels biological neural architectures, and it can be readily generalized to other forms of cellular learning and extinction. The simulation of neural function with electronic device analogs may provide insight into biological processes such as decision making, learning, and adaptation, while facilitating advanced parallel information processing in hardware.

Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction

PubMed Central

Ma, Xiaolei; Dai, Zhuang; He, Zhengbing; Ma, Jihui; Wang, Yong; Wang, Yunpeng

2017-01-01

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks. PMID:28394270

A broadband multimedia TeleLearning system

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

Wang, Ruiping; Karmouch, A.

1996-12-31

In this paper we discuss a broadband multimedia TeleLearning system under development in the Multimedia Information Research Laboratory at the University of Ottawa. The system aims at providing a seamless environment for TeleLearning using the latest telecommunication and multimedia information processing technology. It basically consists of a media production center, a courseware author site, a courseware database, a courseware user site, and an on-line facilitator site. All these components are distributed over an ATM network and work together to offer a multimedia interactive courseware service. An MHEG-based model is exploited in designing the system architecture to achieve the real-time, interactive,more » and reusable information interchange through heterogeneous platforms. The system architecture, courseware processing strategies, courseware document models are presented.« less

Large-Scale Networked Virtual Environments: Architecture and Applications

ERIC Educational Resources Information Center

Lamotte, Wim; Quax, Peter; Flerackers, Eddy

2008-01-01

Purpose: Scalability is an important research topic in the context of networked virtual environments (NVEs). This paper aims to describe the ALVIC (Architecture for Large-scale Virtual Interactive Communities) approach to NVE scalability. Design/methodology/approach: The setup and results from two case studies are shown: a 3-D learning environment…

India's People, Country, and Great Religions: Two Instructional Learning Packages.

ERIC Educational Resources Information Center

Wales, Largo Ann

Divided into two parts, this slide narration covers India's history, people, religions, geography, and architecture. The first part, "Introduction: Country, People, and History," covers the general history of India and its people. The history is presented through: (1) the architecture, including the Palace of Winds, the Amber Fort, the…

Improving Project Management Using Formal Models and Architectures

NASA Technical Reports Server (NTRS)

Kahn, Theodore; Sturken, Ian

2011-01-01

This talk discusses the advantages formal modeling and architecture brings to project management. These emerging technologies have both great potential and challenges for improving information available for decision-making. The presentation covers standards, tools and cultural issues needing consideration, and includes lessons learned from projects the presenters have worked on.

5 CFR 1207.170 - Compliance procedures.

Code of Federal Regulations, 2010 CFR

2010-01-01

... recommendation by the time the party learns of the alleged discrimination, the party may raise the allegation in... delegated to another agency. (d) The agency shall notify the Architectural and Transportation Barriers... Architectural Barriers Act of 1968, as amended (42 U.S.C. 4151-4157), is not readily accessible to and usable by...

Design and Implementation of an Intelligent Virtual Environment for Improving Speaking and Listening Skills

ERIC Educational Resources Information Center

Hassani, Kaveh; Nahvi, Ali; Ahmadi, Ali

2016-01-01

In this paper, we present an intelligent architecture, called intelligent virtual environment for language learning, with embedded pedagogical agents for improving listening and speaking skills of non-native English language learners. The proposed architecture integrates virtual environments into the Intelligent Computer-Assisted Language…

The Relevance of Innovative School Architecture for School Principals

ERIC Educational Resources Information Center

Schabmann, Alfred; Popper, Vera; Schmidt, Barbara Maria; Kühn, Christian; Pitro, Ulrike; Spiel, Christiane

2016-01-01

In many cases, innovative forms of learning require innovative concepts of using space in school. However, so far there has been a lack of research concerning the perspectives of school principals as important stakeholders in the adoption of alternative school architecture. The present study examines the importance of alternative school…

Mythology, Archaeology, Architecture. Learning Works Enrichment Series.

ERIC Educational Resources Information Center

Sylvester, Diane; Wiemann, Mary

The activities in this book have been selected especially for gifted students in grades 4 through 8. They are designed to challenge and help students develop and apply higher-level thinking skills. The activities have been grouped by subject matter into mythology, archaeology, and architecture. The mythology section includes Chinese, Eskimo,…

«

16

17

18

19

20

»

«

17

18

19

20

21

»

Applied Physics Modules Selected for Architectural and Civil Drafting Technologies.

ERIC Educational Resources Information Center

Waring, Gene

Designed for individualized use in an applied physics course in postsecondary vocational-technical education, this series of six learning modules is equivalent to the content of a three-credit hour class in surveying and drafting technology, architectural drafting technology, building construction technology, and civil engineering technology.…

Class Architecture.

ERIC Educational Resources Information Center

Crosbie, Michael J.

This compendium contains more than 40 schools that show new directions in design and the changing demands on this building type. It discusses the design challenges in new schools and how each one of the projects meets the demands of an architecture for learning. An introduction by architect Raymond Bordwell explains many of the trends in new…

Web Image Retrieval Using Self-Organizing Feature Map.

ERIC Educational Resources Information Center

Wu, Qishi; Iyengar, S. Sitharama; Zhu, Mengxia

2001-01-01

Provides an overview of current image retrieval systems. Describes the architecture of the SOFM (Self Organizing Feature Maps) based image retrieval system, discussing the system architecture and features. Introduces the Kohonen model, and describes the implementation details of SOFM computation and its learning algorithm. Presents a test example…

School Students' Responses to Architecture: A Practical Studio Project.

ERIC Educational Resources Information Center

Hickman, Richard

2001-01-01

Describes a project with mixed ability learners attending Deacon's School (Peterborough, England). The project, which emphasized critical response to the built environment, involved students making "pop up cards" based on firsthand observation of local architecture. Students were encouraged to learn about art and design through reacting,…

Traditional Earthen Architecture in the Art Curriculum.

ERIC Educational Resources Information Center

Heil, Steven E.

2001-01-01

Describes an adobe conservation project used with seventh- and eighth-grade students at the Zuni Pueblo (New Mexico). States that the project motivates students as they participate in experiential learning. Addresses the objectives in a traditional architecture curriculum and contends that the adobe conservation project demonstrates the place of…

Architecture. Intermediate ThemeWorks. An Integrated Activity Bank.

ERIC Educational Resources Information Center

Stewart, Kelly

This resource book offers an activity bank of learning experiences related to the theme of architecture. The activities, which are designed for use with students in grades 4-6, require active engagement of the students and integrate language arts, mathematics, science, social studies, and art experiences. Activities exploring the architectural…

Energy-efficient STDP-based learning circuits with memristor synapses

NASA Astrophysics Data System (ADS)

Wu, Xinyu; Saxena, Vishal; Campbell, Kristy A.

2014-05-01

It is now accepted that the traditional von Neumann architecture, with processor and memory separation, is ill suited to process parallel data streams which a mammalian brain can efficiently handle. Moreover, researchers now envision computing architectures which enable cognitive processing of massive amounts of data by identifying spatio-temporal relationships in real-time and solving complex pattern recognition problems. Memristor cross-point arrays, integrated with standard CMOS technology, are expected to result in massively parallel and low-power Neuromorphic computing architectures. Recently, significant progress has been made in spiking neural networks (SNN) which emulate data processing in the cortical brain. These architectures comprise of a dense network of neurons and the synapses formed between the axons and dendrites. Further, unsupervised or supervised competitive learning schemes are being investigated for global training of the network. In contrast to a software implementation, hardware realization of these networks requires massive circuit overhead for addressing and individually updating network weights. Instead, we employ bio-inspired learning rules such as the spike-timing-dependent plasticity (STDP) to efficiently update the network weights locally. To realize SNNs on a chip, we propose to use densely integrating mixed-signal integrate-andfire neurons (IFNs) and cross-point arrays of memristors in back-end-of-the-line (BEOL) of CMOS chips. Novel IFN circuits have been designed to drive memristive synapses in parallel while maintaining overall power efficiency (<1 pJ/spike/synapse), even at spike rate greater than 10 MHz. We present circuit design details and simulation results of the IFN with memristor synapses, its response to incoming spike trains and STDP learning characterization.

Artificial Neural Networks as an Architectural Design Tool-Generating New Detail Forms Based On the Roman Corinthian Order Capital

NASA Astrophysics Data System (ADS)

Radziszewski, Kacper

2017-10-01

The following paper presents the results of the research in the field of the machine learning, investigating the scope of application of the artificial neural networks algorithms as a tool in architectural design. The computational experiment was held using the backward propagation of errors method of training the artificial neural network, which was trained based on the geometry of the details of the Roman Corinthian order capital. During the experiment, as an input training data set, five local geometry parameters combined has given the best results: Theta, Pi, Rho in spherical coordinate system based on the capital volume centroid, followed by Z value of the Cartesian coordinate system and a distance from vertical planes created based on the capital symmetry. Additionally during the experiment, artificial neural network hidden layers optimal count and structure was found, giving results of the error below 0.2% for the mentioned before input parameters. Once successfully trained artificial network, was able to mimic the details composition on any other geometry type given. Despite of calculating the transformed geometry locally and separately for each of the thousands of surface points, system could create visually attractive and diverse, complex patterns. Designed tool, based on the supervised learning method of machine learning, gives possibility of generating new architectural forms- free of the designer’s imagination bounds. Implementing the infinitely broad computational methods of machine learning, or Artificial Intelligence in general, not only could accelerate and simplify the design process, but give an opportunity to explore never seen before, unpredictable forms or everyday architectural practice solutions.

Sustainable, Reliable Mission-Systems Architecture

NASA Technical Reports Server (NTRS)

O'Neil, Graham; Orr, James K.; Watson, Steve

2005-01-01

A mission-systems architecture, based on a highly modular infrastructure utilizing open-standards hardware and software interfaces as the enabling technology is essential for affordable md sustainable space exploration programs. This mission-systems architecture requires (8) robust communication between heterogeneous systems, (b) high reliability, (c) minimal mission-to-mission reconfiguration, (d) affordable development, system integration, end verification of systems, and (e) minimal sustaining engineering. This paper proposes such an architecture. Lessons learned from the Space Shuttle program and Earthbound complex engineered systems are applied to define the model. Technology projections reaching out 5 years are made to refine model details.

A Sustainable, Reliable Mission-Systems Architecture that Supports a System of Systems Approach to Space Exploration

NASA Technical Reports Server (NTRS)

Watson, Steve; Orr, Jim; O'Neil, Graham

2004-01-01

A mission-systems architecture based on a highly modular "systems of systems" infrastructure utilizing open-standards hardware and software interfaces as the enabling technology is absolutely essential for an affordable and sustainable space exploration program. This architecture requires (a) robust communication between heterogeneous systems, (b) high reliability, (c) minimal mission-to-mission reconfiguration, (d) affordable development, system integration, and verification of systems, and (e) minimum sustaining engineering. This paper proposes such an architecture. Lessons learned from the space shuttle program are applied to help define and refine the model.

Sustainable, Reliable Mission-Systems Architecture

NASA Technical Reports Server (NTRS)

O'Neil, Graham; Orr, James K.; Watson, Steve

2007-01-01

A mission-systems architecture, based on a highly modular infrastructure utilizing: open-standards hardware and software interfaces as the enabling technology is essential for affordable and sustainable space exploration programs. This mission-systems architecture requires (a) robust communication between heterogeneous system, (b) high reliability, (c) minimal mission-to-mission reconfiguration, (d) affordable development, system integration, and verification of systems, and (e) minimal sustaining engineering. This paper proposes such an architecture. Lessons learned from the Space Shuttle program and Earthbound complex engineered system are applied to define the model. Technology projections reaching out 5 years are mde to refine model details.

Research Results of Two Personal Learning Environments Experiments in a Higher Education Institution

ERIC Educational Resources Information Center

Marín Juarros, Victoria; Salinas Ibáñez, Jesús; de Benito Crosetti, Bárbara

2014-01-01

This paper focuses on institutionally powered personal learning environments (iPLEs). The concept of the iPLE can be seen as a way universities can incorporate learner-centred approach into the architecture of their technology-enhanced learning environments. The aim of this paper is to pose that there are other ways to learn complementary to…

Proceedings of the Workshop on Models of Complex Human Learning Held in Ithaca, New York on June 27-28, 1989

DTIC Science & Technology

1989-06-01

to facilitate in-depth communication of research results in a multi-disciplinary gathering led to a decision to have long presentations and limit the...learning subfields such as computational learning theory and explanation based learning? Second, as the machine learning field increases its emphasis...Architecture, Pat Langley, University of California, Irvine .................................................... 22 A Theory of Human Plausible Reasoning

Effects of classrooms' architecture on academic performance in view of telic versus paratelic motivation: a review.

PubMed

Lewinski, Peter

2015-01-01

This mini literature review analyzes research papers from many countries that directly or indirectly test how classrooms' architecture influences academic performance. These papers evaluate and explain specific characteristics of classrooms, with an emphasis on how they affect learning processes and learning outcomes. Factors such as acoustics, light, color, temperature, and seat arrangement are scrutinized to determine whether and by how much they improve or hinder students' academic performance in classrooms. Apter's (1982, 1984, 2014) reversal theory of telic versus paratelic motivation is presented and used to explain these findings. The results show preference for a learning environment that cues a telic motivation state in the students. Therefore, classroom features should not be distracting or arousing. Moreover, it appears the most influential factors affecting the learning process are noise, temperature and seat arrangement. In addition, there is no current agreement on how some particular physical characteristics of classrooms affect learning outcomes. More research is needed to establish stronger conclusions and recommendations.

Designing Online Education Courses.

ERIC Educational Resources Information Center

Trentin, Guglielmo

2001-01-01

Focuses on the main elements that characterize online course design. Topics include design constraints; analysis of learning needs; defining objectives; course prerequisites; content structuring; course flexibility; learning strategies; evaluation criteria; course activities; course structure; communication architecture; and design evaluation.…

Random synaptic feedback weights support error backpropagation for deep learning

NASA Astrophysics Data System (ADS)

Lillicrap, Timothy P.; Cownden, Daniel; Tweed, Douglas B.; Akerman, Colin J.

2016-11-01

The brain processes information through multiple layers of neurons. This deep architecture is representationally powerful, but complicates learning because it is difficult to identify the responsible neurons when a mistake is made. In machine learning, the backpropagation algorithm assigns blame by multiplying error signals with all the synaptic weights on each neuron's axon and further downstream. However, this involves a precise, symmetric backward connectivity pattern, which is thought to be impossible in the brain. Here we demonstrate that this strong architectural constraint is not required for effective error propagation. We present a surprisingly simple mechanism that assigns blame by multiplying errors by even random synaptic weights. This mechanism can transmit teaching signals across multiple layers of neurons and performs as effectively as backpropagation on a variety of tasks. Our results help reopen questions about how the brain could use error signals and dispel long-held assumptions about algorithmic constraints on learning.

Lessons Learned and Flight Results from the F15 Intelligent Flight Control System Project

NASA Technical Reports Server (NTRS)

Bosworth, John

2006-01-01

A viewgraph presentation on the lessons learned and flight results from the F15 Intelligent Flight Control System (IFCS) project is shown. The topics include: 1) F-15 IFCS Project Goals; 2) Motivation; 3) IFCS Approach; 4) NASA F-15 #837 Aircraft Description; 5) Flight Envelope; 6) Limited Authority System; 7) NN Floating Limiter; 8) Flight Experiment; 9) Adaptation Goals; 10) Handling Qualities Performance Metric; 11) Project Phases; 12) Indirect Adaptive Control Architecture; 13) Indirect Adaptive Experience and Lessons Learned; 14) Gen II Direct Adaptive Control Architecture; 15) Current Status; 16) Effect of Canard Multiplier; 17) Simulated Canard Failure Stab Open Loop; 18) Canard Multiplier Effect Closed Loop Freq. Resp.; 19) Simulated Canard Failure Stab Open Loop with Adaptation; 20) Canard Multiplier Effect Closed Loop with Adaptation; 21) Gen 2 NN Wts from Simulation; 22) Direct Adaptive Experience and Lessons Learned; and 23) Conclusions

A Fly-Inspired Mushroom Bodies Model for Sensory-Motor Control Through Sequence and Subsequence Learning.

PubMed

Arena, Paolo; Calí, Marco; Patané, Luca; Portera, Agnese; Strauss, Roland

2016-09-01

Classification and sequence learning are relevant capabilities used by living beings to extract complex information from the environment for behavioral control. The insect world is full of examples where the presentation time of specific stimuli shapes the behavioral response. On the basis of previously developed neural models, inspired by Drosophila melanogaster, a new architecture for classification and sequence learning is here presented under the perspective of the Neural Reuse theory. Classification of relevant input stimuli is performed through resonant neurons, activated by the complex dynamics generated in a lattice of recurrent spiking neurons modeling the insect Mushroom Bodies neuropile. The network devoted to context formation is able to reconstruct the learned sequence and also to trace the subsequences present in the provided input. A sensitivity analysis to parameter variation and noise is reported. Experiments on a roving robot are reported to show the capabilities of the architecture used as a neural controller.

Random synaptic feedback weights support error backpropagation for deep learning

PubMed Central

Lillicrap, Timothy P.; Cownden, Daniel; Tweed, Douglas B.; Akerman, Colin J.

2016-01-01

The brain processes information through multiple layers of neurons. This deep architecture is representationally powerful, but complicates learning because it is difficult to identify the responsible neurons when a mistake is made. In machine learning, the backpropagation algorithm assigns blame by multiplying error signals with all the synaptic weights on each neuron's axon and further downstream. However, this involves a precise, symmetric backward connectivity pattern, which is thought to be impossible in the brain. Here we demonstrate that this strong architectural constraint is not required for effective error propagation. We present a surprisingly simple mechanism that assigns blame by multiplying errors by even random synaptic weights. This mechanism can transmit teaching signals across multiple layers of neurons and performs as effectively as backpropagation on a variety of tasks. Our results help reopen questions about how the brain could use error signals and dispel long-held assumptions about algorithmic constraints on learning. PMID:27824044

Electrical Grounding Architecture for Unmanned Spacecraft

NASA Technical Reports Server (NTRS)

1998-01-01

This handbook is approved for use by NASA Headquarters and all NASA Centers and is intended to provide a common framework for consistent practices across NASA programs. This handbook was developed to describe electrical grounding design architecture options for unmanned spacecraft. This handbook is written for spacecraft system engineers, power engineers, and electromagnetic compatibility (EMC) engineers. Spacecraft grounding architecture is a system-level decision which must be established at the earliest point in spacecraft design. All other grounding design must be coordinated with and be consistent with the system-level architecture. This handbook assumes that there is no one single 'correct' design for spacecraft grounding architecture. There have been many successful satellite and spacecraft programs from NASA, using a variety of grounding architectures with different levels of complexity. However, some design principles learned over the years apply to all types of spacecraft development. This handbook summarizes those principles to help guide spacecraft grounding architecture design for NASA and others.

«

17

18

19

20

21

»

«

18

19

20

21

22

»

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.

Web-Based Learning for Cultural Heritage: First Experienced with Students of the Private University of Technology in Northern Taiwan

NASA Astrophysics Data System (ADS)

Yen, Y.-N.; Wu, Y.-W.; Weng, K.-H.

2013-07-01

E-learning assisted teaching and learning is the trend of the 21st century and has many advantages - freedom from the constraints of time and space, hypertext and multimedia rich resources - enhancing the interaction between students and the teaching materials. The purpose of this study is to explore how rich Internet resources assisted students with the Western Architectural History course. First, we explored the Internet resources which could assist teaching and learning activities. Second, according to course objectives, we built a web-based platform which integrated the Google spreadsheets form, SIMILE widget, Wikipedia and the Google Maps and applied it to the course of Western Architectural History. Finally, action research was applied to understanding the effectiveness of this teaching/learning mode. Participants were the students of the Department of Architecture in the Private University of Technology in northern Taiwan. Results showed that students were willing to use the web-based platform to assist their learning. They found this platform to be useful in understanding the relationship between different periods of buildings. Through the view of the map mode, this platform also helped students expand their international perspective. However, we found that the information shared by students via the Internet were not completely correct. One possible reason was that students could easily acquire information on Internet but they could not determine the correctness of the information. To conclude, this study found some useful and rich resources that could be well-integrated, from which we built a web-based platform to collect information and present this information in diverse modes to stimulate students' learning motivation. We recommend that future studies should consider hiring teaching assistants in order to ease the burden on teachers, and to assist in the maintenance of information quality.

Life-Long Cyberlearning System: A Pilot Project for the "Learning Society" in the ROC.

ERIC Educational Resources Information Center

Han, Huei-Wen; Wang, Yen-Chao

1999-01-01

Provides an overview of the implementation of lifelong learning in Taiwan, Republic of China (ROC) as part of its educational reform policy and describes a pilot project, the Lifelong Cyberlearning System. Highlights include planning architecture, Web-based learning technology, professional education, industrial and corporate assistance, and…

Adaptive Synchronization of Semantically Compressed Instructional Videos for Collaborative Distance Learning

ERIC Educational Resources Information Center

Phung, Dan; Valetto, Giuseppe; Kaiser, Gail E.; Liu, Tiecheng; Kender, John R.

2007-01-01

The increasing popularity of online courses has highlighted the need for collaborative learning tools for student groups. In this article, we present an e-Learning architecture and adaptation model called AI2TV (Adaptive Interactive Internet Team Video), which allows groups of students to collaboratively view instructional videos in synchrony.…

The Intentional Use of Learning Management Systems (LMS) to Improve Outcomes in Studio

ERIC Educational Resources Information Center

MacKenzie, Andrew; Muminovic, Milica; Oerlemans, Karin

2017-01-01

At the University of Canberra, Australia, the design and architecture faculty are trialling a range of approaches to incorporating learning technologies in the first year foundation studio to improve student learning outcomes. For this study researchers collected information on students' access to their assignment information and feedback from the…

Exploiting Redundancy for Flexible Behavior: Unsupervised Learning in a Modular Sensorimotor Control Architecture

ERIC Educational Resources Information Center

Butz, Martin V.; Herbort, Oliver; Hoffmann, Joachim

2007-01-01

Autonomously developing organisms face several challenges when learning reaching movements. First, motor control is learned unsupervised or self-supervised. Second, knowledge of sensorimotor contingencies is acquired in contexts in which action consequences unfold in time. Third, motor redundancies must be resolved. To solve all 3 of these…

Learning Centers: A Report of the 1977 NEH Institute at Ohio State University.

ERIC Educational Resources Information Center

Allen, Edward D.

1978-01-01

A description of the twenty learning center units for advanced classes developed by the French and Spanish teacher-participants. Learning centers permit students to work independently at well-defined tasks. The units deal with housing, shopping, cooking, transportation, sports, fiestas, literature, history, architecture, painting, and music.…

The Role of a Reference Synthetic Data Generator within the Field of Learning Analytics

ERIC Educational Resources Information Center

Berg, Alan\tM.; Mol, Stefan T.; Kismihók, Gábor; Sclater, Niall

2016-01-01

This paper details the anticipated impact of synthetic "big" data on learning analytics (LA) infrastructures, with a particular focus on data governance, the acceleration of service development, and the benchmarking of predictive models. By reviewing two cases, one at the sector-wide level (the Jisc learning analytics architecture) and…

A Conversational Intelligent Tutoring System to Automatically Predict Learning Styles

ERIC Educational Resources Information Center

Latham, Annabel; Crockett, Keeley; McLean, David; Edmonds, Bruce

2012-01-01

This paper proposes a generic methodology and architecture for developing a novel conversational intelligent tutoring system (CITS) called Oscar that leads a tutoring conversation and dynamically predicts and adapts to a student's learning style. Oscar aims to mimic a human tutor by implicitly modelling the learning style during tutoring, and…

Mobile Learning with a Mobile Game: Design and Motivational Effects

ERIC Educational Resources Information Center

Schwabe, Gerhard; Goth, Christoph

2005-01-01

Mobile technologies offer the opportunity to embed learning in a natural environment. This paper describes the design of the MobileGame prototype, exploring the opportunities to support learning through an orientation game in a university setting. The paper first introduces the scenario and then describes the general architecture of the prototype.…

A Collaborative Virtual Environment for Situated Language Learning Using VEC3D

ERIC Educational Resources Information Center

Shih, Ya-Chun; Yang, Mau-Tsuen

2008-01-01

A 3D virtually synchronous communication architecture for situated language learning has been designed to foster communicative competence among undergraduate students who have studied English as a foreign language (EFL). We present an innovative approach that offers better e-learning than the previous virtual reality educational applications. The…

Collaborative Annotation System Environment (CASE) for Online Learning

ERIC Educational Resources Information Center

Glover, Ian; Hardaker, Glenn; Xu, Zhijie

2004-01-01

This paper outlines the design and development process of an online annotation system and how it is applied to the sphere of collaborative online learning. The architecture and design of the annotation system, illustrated in this paper, have been developed to enrich collaborative learning content through adding a layer of information in online…

The "Tutorless" Design Studio: A Radical Experiment in Blended Learning

ERIC Educational Resources Information Center

Hill, Glen Andrew

2017-01-01

This paper describes a pedagogical experiment in which a suite of novel blended learning strategies was used to replace the traditional role of design tutors in a first year architectural design studio. The pedagogical objectives, blended learning strategies and outcomes of the course are detailed. While the quality of the student design work…

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.

Neural Architectures for Control

NASA Technical Reports Server (NTRS)

Peterson, James K.

1991-01-01

The cerebellar model articulated controller (CMAC) neural architectures are shown to be viable for the purposes of real-time learning and control. Software tools for the exploration of CMAC performance are developed for three hardware platforms, the MacIntosh, the IBM PC, and the SUN workstation. All algorithm development was done using the C programming language. These software tools were then used to implement an adaptive critic neuro-control design that learns in real-time how to back up a trailer truck. The truck backer-upper experiment is a standard performance measure in the neural network literature, but previously the training of the controllers was done off-line. With the CMAC neural architectures, it was possible to train the neuro-controllers on-line in real-time on a MS-DOS PC 386. CMAC neural architectures are also used in conjunction with a hierarchical planning approach to find collision-free paths over 2-D analog valued obstacle fields. The method constructs a coarse resolution version of the original problem and then finds the corresponding coarse optimal path using multipass dynamic programming. CMAC artificial neural architectures are used to estimate the analog transition costs that dynamic programming requires. The CMAC architectures are trained in real-time for each obstacle field presented. The coarse optimal path is then used as a baseline for the construction of a fine scale optimal path through the original obstacle array. These results are a very good indication of the potential power of the neural architectures in control design. In order to reach as wide an audience as possible, we have run a seminar on neuro-control that has met once per week since 20 May 1991. This seminar has thoroughly discussed the CMAC architecture, relevant portions of classical control, back propagation through time, and adaptive critic designs.

Hybrid Multiagent System for Automatic Object Learning Classification

NASA Astrophysics Data System (ADS)

Gil, Ana; de La Prieta, Fernando; López, Vivian F.

The rapid evolution within the context of e-learning is closely linked to international efforts on the standardization of learning object metadata, which provides learners in a web-based educational system with ubiquitous access to multiple distributed repositories. This article presents a hybrid agent-based architecture that enables the recovery of learning objects tagged in Learning Object Metadata (LOM) and provides individualized help with selecting learning materials to make the most suitable choice among many alternatives.

A neurocomputational theory of how explicit learning bootstraps early procedural learning.

PubMed

Paul, Erick J; Ashby, F Gregory

2013-01-01

It is widely accepted that human learning and memory is mediated by multiple memory systems that are each best suited to different requirements and demands. Within the domain of categorization, at least two systems are thought to facilitate learning: an explicit (declarative) system depending largely on the prefrontal cortex, and a procedural (non-declarative) system depending on the basal ganglia. Substantial evidence suggests that each system is optimally suited to learn particular categorization tasks. However, it remains unknown precisely how these systems interact to produce optimal learning and behavior. In order to investigate this issue, the present research evaluated the progression of learning through simulation of categorization tasks using COVIS, a well-known model of human category learning that includes both explicit and procedural learning systems. Specifically, the model's parameter space was thoroughly explored in procedurally learned categorization tasks across a variety of conditions and architectures to identify plausible interaction architectures. The simulation results support the hypothesis that one-way interaction between the systems occurs such that the explicit system "bootstraps" learning early on in the procedural system. Thus, the procedural system initially learns a suboptimal strategy employed by the explicit system and later refines its strategy. This bootstrapping could be from cortical-striatal projections that originate in premotor or motor regions of cortex, or possibly by the explicit system's control of motor responses through basal ganglia-mediated loops.

Power Lander for Support of Long-Term Lunar Presence

NASA Technical Reports Server (NTRS)

Joyner, Russ; Rodriguez, Gary

2004-01-01

Emerging industrial base and the consequent sustained manned Lunar presence will require consistent high power capacities. This paper proposes a first iteration design of a flyable electric power platform which could serve as an enabler of Lunar Development and Exploration. It is intended to support a small facility solo or an emerging industrial base as part of a grid. Lunar Missions, Habitats and Facilities stand to benefit from an expected decade of non-stop operation, the economics of scale, Commercial Off-The-Shelf (COTS) availability, standardization of design, and logistical support for Lunar encampments provided by this architecture. The unattended and unmanned vehicle design is to be man- and robotics-serviceable after delivery by current and proposed heavy-lift boosters. Design continuity within a family of systems will improve reliability through "lessons learned'' in the field. Further, various configurations of the proposed scalable architecture will provide reference platforms for the indigenous construction of similar power plant facilities from in-situ Lunar resources (ISRU). The baseline design should be directed towards those materials available on the Moon and expected to be manufacturable on-site within the first decade of operation.

Non parametric, self organizing, scalable modeling of spatiotemporal inputs: the sign language paradigm.

PubMed

Caridakis, G; Karpouzis, K; Drosopoulos, A; Kollias, S

2012-12-01

Modeling and recognizing spatiotemporal, as opposed to static input, is a challenging task since it incorporates input dynamics as part of the problem. The vast majority of existing methods tackle the problem as an extension of the static counterpart, using dynamics, such as input derivatives, at feature level and adopting artificial intelligence and machine learning techniques originally designed for solving problems that do not specifically address the temporal aspect. The proposed approach deals with temporal and spatial aspects of the spatiotemporal domain in a discriminative as well as coupling manner. Self Organizing Maps (SOM) model the spatial aspect of the problem and Markov models its temporal counterpart. Incorporation of adjacency, both in training and classification, enhances the overall architecture with robustness and adaptability. The proposed scheme is validated both theoretically, through an error propagation study, and experimentally, on the recognition of individual signs, performed by different, native Greek Sign Language users. Results illustrate the architecture's superiority when compared to Hidden Markov Model techniques and variations both in terms of classification performance and computational cost. Copyright © 2012 Elsevier Ltd. All rights reserved.

Astrophysics and Big Data: Challenges, Methods, and Tools

NASA Astrophysics Data System (ADS)

Garofalo, Mauro; Botta, Alessio; Ventre, Giorgio

2017-06-01

Nowadays there is no field research which is not flooded with data. Among the sciences, astrophysics has always been driven by the analysis of massive amounts of data. The development of new and more sophisticated observation facilities, both ground-based and spaceborne, has led data more and more complex (Variety), an exponential growth of both data Volume (i.e., in the order of petabytes), and Velocity in terms of production and transmission. Therefore, new and advanced processing solutions will be needed to process this huge amount of data. We investigate some of these solutions, based on machine learning models as well as tools and architectures for Big Data analysis that can be exploited in the astrophysical context.

«

18

19

20

21

22

»

«

19

20

21

22

23

»

Lessons in financial literacy task design: authentic, imaginable, useful

NASA Astrophysics Data System (ADS)

Sawatzki, Carly

2017-03-01

As part of ongoing design-based research exploring financial literacy teaching and learning, 10 tasks termed "financial dilemmas" were trialled by 14 teachers and more than 300 year 5 and 6 students in four government primary schools in urban Darwin. Drawing on data related to three tasks— Catching the bus, Laser Tag and Buying bread—this article explores insights into problem context and task design principles. The findings highlight that fit to circumstance, challenge yet accessibility and pedagogical architecture are important task design principles. Further, tasks involving unfamiliar, novel and imaginable problem contexts, while pedagogically demanding for teachers, can be considered useful by students and have the potential to broaden their horizons.

Mobilizing Disability Experience to Inform Architectural Practice: Lessons Learned from a Field Study

ERIC Educational Resources Information Center

Vermeersch, Peter-Willem; Heylighen, Ann

2015-01-01

Through their bodily interaction with the designed environment, disabled people can detect obstacles and appreciate spatial qualities architects may not be attuned to. While designers in several disciplines acknowledge disabled people as lead or critical users, in architectural practice their embodied experience is hardly recognized as a valuable…

What Did It Look Like Then? Eighteenth Century Architectural Elements.

ERIC Educational Resources Information Center

Taylor, Joshua, Jr.

Designed primarily for use in the intermediate grades, the teaching unit provides 11 lessons and related activities for teaching students to look at colonial architectural elements as a means of learning about 18th century lifestyles. Although the unit relies upon resources available in Alexandria and Arlington, Virginia, other 18th century cities…

Curiositas and Studiositas: Investigating Student Curiosity and the Design Studio

ERIC Educational Resources Information Center

Smith, Korydon

2011-01-01

Curiosity is often considered the foundation of learning. There is, however, little understanding of how (or if) pedagogy in higher education affects student curiosity, especially in the studio setting of architecture, interior design and landscape architecture. This article provides a brief cultural history of curiosity and its role in the design…

Curiosity and Pedagogy: A Mixed-Methods Study of Student Experiences in the Design Studio

ERIC Educational Resources Information Center

Smith, Korydon H.

2010-01-01

Curiosity is often considered the foundation of learning. There is, however, little understanding of how (or if) pedagogy in higher education affects student curiosity, especially in the studio setting of architecture, interior design, and landscape architecture. This study used mixed-methods to investigate curiosity among design students in the…

Human Symbol Manipulation within an Integrated Cognitive Architecture

ERIC Educational Resources Information Center

Anderson, John R.

2005-01-01

This article describes the Adaptive Control of Thought-Rational (ACT-R) cognitive architecture (Anderson et al., 2004; Anderson & Lebiere, 1998) and its detailed application to the learning of algebraic symbol manipulation. The theory is applied to modeling the data from a study by Qin, Anderson, Silk, Stenger, & Carter (2004) in which children…

Architecture of Primary Schools in Serbia in the 21st Century: A Critical Appraisal

ERIC Educational Resources Information Center

Brkovic, Marta

2015-01-01

Since 2000, when education reform in Serbia began education goals, teachers' training, curriculum and teaching/learning methods have been modernised and improved. However, a closer examination of the schools built from 2000 onwards reveals that architectural design of primary schools rests on standardised school design schemes from socialist…

Embodying a cognitive model in a mobile robot

NASA Astrophysics Data System (ADS)

Benjamin, D. Paul; Lyons, Damian; Lonsdale, Deryle

2006-10-01

The ADAPT project is a collaboration of researchers in robotics, linguistics and artificial intelligence at three universities to create a cognitive architecture specifically designed to be embodied in a mobile robot. There are major respects in which existing cognitive architectures are inadequate for robot cognition. In particular, they lack support for true concurrency and for active perception. ADAPT addresses these deficiencies by modeling the world as a network of concurrent schemas, and modeling perception as problem solving. Schemas are represented using the RS (Robot Schemas) language, and are activated by spreading activation. RS provides a powerful language for distributed control of concurrent processes. Also, The formal semantics of RS provides the basis for the semantics of ADAPT's use of natural language. We have implemented the RS language in Soar, a mature cognitive architecture originally developed at CMU and used at a number of universities and companies. Soar's subgoaling and learning capabilities enable ADAPT to manage the complexity of its environment and to learn new schemas from experience. We describe the issues faced in developing an embodied cognitive architecture, and our implementation choices.

Multi-Modal Traveler Information System - Lessons Learned

DOT National Transportation Integrated Search

1997-05-19

The purpose of this working paper is to provide an information base of lessons learned from activities similar to the design of the Gary Chicago Milwaukee (GCM) Corridor Architecture and the Gateway Traveler Information System (TIS). Many similar act...

E-Learning

ERIC Educational Resources Information Center

Buzzi, Marina, Ed.

2010-01-01

E-Learning is a vast and complex research topic that poses many challenges in every aspect: educational and pedagogical strategies and techniques and the tools for achieving them; usability, accessibility and user interface design; knowledge sharing and collaborative environments; technologies, architectures, and protocols; user activity…

Towards a Framework for Modeling Space Systems Architectures

NASA Technical Reports Server (NTRS)

Shames, Peter; Skipper, Joseph

2006-01-01

Topics covered include: 1) Statement of the problem: a) Space system architecture is complex; b) Existing terrestrial approaches must be adapted for space; c) Need a common architecture methodology and information model; d) Need appropriate set of viewpoints. 2) Requirements on a space systems model. 3) Model Based Engineering and Design (MBED) project: a) Evaluated different methods; b) Adapted and utilized RASDS & RM-ODP; c) Identified useful set of viewpoints; d) Did actual model exchanges among selected subset of tools. 4) Lessons learned & future vision.

Spatial integration and cortical dynamics.

PubMed

Gilbert, C D; Das, A; Ito, M; Kapadia, M; Westheimer, G

1996-01-23

Cells in adult primary visual cortex are capable of integrating information over much larger portions of the visual field than was originally thought. Moreover, their receptive field properties can be altered by the context within which local features are presented and by changes in visual experience. The substrate for both spatial integration and cortical plasticity is likely to be found in a plexus of long-range horizontal connections, formed by cortical pyramidal cells, which link cells within each cortical area over distances of 6-8 mm. The relationship between horizontal connections and cortical functional architecture suggests a role in visual segmentation and spatial integration. The distribution of lateral interactions within striate cortex was visualized with optical recording, and their functional consequences were explored by using comparable stimuli in human psychophysical experiments and in recordings from alert monkeys. They may represent the substrate for perceptual phenomena such as illusory contours, surface fill-in, and contour saliency. The dynamic nature of receptive field properties and cortical architecture has been seen over time scales ranging from seconds to months. One can induce a remapping of the topography of visual cortex by making focal binocular retinal lesions. Shorter-term plasticity of cortical receptive fields was observed following brief periods of visual stimulation. The mechanisms involved entailed, for the short-term changes, altering the effectiveness of existing cortical connections, and for the long-term changes, sprouting of axon collaterals and synaptogenesis. The mutability of cortical function implies a continual process of calibration and normalization of the perception of visual attributes that is dependent on sensory experience throughout adulthood and might further represent the mechanism of perceptual learning.

Developing a Long Short-Term Memory (LSTM) based model for predicting water table depth in agricultural areas

NASA Astrophysics Data System (ADS)

Zhang, Jianfeng; Zhu, Yan; Zhang, Xiaoping; Ye, Ming; Yang, Jinzhong

2018-06-01

Predicting water table depth over the long-term in agricultural areas presents great challenges because these areas have complex and heterogeneous hydrogeological characteristics, boundary conditions, and human activities; also, nonlinear interactions occur among these factors. Therefore, a new time series model based on Long Short-Term Memory (LSTM), was developed in this study as an alternative to computationally expensive physical models. The proposed model is composed of an LSTM layer with another fully connected layer on top of it, with a dropout method applied in the first LSTM layer. In this study, the proposed model was applied and evaluated in five sub-areas of Hetao Irrigation District in arid northwestern China using data of 14 years (2000-2013). The proposed model uses monthly water diversion, evaporation, precipitation, temperature, and time as input data to predict water table depth. A simple but effective standardization method was employed to pre-process data to ensure data on the same scale. 14 years of data are separated into two sets: training set (2000-2011) and validation set (2012-2013) in the experiment. As expected, the proposed model achieves higher R2 scores (0.789-0.952) in water table depth prediction, when compared with the results of traditional feed-forward neural network (FFNN), which only reaches relatively low R2 scores (0.004-0.495), proving that the proposed model can preserve and learn previous information well. Furthermore, the validity of the dropout method and the proposed model's architecture are discussed. Through experimentation, the results show that the dropout method can prevent overfitting significantly. In addition, comparisons between the R2 scores of the proposed model and Double-LSTM model (R2 scores range from 0.170 to 0.864), further prove that the proposed model's architecture is reasonable and can contribute to a strong learning ability on time series data. Thus, one can conclude that the proposed model can serve as an alternative approach predicting water table depth, especially in areas where hydrogeological data are difficult to obtain.

Efficient Numeric and Geometric Computations using Heterogeneous Shared Memory Architectures

DTIC Science & Technology

2017-10-04

Report: Efficient Numeric and Geometric Computations using Heterogeneous Shared Memory Architectures The views, opinions and/or findings contained in this...Chapel Hill Title: Efficient Numeric and Geometric Computations using Heterogeneous Shared Memory Architectures Report Term: 0-Other Email: dm...algorithms for scientific and geometric computing by exploiting the power and performance efficiency of heterogeneous shared memory architectures . These

Saliency Detection and Deep Learning-Based Wildfire Identification in UAV Imagery.

PubMed

Zhao, Yi; Ma, Jiale; Li, Xiaohui; Zhang, Jie

2018-02-27

An unmanned aerial vehicle (UAV) equipped with global positioning systems (GPS) can provide direct georeferenced imagery, mapping an area with high resolution. So far, the major difficulty in wildfire image classification is the lack of unified identification marks, the fire features of color, shape, texture (smoke, flame, or both) and background can vary significantly from one scene to another. Deep learning (e.g., DCNN for Deep Convolutional Neural Network) is very effective in high-level feature learning, however, a substantial amount of training images dataset is obligatory in optimizing its weights value and coefficients. In this work, we proposed a new saliency detection algorithm for fast location and segmentation of core fire area in aerial images. As the proposed method can effectively avoid feature loss caused by direct resizing; it is used in data augmentation and formation of a standard fire image dataset 'UAV_Fire'. A 15-layered self-learning DCNN architecture named 'Fire_Net' is then presented as a self-learning fire feature exactor and classifier. We evaluated different architectures and several key parameters (drop out ratio, batch size, etc.) of the DCNN model regarding its validation accuracy. The proposed architecture outperformed previous methods by achieving an overall accuracy of 98%. Furthermore, 'Fire_Net' guarantied an average processing speed of 41.5 ms per image for real-time wildfire inspection. To demonstrate its practical utility, Fire_Net is tested on 40 sampled images in wildfire news reports and all of them have been accurately identified.

Saliency Detection and Deep Learning-Based Wildfire Identification in UAV Imagery

PubMed Central

Zhao, Yi; Ma, Jiale; Li, Xiaohui

2018-01-01

An unmanned aerial vehicle (UAV) equipped with global positioning systems (GPS) can provide direct georeferenced imagery, mapping an area with high resolution. So far, the major difficulty in wildfire image classification is the lack of unified identification marks, the fire features of color, shape, texture (smoke, flame, or both) and background can vary significantly from one scene to another. Deep learning (e.g., DCNN for Deep Convolutional Neural Network) is very effective in high-level feature learning, however, a substantial amount of training images dataset is obligatory in optimizing its weights value and coefficients. In this work, we proposed a new saliency detection algorithm for fast location and segmentation of core fire area in aerial images. As the proposed method can effectively avoid feature loss caused by direct resizing; it is used in data augmentation and formation of a standard fire image dataset ‘UAV_Fire’. A 15-layered self-learning DCNN architecture named ‘Fire_Net’ is then presented as a self-learning fire feature exactor and classifier. We evaluated different architectures and several key parameters (drop out ratio, batch size, etc.) of the DCNN model regarding its validation accuracy. The proposed architecture outperformed previous methods by achieving an overall accuracy of 98%. Furthermore, ‘Fire_Net’ guarantied an average processing speed of 41.5 ms per image for real-time wildfire inspection. To demonstrate its practical utility, Fire_Net is tested on 40 sampled images in wildfire news reports and all of them have been accurately identified. PMID:29495504

Recurrent cerebellar architecture solves the motor-error problem.

PubMed Central

Porrill, John; Dean, Paul; Stone, James V.

2004-01-01

Current views of cerebellar function have been heavily influenced by the models of Marr and Albus, who suggested that the climbing fibre input to the cerebellum acts as a teaching signal for motor learning. It is commonly assumed that this teaching signal must be motor error (the difference between actual and correct motor command), but this approach requires complex neural structures to estimate unobservable motor error from its observed sensory consequences. We have proposed elsewhere a recurrent decorrelation control architecture in which Marr-Albus models learn without requiring motor error. Here, we prove convergence for this architecture and demonstrate important advantages for the modular control of systems with multiple degrees of freedom. These results are illustrated by modelling adaptive plant compensation for the three-dimensional vestibular ocular reflex. This provides a functional role for recurrent cerebellar connectivity, which may be a generic anatomical feature of projections between regions of cerebral and cerebellar cortex. PMID:15255096

Enhanced risk management by an emerging multi-agent architecture

NASA Astrophysics Data System (ADS)

Lin, Sin-Jin; Hsu, Ming-Fu

2014-07-01

Classification in imbalanced datasets has attracted much attention from researchers in the field of machine learning. Most existing techniques tend not to perform well on minority class instances when the dataset is highly skewed because they focus on minimising the forecasting error without considering the relative distribution of each class. This investigation proposes an emerging multi-agent architecture, grounded on cooperative learning, to solve the class-imbalanced classification problem. Additionally, this study deals further with the obscure nature of the multi-agent architecture and expresses comprehensive rules for auditors. The results from this study indicate that the presented model performs satisfactorily in risk management and is able to tackle a highly class-imbalanced dataset comparatively well. Furthermore, the knowledge visualised process, supported by real examples, can assist both internal and external auditors who must allocate limited detecting resources; they can take the rules as roadmaps to modify the auditing programme.

Sample RFP for Architectural Services, 2000.

ERIC Educational Resources Information Center

Arizona State School Facilities Board, Phoenix.

This document presents a sample request for proposal that Arizona school districts can use when requesting architectural services, from the general request requirements to response information and signature sheet. General proposal requirements cover such areas as information on special terms and conditions, the scope of architectural services…

47 CFR 52.25 - Database architecture and administration.

Code of Federal Regulations, 2014 CFR

2014-10-01

... 47 Telecommunication 3 2014-10-01 2014-10-01 false Database architecture and administration. 52.25... (CONTINUED) NUMBERING Number Portability § 52.25 Database architecture and administration. (a) The North... databases for the provision of long-term database methods for number portability. (b) All telecommunications...

«

19

20

21

22

23

»

«

20

21

22

23

24

»

47 CFR 52.25 - Database architecture and administration.

Code of Federal Regulations, 2012 CFR

2012-10-01

... 47 Telecommunication 3 2012-10-01 2012-10-01 false Database architecture and administration. 52.25... (CONTINUED) NUMBERING Number Portability § 52.25 Database architecture and administration. (a) The North... databases for the provision of long-term database methods for number portability. (b) All telecommunications...

47 CFR 52.25 - Database architecture and administration.

Code of Federal Regulations, 2010 CFR

2010-10-01

... 47 Telecommunication 3 2010-10-01 2010-10-01 false Database architecture and administration. 52.25... (CONTINUED) NUMBERING Number Portability § 52.25 Database architecture and administration. (a) The North... databases for the provision of long-term database methods for number portability. (b) All telecommunications...

47 CFR 52.25 - Database architecture and administration.

Code of Federal Regulations, 2013 CFR

2013-10-01

... 47 Telecommunication 3 2013-10-01 2013-10-01 false Database architecture and administration. 52.25... (CONTINUED) NUMBERING Number Portability § 52.25 Database architecture and administration. (a) The North... databases for the provision of long-term database methods for number portability. (b) All telecommunications...

47 CFR 52.25 - Database architecture and administration.

Code of Federal Regulations, 2011 CFR

2011-10-01

... 47 Telecommunication 3 2011-10-01 2011-10-01 false Database architecture and administration. 52.25... (CONTINUED) NUMBERING Number Portability § 52.25 Database architecture and administration. (a) The North... databases for the provision of long-term database methods for number portability. (b) All telecommunications...

A Robust Deep-Learning-Based Detector for Real-Time Tomato Plant Diseases and Pests Recognition.

PubMed

Fuentes, Alvaro; Yoon, Sook; Kim, Sang Cheol; Park, Dong Sun

2017-09-04

Plant Diseases and Pests are a major challenge in the agriculture sector. An accurate and a faster detection of diseases and pests in plants could help to develop an early treatment technique while substantially reducing economic losses. Recent developments in Deep Neural Networks have allowed researchers to drastically improve the accuracy of object detection and recognition systems. In this paper, we present a deep-learning-based approach to detect diseases and pests in tomato plants using images captured in-place by camera devices with various resolutions. Our goal is to find the more suitable deep-learning architecture for our task. Therefore, we consider three main families of detectors: Faster Region-based Convolutional Neural Network (Faster R-CNN), Region-based Fully Convolutional Network (R-FCN), and Single Shot Multibox Detector (SSD), which for the purpose of this work are called "deep learning meta-architectures". We combine each of these meta-architectures with "deep feature extractors" such as VGG net and Residual Network (ResNet). We demonstrate the performance of deep meta-architectures and feature extractors, and additionally propose a method for local and global class annotation and data augmentation to increase the accuracy and reduce the number of false positives during training. We train and test our systems end-to-end on our large Tomato Diseases and Pests Dataset, which contains challenging images with diseases and pests, including several inter- and extra-class variations, such as infection status and location in the plant. Experimental results show that our proposed system can effectively recognize nine different types of diseases and pests, with the ability to deal with complex scenarios from a plant's surrounding area.

Identification of emergent off-nominal operational requirements during conceptual architecting of the more electric aircraft

NASA Astrophysics Data System (ADS)

Armstrong, Michael James

Increases in power demands and changes in the design practices of overall equipment manufacturers has led to a new paradigm in vehicle systems definition. The development of unique power systems architectures is of increasing importance to overall platform feasibility and must be pursued early in the aircraft design process. Many vehicle systems architecture trades must be conducted concurrent to platform definition. With an increased complexity introduced during conceptual design, accurate predictions of unit level sizing requirements must be made. Architecture specific emergent requirements must be identified which arise due to the complex integrated effect of unit behaviors. Off-nominal operating scenarios present sizing critical requirements to the aircraft vehicle systems. These requirements are architecture specific and emergent. Standard heuristically defined failure mitigation is sufficient for sizing traditional and evolutionary architectures. However, architecture concepts which vary significantly in terms of structure and composition require that unique failure mitigation strategies be defined for accurate estimations of unit level requirements. Identifying of these off-nominal emergent operational requirements require extensions to traditional safety and reliability tools and the systematic identification of optimal performance degradation strategies. Discrete operational constraints posed by traditional Functional Hazard Assessment (FHA) are replaced by continuous relationships between function loss and operational hazard. These relationships pose the objective function for hazard minimization. Load shedding optimization is performed for all statistically significant failures by varying the allocation of functional capability throughout the vehicle systems architecture. Expressing hazards, and thereby, reliability requirements as continuous relationships with the magnitude and duration of functional failure requires augmentations to the traditional means for system safety assessment (SSA). The traditional two state and discrete system reliability assessment proves insufficient. Reliability is, therefore, handled in an analog fashion: as a function of magnitude of failure and failure duration. A series of metrics are introduced which characterize system performance in terms of analog hazard probabilities. These include analog and cumulative system and functional risk, hazard correlation, and extensions to the traditional component importance metrics. Continuous FHA, load shedding optimization, and analog SSA constitute the SONOMA process (Systematic Off-Nominal Requirements Analysis). Analog system safety metrics inform both architecture optimization (changes in unit level capability and reliability) and architecture augmentation (changes in architecture structure and composition). This process was applied for two vehicle systems concepts (conventional and 'more-electric') in terms of loss/hazard relationships with varying degrees of fidelity. Application of this process shows that the traditional assumptions regarding the structure of the function loss vs. hazard relationship apply undue design bias to functions and components during exploratory design. This bias is illustrated in terms of inaccurate estimations of the system and function level risk and unit level importance. It was also shown that off-nominal emergent requirements must be defined specific to each architecture concept. Quantitative comparisons of architecture specific off-nominal performance were obtained which provide evidence to the need for accurate definition of load shedding strategies during architecture exploratory design. Formally expressing performance degradation strategies in terms of the minimization of a continuous hazard space enhances the system architects ability to accurately predict sizing critical emergent requirements concurrent to architecture definition. Furthermore, the methods and frameworks generated here provide a structured and flexible means for eliciting these architecture specific requirements during the performance of architecture trades.

Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands

PubMed Central

Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

2016-01-01

Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too. PMID:27656140

Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands.

PubMed

Atzori, Manfredo; Cognolato, Matteo; Müller, Henning

2016-01-01

Natural control methods based on surface electromyography (sEMG) and pattern recognition are promising for hand prosthetics. However, the control robustness offered by scientific research is still not sufficient for many real life applications, and commercial prostheses are capable of offering natural control for only a few movements. In recent years deep learning revolutionized several fields of machine learning, including computer vision and speech recognition. Our objective is to test its methods for natural control of robotic hands via sEMG using a large number of intact subjects and amputees. We tested convolutional networks for the classification of an average of 50 hand movements in 67 intact subjects and 11 transradial amputees. The simple architecture of the neural network allowed to make several tests in order to evaluate the effect of pre-processing, layer architecture, data augmentation and optimization. The classification results are compared with a set of classical classification methods applied on the same datasets. The classification accuracy obtained with convolutional neural networks using the proposed architecture is higher than the average results obtained with the classical classification methods, but lower than the results obtained with the best reference methods in our tests. The results show that convolutional neural networks with a very simple architecture can produce accurate results comparable to the average classical classification methods. They show that several factors (including pre-processing, the architecture of the net and the optimization parameters) can be fundamental for the analysis of sEMG data. Larger networks can achieve higher accuracy on computer vision and object recognition tasks. This fact suggests that it may be interesting to evaluate if larger networks can increase sEMG classification accuracy too.

The Sound of Learning.

ERIC Educational Resources Information Center

Anderson, Karen L.

1997-01-01

Children often struggle in noisy classrooms. Many classrooms being planned duplicate acoustically inadequate 50-year-old designs that cannot accommodate group learning and hands-on science. The Architectural and Transportation Barriers Compliance Board, which enforces Individuals with Disabilities Education Act regulations, has been asked to…

The "Total Immersion" Meeting Environment.

ERIC Educational Resources Information Center

Finkel, Coleman

1980-01-01

The designing of intelligently planned meeting facilities can aid management communication and learning. The author examines the psychology of meeting attendance; architectural considerations (lighting, windows, color, etc.); design elements and learning modes (furniture, walls, audiovisuals, materials); and the idea of "total immersion meeting…

Designing Science Laboratories: Learning Environments, School Architecture and Teaching and Learning Models

ERIC Educational Resources Information Center

Veloso, Luísa; Marques, Joana S.

2017-01-01

This article on secondary schools science laboratories in Portugal focuses on how school space functions as a pedagogical and political instrument by contributing to shape the conditions for teaching and learning dynamics. The article places the impact of changes to school layouts within the larger context of a public school renovation programme,…

Moving towards Optimising Demand-Led Learning: The 2005-2007 ECUANET Leonardo Da Vinci Project

ERIC Educational Resources Information Center

Dealtry, Richard; Howard, Keith

2008-01-01

Purpose: The purpose of this paper is to present the key project learning points and outcomes as a guideline for the future quality management of demand-led learning and development. Design/methodology/approach: The research methodology was based upon a corporate university blueprint architecture and browser toolkit developed by a member of the…

Hidden Dangers of Computer Modelling: Remarks on Sokolik and Smith's Connectionist Learning Model of French Gender.

ERIC Educational Resources Information Center

Carroll, Susanne E.

1995-01-01

Criticizes the computer modelling experiments conducted by Sokolik and Smith (1992), which involved the learning of French gender attribution using connectionist architecture. The article argues that the experiments greatly oversimplified the complexity of gender learning, in that they were designed in such a way that knowledge that must be…

Design Principles of an Open Agent Architecture for Web-Based Learning Community.

ERIC Educational Resources Information Center

Jin, Qun; Ma, Jianhua; Huang, Runhe; Shih, Timothy K.

A Web-based learning community involves much more than putting learning materials into a Web site. It can be seen as a complex virtual organization involved with people, facilities, and cyber-environment. Tremendous work and manpower for maintaining, upgrading, and managing facilities and the cyber-environment are required. There is presented an…

Incidental Learning Speeds Visual Search by Lowering Response Thresholds, Not by Improving Efficiency: Evidence from Eye Movements

ERIC Educational Resources Information Center

Hout, Michael C.; Goldinger, Stephen D.

2012-01-01

When observers search for a target object, they incidentally learn the identities and locations of "background" objects in the same display. This learning can facilitate search performance, eliciting faster reaction times for repeated displays. Despite these findings, visual search has been successfully modeled using architectures that maintain no…

A Study Exploring Learners' Informal Learning Space Behaviors, Attitudes, and Preferences

ERIC Educational Resources Information Center

Harrop, Deborah; Turpin, Bea

2013-01-01

What makes a successful informal learning space is a topic in need of further research. The body of discourse on informal space design is drawn from learning theory, placemaking, and architecture, with a need for understanding of the synergy between the three. Findings from a longitudinal, quantitative, and qualitative study at Sheffield Hallam…

Moving across Physical and Online Spaces: A Case Study in a Blended Primary Classroom

ERIC Educational Resources Information Center

Thibaut, Patricia; Curwood, Jen Scott; Carvalho, Lucila; Simpson, Alyson

2015-01-01

With the introduction of digital tools and online connectivity in primary schools, the shape of teaching and learning is shifting beyond the physical classroom. Drawing on the architecture of productive learning networks framework, we examine the affordances and limitations of an upper primary learning network and focus on how the digital and…

Evaluation of the impact of deep learning architectural components selection and dataset size on a medical imaging task

NASA Astrophysics Data System (ADS)

Dutta, Sandeep; Gros, Eric

2018-03-01

Deep Learning (DL) has been successfully applied in numerous fields fueled by increasing computational power and access to data. However, for medical imaging tasks, limited training set size is a common challenge when applying DL. This paper explores the applicability of DL to the task of classifying a single axial slice from a CT exam into one of six anatomy regions. A total of 29000 images selected from 223 CT exams were manually labeled for ground truth. An additional 54 exams were labeled and used as an independent test set. The network architecture developed for this application is composed of 6 convolutional layers and 2 fully connected layers with RELU non-linear activations between each layer. Max-pooling was used after every second convolutional layer, and a softmax layer was used at the end. Given this base architecture, the effect of inclusion of network architecture components such as Dropout and Batch Normalization on network performance and training is explored. The network performance as a function of training and validation set size is characterized by training each network architecture variation using 5,10,20,40,50 and 100% of the available training data. The performance comparison of the various network architectures was done for anatomy classification as well as two computer vision datasets. The anatomy classifier accuracy varied from 74.1% to 92.3% in this study depending on the training size and network layout used. Dropout layers improved the model accuracy for all training sizes.

Convolutional neural network architectures for predicting DNA–protein binding

PubMed Central

Zeng, Haoyang; Edwards, Matthew D.; Liu, Ge; Gifford, David K.

2016-01-01

Motivation: Convolutional neural networks (CNN) have outperformed conventional methods in modeling the sequence specificity of DNA–protein binding. Yet inappropriate CNN architectures can yield poorer performance than simpler models. Thus an in-depth understanding of how to match CNN architecture to a given task is needed to fully harness the power of CNNs for computational biology applications. Results: We present a systematic exploration of CNN architectures for predicting DNA sequence binding using a large compendium of transcription factor datasets. We identify the best-performing architectures by varying CNN width, depth and pooling designs. We find that adding convolutional kernels to a network is important for motif-based tasks. We show the benefits of CNNs in learning rich higher-order sequence features, such as secondary motifs and local sequence context, by comparing network performance on multiple modeling tasks ranging in difficulty. We also demonstrate how careful construction of sequence benchmark datasets, using approaches that control potentially confounding effects like positional or motif strength bias, is critical in making fair comparisons between competing methods. We explore how to establish the sufficiency of training data for these learning tasks, and we have created a flexible cloud-based framework that permits the rapid exploration of alternative neural network architectures for problems in computational biology. Availability and Implementation: All the models analyzed are available at http://cnn.csail.mit.edu. Contact: gifford@mit.edu Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27307608

Joint Segmentation of Multiple Thoracic Organs in CT Images with Two Collaborative Deep Architectures.

PubMed

Trullo, Roger; Petitjean, Caroline; Nie, Dong; Shen, Dinggang; Ruan, Su

2017-09-01

Computed Tomography (CT) is the standard imaging technique for radiotherapy planning. The delineation of Organs at Risk (OAR) in thoracic CT images is a necessary step before radiotherapy, for preventing irradiation of healthy organs. However, due to low contrast, multi-organ segmentation is a challenge. In this paper, we focus on developing a novel framework for automatic delineation of OARs. Different from previous works in OAR segmentation where each organ is segmented separately, we propose two collaborative deep architectures to jointly segment all organs, including esophagus, heart, aorta and trachea. Since most of the organ borders are ill-defined, we believe spatial relationships must be taken into account to overcome the lack of contrast. The aim of combining two networks is to learn anatomical constraints with the first network, which will be used in the second network, when each OAR is segmented in turn. Specifically, we use the first deep architecture, a deep SharpMask architecture, for providing an effective combination of low-level representations with deep high-level features, and then take into account the spatial relationships between organs by the use of Conditional Random Fields (CRF). Next, the second deep architecture is employed to refine the segmentation of each organ by using the maps obtained on the first deep architecture to learn anatomical constraints for guiding and refining the segmentations. Experimental results show superior performance on 30 CT scans, comparing with other state-of-the-art methods.

«

20

21

22

23

24

»

«

21

22

23

24

25

»

Playable Serious Games for Studying and Programming Computational STEM and Informatics Applications of Distributed and Parallel Computer Architectures

ERIC Educational Resources Information Center

Amenyo, John-Thones

2012-01-01

Carefully engineered playable games can serve as vehicles for students and practitioners to learn and explore the programming of advanced computer architectures to execute applications, such as high performance computing (HPC) and complex, inter-networked, distributed systems. The article presents families of playable games that are grounded in…

Analysis of Introducing Active Learning Methodologies in a Basic Computer Architecture Course

ERIC Educational Resources Information Center

Arbelaitz, Olatz; José I. Martín; Muguerza, Javier

2015-01-01

This paper presents an analysis of introducing active methodologies in the Computer Architecture course taught in the second year of the Computer Engineering Bachelor's degree program at the University of the Basque Country (UPV/EHU), Spain. The paper reports the experience from three academic years, 2011-2012, 2012-2013, and 2013-2014, in which…

Architecture as a Primary Source for Social Studies. How To Do It Series, Series 2, Number 5.

ERIC Educational Resources Information Center

Leclerc, Daniel C.

Designed for elementary and secondary use in the social studies, this guide provides activities for learning the basic elements and the history of architecture. Through this study, students develop critical observation skills and investigate buildings as manifestations of religious, social, and personal values. The historical overview traces the…

Be a Building Watcher on the Street Where You Live.

ERIC Educational Resources Information Center

Historic Landmarks Foundation of Indiana, Indianapolis.

Architecture is an art form and a guide to the study of history. By increasing visual awareness of the architectural environment more is learned about the history and cultural heritage of an area, region, or country. In addition, an appreciation for fine craftsmanship, good design, and their influences on individual lives is developed. The article…

Component Architectures and Web-Based Learning Environments

ERIC Educational Resources Information Center

Ferdig, Richard E.; Mishra, Punya; Zhao, Yong

2004-01-01

The Web has caught the attention of many educators as an efficient communication medium and content delivery system. But we feel there is another aspect of the Web that has not been given the attention it deserves. We call this aspect of the Web its "component architecture." Briefly it means that on the Web one can develop very complex…

A Project-Based Learning Approach to Programmable Logic Design and Computer Architecture

ERIC Educational Resources Information Center

Kellett, C. M.

2012-01-01

This paper describes a course in programmable logic design and computer architecture as it is taught at the University of Newcastle, Australia. The course is designed around a major design project and has two supplemental assessment tasks that are also described. The context of the Computer Engineering degree program within which the course is…

From Archi Torture to Architecture: Undergraduate Students Design and Implement Computers Using the Multimedia Logic Emulator

ERIC Educational Resources Information Center

Stanley, Timothy D.; Wong, Lap Kei; Prigmore, Daniel; Benson, Justin; Fishler, Nathan; Fife, Leslie; Colton, Don

2007-01-01

Students learn better when they both hear and do. In computer architecture courses "doing" can be difficult in small schools without hardware laboratories hosted by computer engineering, electrical engineering, or similar departments. Software solutions exist. Our success with George Mills' Multimedia Logic (MML) is the focus of this paper. MML…

Neural Network Classifier Architectures for Phoneme Recognition. CRC Technical Note No. CRC-TN-92-001.

ERIC Educational Resources Information Center

Treurniet, William

A study applied artificial neural networks, trained with the back-propagation learning algorithm, to modelling phonemes extracted from the DARPA TIMIT multi-speaker, continuous speech data base. A number of proposed network architectures were applied to the phoneme classification task, ranging from the simple feedforward multilayer network to more…

MIT CSAIL and Lincoln Laboratory Task Force Report

DTIC Science & Technology

2016-08-01

projects have been very diverse, spanning several areas of CSAIL concentration, including robotics, big data analytics , wireless communications...spanning several areas of CSAIL concentration, including robotics, big data analytics , wireless communications, computing architectures and...to machine learning systems and algorithms, such as recommender systems, and “Big Data ” analytics . Advanced computing architectures broadly refer to

Toward cognitive robotics

NASA Astrophysics Data System (ADS)

Laird, John E.

2009-05-01

Our long-term goal is to develop autonomous robotic systems that have the cognitive abilities of humans, including communication, coordination, adapting to novel situations, and learning through experience. Our approach rests on the recent integration of the Soar cognitive architecture with both virtual and physical robotic systems. Soar has been used to develop a wide variety of knowledge-rich agents for complex virtual environments, including distributed training environments and interactive computer games. For development and testing in robotic virtual environments, Soar interfaces to a variety of robotic simulators and a simple mobile robot. We have recently made significant extensions to Soar that add new memories and new non-symbolic reasoning to Soar's original symbolic processing, which should significantly improve Soar abilities for control of robots. These extensions include episodic memory, semantic memory, reinforcement learning, and mental imagery. Episodic memory and semantic memory support the learning and recalling of prior events and situations as well as facts about the world. Reinforcement learning provides the ability of the system to tune its procedural knowledge - knowledge about how to do things. Mental imagery supports the use of diagrammatic and visual representations that are critical to support spatial reasoning. We speculate on the future of unmanned systems and the need for cognitive robotics to support dynamic instruction and taskability.

Humanoid infers Archimedes' principle: understanding physical relations and object affordances through cumulative learning experiences

PubMed Central

2016-01-01

Emerging studies indicate that several species such as corvids, apes and children solve ‘The Crow and the Pitcher’ task (from Aesop's Fables) in diverse conditions. Hidden beneath this fascinating paradigm is a fundamental question: by cumulatively interacting with different objects, how can an agent abstract the underlying cause–effect relations to predict and creatively exploit potential affordances of novel objects in the context of sought goals? Re-enacting this Aesop's Fable task on a humanoid within an open-ended ‘learning–prediction–abstraction’ loop, we address this problem and (i) present a brain-guided neural framework that emulates rapid one-shot encoding of ongoing experiences into a long-term memory and (ii) propose four task-agnostic learning rules (elimination, growth, uncertainty and status quo) that correlate predictions from remembered past experiences with the unfolding present situation to gradually abstract the underlying causal relations. Driven by the proposed architecture, the ensuing robot behaviours illustrated causal learning and anticipation similar to natural agents. Results further demonstrate that by cumulatively interacting with few objects, the predictions of the robot in case of novel objects converge close to the physical law, i.e. the Archimedes principle: this being independent of both the objects explored during learning and the order of their cumulative exploration. PMID:27466440

Deep Recurrent Neural Networks for Human Activity Recognition

PubMed Central

Murad, Abdulmajid

2017-01-01

Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs) address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs) for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM) DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM) and k-nearest neighbors (KNN). Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs) and CNNs. PMID:29113103

Deep Recurrent Neural Networks for Human Activity Recognition.

PubMed

Murad, Abdulmajid; Pyun, Jae-Young

2017-11-06

Adopting deep learning methods for human activity recognition has been effective in extracting discriminative features from raw input sequences acquired from body-worn sensors. Although human movements are encoded in a sequence of successive samples in time, typical machine learning methods perform recognition tasks without exploiting the temporal correlations between input data samples. Convolutional neural networks (CNNs) address this issue by using convolutions across a one-dimensional temporal sequence to capture dependencies among input data. However, the size of convolutional kernels restricts the captured range of dependencies between data samples. As a result, typical models are unadaptable to a wide range of activity-recognition configurations and require fixed-length input windows. In this paper, we propose the use of deep recurrent neural networks (DRNNs) for building recognition models that are capable of capturing long-range dependencies in variable-length input sequences. We present unidirectional, bidirectional, and cascaded architectures based on long short-term memory (LSTM) DRNNs and evaluate their effectiveness on miscellaneous benchmark datasets. Experimental results show that our proposed models outperform methods employing conventional machine learning, such as support vector machine (SVM) and k-nearest neighbors (KNN). Additionally, the proposed models yield better performance than other deep learning techniques, such as deep believe networks (DBNs) and CNNs.

Application of fuzzy logic-neural network based reinforcement learning to proximity and docking operations: Special approach/docking testcase results

NASA Technical Reports Server (NTRS)

Jani, Yashvant

1993-01-01

As part of the RICIS project, the reinforcement learning techniques developed at Ames Research Center are being applied to proximity and docking operations using the Shuttle and Solar Maximum Mission (SMM) satellite simulation. In utilizing these fuzzy learning techniques, we use the Approximate Reasoning based Intelligent Control (ARIC) architecture, and so we use these two terms interchangeably to imply the same. This activity is carried out in the Software Technology Laboratory utilizing the Orbital Operations Simulator (OOS) and programming/testing support from other contractor personnel. This report is the final deliverable D4 in our milestones and project activity. It provides the test results for the special testcase of approach/docking scenario for the shuttle and SMM satellite. Based on our experience and analysis with the attitude and translational controllers, we have modified the basic configuration of the reinforcement learning algorithm in ARIC. The shuttle translational controller and its implementation in ARIC is described in our deliverable D3. In order to simulate the final approach and docking operations, we have set-up this special testcase as described in section 2. The ARIC performance results for these operations are discussed in section 3 and conclusions are provided in section 4 along with the summary for the project.

Sustaining a Global Social Network: a quasi-experimental study.

PubMed

Benton, D C; Ferguson, S L

2017-03-01

To examine the longer term impact on the social network of participating nurses in the Global Nursing Leadership Institute (GNLI2013) through using differing frequencies of follow-up to assess impact on maintenance of network cohesion. Social network analysis is increasingly been used by nurse researchers, however, studies tend to use single point-in-time descriptive methods. This study utilizes a repeated measures, block group, control-intervention, quasi-experimental design. Twenty-eight nurse leaders, competitively selected through a double-blind peer review process, were allocated to five action learning-based learning groups. Network architecture, measures of cohesion and node degree frequency were all used to assess programme impact. The programme initiated and sustained connections between nurse leaders drawn from a geographically dispersed heterogeneous group. Modest inputs of two to three e-mails over a 6-month period seem sufficient to maintain connectivity as indicated by measures of network density, diameter and path length. Due to the teaching methodology used, the study sample was relatively small and the follow-up data collection took place after a relatively short time. Replication and further cohort data collection would be advantageous. In an era where many policy solutions are being debated and initiated at the global level, action learning leadership development that utilizes new technology follow-up appears to show significant impact and is worthy of wider application. The approach warrants further inquiry and testing as to its longer term effects on nursing's influence on policy formulation and implementation. © 2016 International Council of Nurses.

Middle Level Learning.

ERIC Educational Resources Information Center

Rothwell, Jennifer; Levy, Tedd; Manaster, Jane; Bernson, Mary Hammond

1998-01-01

Presents a pull-out section that includes four brief articles and accompanying learning activities. The articles include an architectural examination of the move from medieval fort to Renaissance palace, interdisciplinary biographical writing assignments, a look at the portrayal of people with disabilities in juvenile literature, and material on…

Advanced Networks in Dental Rich Online MEDiA (ANDROMEDA)

NASA Astrophysics Data System (ADS)

Elson, Bruce; Reynolds, Patricia; Amini, Ardavan; Burke, Ezra; Chapman, Craig

There is growing demand for dental education and training not only in terms of knowledge but also skills. This demand is driven by continuing professional development requirements in the more developed economies, personnel shortages and skills differences across the European Union (EU) accession states and more generally in the developing world. There is an excellent opportunity for the EU to meet this demand by developing an innovative online flexible learning platform (FLP). Current clinical online systems are restricted to the delivery of general, knowledge-based training with no easy method of personalization or delivery of skill-based training. The PHANTOM project, headed by Kings College London is developing haptic-based virtual reality training systems for clinical dental training. ANDROMEDA seeks to build on this and establish a Flexible Learning Platform that can integrate the haptic and sensor based training with rich media knowledge transfer, whilst using sophisticated technologies such as including service-orientated architecture (SOA), Semantic Web technologies, knowledge-based engineering, business intelligence (BI) and virtual worlds for personalization.

Training echo state networks for rotation-invariant bone marrow cell classification.

PubMed

Kainz, Philipp; Burgsteiner, Harald; Asslaber, Martin; Ahammer, Helmut

2017-01-01

The main principle of diagnostic pathology is the reliable interpretation of individual cells in context of the tissue architecture. Especially a confident examination of bone marrow specimen is dependent on a valid classification of myeloid cells. In this work, we propose a novel rotation-invariant learning scheme for multi-class echo state networks (ESNs), which achieves very high performance in automated bone marrow cell classification. Based on representing static images as temporal sequence of rotations, we show how ESNs robustly recognize cells of arbitrary rotations by taking advantage of their short-term memory capacity. The performance of our approach is compared to a classification random forest that learns rotation-invariance in a conventional way by exhaustively training on multiple rotations of individual samples. The methods were evaluated on a human bone marrow image database consisting of granulopoietic and erythropoietic cells in different maturation stages. Our ESN approach to cell classification does not rely on segmentation of cells or manual feature extraction and can therefore directly be applied to image data.

Adaptive learning in a compartmental model of visual cortex—how feedback enables stable category learning and refinement

PubMed Central

Layher, Georg; Schrodt, Fabian; Butz, Martin V.; Neumann, Heiko

2014-01-01

The categorization of real world objects is often reflected in the similarity of their visual appearances. Such categories of objects do not necessarily form disjunct sets of objects, neither semantically nor visually. The relationship between categories can often be described in terms of a hierarchical structure. For instance, tigers and leopards build two separate mammalian categories, both of which are subcategories of the category Felidae. In the last decades, the unsupervised learning of categories of visual input stimuli has been addressed by numerous approaches in machine learning as well as in computational neuroscience. However, the question of what kind of mechanisms might be involved in the process of subcategory learning, or category refinement, remains a topic of active investigation. We propose a recurrent computational network architecture for the unsupervised learning of categorial and subcategorial visual input representations. During learning, the connection strengths of bottom-up weights from input to higher-level category representations are adapted according to the input activity distribution. In a similar manner, top-down weights learn to encode the characteristics of a specific stimulus category. Feedforward and feedback learning in combination realize an associative memory mechanism, enabling the selective top-down propagation of a category's feedback weight distribution. We suggest that the difference between the expected input encoded in the projective field of a category node and the current input pattern controls the amplification of feedforward-driven representations. Large enough differences trigger the recruitment of new representational resources and the establishment of additional (sub-) category representations. We demonstrate the temporal evolution of such learning and show how the proposed combination of an associative memory with a modulatory feedback integration successfully establishes category and subcategory representations. PMID:25538637

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.

«

21

22

23

24

25

»

«

21

22

23

24

25

»

Exemplar-Based Image and Video Stylization Using Fully Convolutional Semantic Features.

PubMed

Zhu, Feida; Yan, Zhicheng; Bu, Jiajun; Yu, Yizhou

2017-05-10

Color and tone stylization in images and videos strives to enhance unique themes with artistic color and tone adjustments. It has a broad range of applications from professional image postprocessing to photo sharing over social networks. Mainstream photo enhancement softwares, such as Adobe Lightroom and Instagram, provide users with predefined styles, which are often hand-crafted through a trial-and-error process. Such photo adjustment tools lack a semantic understanding of image contents and the resulting global color transform limits the range of artistic styles it can represent. On the other hand, stylistic enhancement needs to apply distinct adjustments to various semantic regions. Such an ability enables a broader range of visual styles. In this paper, we first propose a novel deep learning architecture for exemplar-based image stylization, which learns local enhancement styles from image pairs. Our deep learning architecture consists of fully convolutional networks (FCNs) for automatic semantics-aware feature extraction and fully connected neural layers for adjustment prediction. Image stylization can be efficiently accomplished with a single forward pass through our deep network. To extend our deep network from image stylization to video stylization, we exploit temporal superpixels (TSPs) to facilitate the transfer of artistic styles from image exemplars to videos. Experiments on a number of datasets for image stylization as well as a diverse set of video clips demonstrate the effectiveness of our deep learning architecture.

Joint multiple fully connected convolutional neural network with extreme learning machine for hepatocellular carcinoma nuclei grading.

PubMed

Li, Siqi; Jiang, Huiyan; Pang, Wenbo

2017-05-01

Accurate cell grading of cancerous tissue pathological image is of great importance in medical diagnosis and treatment. This paper proposes a joint multiple fully connected convolutional neural network with extreme learning machine (MFC-CNN-ELM) architecture for hepatocellular carcinoma (HCC) nuclei grading. First, in preprocessing stage, each grayscale image patch with the fixed size is obtained using center-proliferation segmentation (CPS) method and the corresponding labels are marked under the guidance of three pathologists. Next, a multiple fully connected convolutional neural network (MFC-CNN) is designed to extract the multi-form feature vectors of each input image automatically, which considers multi-scale contextual information of deep layer maps sufficiently. After that, a convolutional neural network extreme learning machine (CNN-ELM) model is proposed to grade HCC nuclei. Finally, a back propagation (BP) algorithm, which contains a new up-sample method, is utilized to train MFC-CNN-ELM architecture. The experiment comparison results demonstrate that our proposed MFC-CNN-ELM has superior performance compared with related works for HCC nuclei grading. Meanwhile, external validation using ICPR 2014 HEp-2 cell dataset shows the good generalization of our MFC-CNN-ELM architecture. Copyright © 2017 Elsevier Ltd. All rights reserved.

The role of taxonomies in social media and the semantic web for health education. A study of SNOMED CT terms in YouTube health video tags.

PubMed

Konstantinidis, S; Fernandez-Luque, L; Bamidis, P; Karlsen, R

2013-01-01

An increasing amount of health education resources for patients and professionals are distributed via social media channels. For example, thousands of health education videos are disseminated via YouTube. Often, tags are assigned by the disseminator. However, the lack of use of standardized terminologies in those tags and the presence of misleading videos make it particularly hard to retrieve relevant videos. i) Identify the use of standardized medical thesauri (SNOMED CT) in YouTube Health videos tags from preselected YouTube Channels and demonstrate an information technology (IT) architecture for treating the tags of these health (video) resources. ii) Investigate the relative percentage of the tags used that relate to SNOMED CT terms. As such resources may play a key role in educating professionals and patients, the use of standardized vocabularies may facilitate the sharing of such resources. iii) Demonstrate how such resources may be properly exploited within the new generation of semantically enriched content or learning management systems that allow for knowledge expansion through the use of linked medical data and numerous literature resources also described through the same vocabularies. We implemented a video portal integrating videos from 500 US Hospital channels. The portal integrated 4,307 YouTube videos regarding surgery as described by 64,367 tags. BioPortal REST services were used within our portal to match SNOMED CT terms with YouTube tags by both exact match and non-exact match. The whole architecture was complemented with a mechanism to enrich the retrieved video resources with other educational material residing in other repositories by following contemporary semantic web advances, in the form of Linked Open Data (LOD) principles. The average percentage of YouTube tags that were expressed using SNOMED CT terms was about 22.5%, while one third of YouTube tags per video contained a SNOMED CT term in a loose search; this analogy became one tenth in the case of exact match. Retrieved videos were then linked further to other resources by using LOD compliant systems. Such results were exemplified in the case of systems and technologies used in the mEducator EC funded project. YouTube Health videos can be searched for and retrieved using SNOMED CT terms with a high possibility of identifying health videos that users want based on their search criteria. Despite the fact that tagging of this information with SNOMED CT terms may vary, its availability and linked data capacity opens the door to new studies for personalized retrieval of content and linking with other knowledge through linked medical data and semantic advances in (learning) content management systems.

Teaching Creative Thinking through Architectural Design

ERIC Educational Resources Information Center

Jeon, Kijeong; Cotner, Teresa L.

2010-01-01

Art and art education are open to broader definitions in the twenty-first century. It is time that teachers seriously think about including built environment design in K-12 art education. The term "built environment" includes interior design, architecture, landscape architecture, and urban planning. Due to increased exposure to built environment…

An On-Chip Learning Neuromorphic Autoencoder With Current-Mode Transposable Memory Read and Virtual Lookup Table.

PubMed

Cho, Hwasuk; Son, Hyunwoo; Seong, Kihwan; Kim, Byungsub; Park, Hong-June; Sim, Jae-Yoon

2018-02-01

This paper presents an IC implementation of on-chip learning neuromorphic autoencoder unit in a form of rate-based spiking neural network. With a current-mode signaling scheme embedded in a 500 × 500 6b SRAM-based memory, the proposed architecture achieves simultaneous processing of multiplications and accumulations. In addition, a transposable memory read for both forward and backward propagations and a virtual lookup table are also proposed to perform an unsupervised learning of restricted Boltzmann machine. The IC is fabricated using 28-nm CMOS process and is verified in a three-layer network of encoder-decoder pair for training and recovery of images with two-dimensional pixels. With a dataset of 50 digits, the IC shows a normalized root mean square error of 0.078. Measured energy efficiencies are 4.46 pJ per synaptic operation for inference and 19.26 pJ per synaptic weight update for learning, respectively. The learning performance is also estimated by simulations if the proposed hardware architecture is extended to apply to a batch training of 60 000 MNIST datasets.

A Framework System for Intelligent Support in Open Distributed Learning Environments--A Look Back from 16 Years Later

ERIC Educational Resources Information Center

Hoppe, H. Ulrich

2016-01-01

The 1998 paper by Martin Mühlenbrock, Frank Tewissen, and myself introduced a multi-agent architecture and a component engineering approach for building open distributed learning environments to support group learning in different types of classroom settings. It took up prior work on "multiple student modeling" as a method to configure…

Machine vision systems using machine learning for industrial product inspection

NASA Astrophysics Data System (ADS)

Lu, Yi; Chen, Tie Q.; Chen, Jie; Zhang, Jian; Tisler, Anthony

2002-02-01

Machine vision inspection requires efficient processing time and accurate results. In this paper, we present a machine vision inspection architecture, SMV (Smart Machine Vision). SMV decomposes a machine vision inspection problem into two stages, Learning Inspection Features (LIF), and On-Line Inspection (OLI). The LIF is designed to learn visual inspection features from design data and/or from inspection products. During the OLI stage, the inspection system uses the knowledge learnt by the LIF component to inspect the visual features of products. In this paper we will present two machine vision inspection systems developed under the SMV architecture for two different types of products, Printed Circuit Board (PCB) and Vacuum Florescent Displaying (VFD) boards. In the VFD board inspection system, the LIF component learns inspection features from a VFD board and its displaying patterns. In the PCB board inspection system, the LIF learns the inspection features from the CAD file of a PCB board. In both systems, the LIF component also incorporates interactive learning to make the inspection system more powerful and efficient. The VFD system has been deployed successfully in three different manufacturing companies and the PCB inspection system is the process of being deployed in a manufacturing plant.

Model learning for robot control: a survey.

PubMed

Nguyen-Tuong, Duy; Peters, Jan

2011-11-01

Models are among the most essential tools in robotics, such as kinematics and dynamics models of the robot's own body and controllable external objects. It is widely believed that intelligent mammals also rely on internal models in order to generate their actions. However, while classical robotics relies on manually generated models that are based on human insights into physics, future autonomous, cognitive robots need to be able to automatically generate models that are based on information which is extracted from the data streams accessible to the robot. In this paper, we survey the progress in model learning with a strong focus on robot control on a kinematic as well as dynamical level. Here, a model describes essential information about the behavior of the environment and the influence of an agent on this environment. In the context of model-based learning control, we view the model from three different perspectives. First, we need to study the different possible model learning architectures for robotics. Second, we discuss what kind of problems these architecture and the domain of robotics imply for the applicable learning methods. From this discussion, we deduce future directions of real-time learning algorithms. Third, we show where these scenarios have been used successfully in several case studies.

On the impact of approximate computation in an analog DeSTIN architecture.

PubMed

Young, Steven; Lu, Junjie; Holleman, Jeremy; Arel, Itamar

2014-05-01

Deep machine learning (DML) holds the potential to revolutionize machine learning by automating rich feature extraction, which has become the primary bottleneck of human engineering in pattern recognition systems. However, the heavy computational burden renders DML systems implemented on conventional digital processors impractical for large-scale problems. The highly parallel computations required to implement large-scale deep learning systems are well suited to custom hardware. Analog computation has demonstrated power efficiency advantages of multiple orders of magnitude relative to digital systems while performing nonideal computations. In this paper, we investigate typical error sources introduced by analog computational elements and their impact on system-level performance in DeSTIN--a compositional deep learning architecture. These inaccuracies are evaluated on a pattern classification benchmark, clearly demonstrating the robustness of the underlying algorithm to the errors introduced by analog computational elements. A clear understanding of the impacts of nonideal computations is necessary to fully exploit the efficiency of analog circuits.

Homeostatic Agent for General Environment

NASA Astrophysics Data System (ADS)

Yoshida, Naoto

2018-03-01

One of the essential aspect in biological agents is dynamic stability. This aspect, called homeostasis, is widely discussed in ethology, neuroscience and during the early stages of artificial intelligence. Ashby's homeostats are general-purpose learning machines for stabilizing essential variables of the agent in the face of general environments. However, despite their generality, the original homeostats couldn't be scaled because they searched their parameters randomly. In this paper, first we re-define the objective of homeostats as the maximization of a multi-step survival probability from the view point of sequential decision theory and probabilistic theory. Then we show that this optimization problem can be treated by using reinforcement learning algorithms with special agent architectures and theoretically-derived intrinsic reward functions. Finally we empirically demonstrate that agents with our architecture automatically learn to survive in a given environment, including environments with visual stimuli. Our survival agents can learn to eat food, avoid poison and stabilize essential variables through theoretically-derived single intrinsic reward formulations.

Modeling and Improving Information Flows in the Development of Large Business Applications

NASA Astrophysics Data System (ADS)

Schneider, Kurt; Lübke, Daniel

Designing a good architecture for an application is a wicked problem. Therefore, experience and knowledge are considered crucial for informing work in software architecture. However, many organizations do not pay sufficient attention to experience exploitation and architectural learning. Many users of information systems are not aware of the options and the needs to report problems and requirements. They often do not have time to describe a problem encountered in sufficient detail for developers to remove it. And there may be a lengthy process for providing feedback. Hence, the knowledge about problems and potential solutions is not shared effectively. Architectural knowledge needs to include evaluative feedback as well as decisions and their reasons (rationale).

Designing the Architecture of Hierachical Neural Networks Model Attention, Learning and Goal-Oriented Behavior

DTIC Science & Technology

1993-12-31

19,23,25,26,27,28,32,33,35,41]) - A new cost function is postulated and an algorithm that employs this cost function is proposed for the learning of...updates the controller parameters from time to time [53]. The learning control algorithm consist of updating the parameter estimates as used in the...proposed cost function with the other learning type algorithms , such as based upon learning of iterative tasks [Kawamura-85], variable structure

A Conceptual Architecture for National Biosurveillance: Moving Beyond Situational Awareness to Enable Digital Detection of Emerging Threats

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

Velsko, Stephan; Bates, Thomas

Despite numerous calls for improvement, the U.S. biosurveillance enterprise remains a patchwork of uncoordinated systems that fail to take advantage of the rapid progress in information processing, communication, and analytics made in the past decade. By synthesizing components from the extensive biosurveillance literature, we propose a conceptual framework for a national biosurveillance architecture and provide suggestions for implementation. The framework differs from the current federal biosurveillance development pathway in that it is not focused on systems useful for “situational awareness,” but is instead focused on the long-term goal of having true warning capabilities. Therefore, a guiding design objective is themore » ability to digitally detect emerging threats that span jurisdictional boundaries, because attempting to solve the most challenging biosurveillance problem first provides the strongest foundation to meet simpler surveillance objectives. Core components of the vision are: (1) a whole-of-government approach to support currently disparate federal surveillance efforts that have a common data need, including those for food safety, vaccine and medical product safety, and infectious disease surveillance; (2) an information architecture that enables secure, national access to electronic health records, yet does not require that data be sent to a centralized location for surveillance analysis; (3) an inference architecture that leverages advances in ‘big data’ analytics and learning inference engines—a significant departure from the statistical process control paradigm that underpins nearly all current syndromic surveillance systems; and, (4) an organizational architecture with a governance model aimed at establishing national biosurveillance as a critical part of the U.S. national infrastructure. Although it will take many years to implement, and a national campaign of education and debate to acquire public buy-in for such a comprehensive system, the potential benefits warrant increased consideration within the U.S. government.« less

A Conceptual Architecture for National Biosurveillance: Moving Beyond Situational Awareness to Enable Digital Detection of Emerging Threats

DOE PAGES

Velsko, Stephan; Bates, Thomas

2016-06-17

Despite numerous calls for improvement, the U.S. biosurveillance enterprise remains a patchwork of uncoordinated systems that fail to take advantage of the rapid progress in information processing, communication, and analytics made in the past decade. By synthesizing components from the extensive biosurveillance literature, we propose a conceptual framework for a national biosurveillance architecture and provide suggestions for implementation. The framework differs from the current federal biosurveillance development pathway in that it is not focused on systems useful for “situational awareness,” but is instead focused on the long-term goal of having true warning capabilities. Therefore, a guiding design objective is themore » ability to digitally detect emerging threats that span jurisdictional boundaries, because attempting to solve the most challenging biosurveillance problem first provides the strongest foundation to meet simpler surveillance objectives. Core components of the vision are: (1) a whole-of-government approach to support currently disparate federal surveillance efforts that have a common data need, including those for food safety, vaccine and medical product safety, and infectious disease surveillance; (2) an information architecture that enables secure, national access to electronic health records, yet does not require that data be sent to a centralized location for surveillance analysis; (3) an inference architecture that leverages advances in ‘big data’ analytics and learning inference engines—a significant departure from the statistical process control paradigm that underpins nearly all current syndromic surveillance systems; and, (4) an organizational architecture with a governance model aimed at establishing national biosurveillance as a critical part of the U.S. national infrastructure. Although it will take many years to implement, and a national campaign of education and debate to acquire public buy-in for such a comprehensive system, the potential benefits warrant increased consideration within the U.S. government.« less

Neural networks and applications tutorial

NASA Astrophysics Data System (ADS)

Guyon, I.

1991-09-01

The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.

Joint detection and localization of multiple anatomical landmarks through learning

NASA Astrophysics Data System (ADS)

Dikmen, Mert; Zhan, Yiqiang; Zhou, Xiang Sean

2008-03-01

Reliable landmark detection in medical images provides the essential groundwork for successful automation of various open problems such as localization, segmentation, and registration of anatomical structures. In this paper, we present a learning-based system to jointly detect (is it there?) and localize (where?) multiple anatomical landmarks in medical images. The contributions of this work exist in two aspects. First, this method takes the advantage from the learning scenario that is able to automatically extract the most distinctive features for multi-landmark detection. Therefore, it is easily adaptable to detect arbitrary landmarks in various kinds of imaging modalities, e.g., CT, MRI and PET. Second, the use of multi-class/cascaded classifier architecture in different phases of the detection stage combined with robust features that are highly efficient in terms of computation time enables a seemingly real time performance, with very high localization accuracy. This method is validated on CT scans of different body sections, e.g., whole body scans, chest scans and abdominal scans. Aside from improved robustness (due to the exploitation of spatial correlations), it gains a run time efficiency in landmark detection. It also shows good scalability performance under increasing number of landmarks.

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.

I. M. Pei's East Building: Solving Problems of Form and Function. Teacher's Guide. School Arts: Looking/Learning.

ERIC Educational Resources Information Center

Hinish, Heidi

Ieoh Ming (I. M.) Pei, born in Canton, China, came to the United States in 1935 to study architecture, first at the University of Pennsylvania, then at the Massachusetts Institute of Technology, and at Harvard University's Graduate School of Design. Today, Pei's reputation and architectural contributions are renowned worldwide. He has designed…

An Organisational Architecture to Support Personalised Learning: Parents' Perspectives on the Academic Advisers

ERIC Educational Resources Information Center

Dorrington, Jamie

2018-01-01

This article reports some of the findings from research conducted by the author, who was also the principal of Saint Stephen's College, a coeducational independent school in South-east Queensland. The school was in the early stages of transitioning to a new organisational architecture (the way the physical, digital and human resources are aligned)…

An Evaluation of Applying Blended Practices to Employ Studio-Based Learning in a Large-Enrollment Design Thinking Course

ERIC Educational Resources Information Center

Brown, Sydney E.; Karle, Sarah Thomas; Kelly, Brian

2015-01-01

DSGN110 was a multidisciplinary course teaching first year students enrolled in in a variety of majors about design thinking. The course is offered for the majors of architecture, landscape architecture, interior design, community and regional planning, along with computer science and business students. By blending face-to-face and online…

«

21

22

23

24

25

»

«

21

22

23

24

25

»

Learning to Achieve Perfect Timesharing: Architectural Implications of Hazeltine, Teague, and Ivry (2002)

ERIC Educational Resources Information Center

Anderson, John R.; Taatgen, Niels A.; Byrne, Michael D.

2005-01-01

E. Hazeltine, D. Teague, and R. B. Ivry have presented data that have been interpreted as evidence against a central bottleneck. This article describes simulations of their Experiments 1 and 4 in the ACT-R cognitive architecture, which does possess a central bottleneck in production execution. The simulation model is capable of accounting for the…

Tensor Basis Neural Network v. 1.0 (beta)

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

Ling, Julia; Templeton, Jeremy

This software package can be used to build, train, and test a neural network machine learning model. The neural network architecture is specifically designed to embed tensor invariance properties by enforcing that the model predictions sit on an invariant tensor basis. This neural network architecture can be used in developing constitutive models for applications such as turbulence modeling, materials science, and electromagnetism.

Combining semi-automated image analysis techniques with machine learning algorithms to accelerate large-scale genetic studies.

PubMed

Atkinson, Jonathan A; Lobet, Guillaume; Noll, Manuel; Meyer, Patrick E; Griffiths, Marcus; Wells, Darren M

2017-10-01

Genetic analyses of plant root systems require large datasets of extracted architectural traits. To quantify such traits from images of root systems, researchers often have to choose between automated tools (that are prone to error and extract only a limited number of architectural traits) or semi-automated ones (that are highly time consuming). We trained a Random Forest algorithm to infer architectural traits from automatically extracted image descriptors. The training was performed on a subset of the dataset, then applied to its entirety. This strategy allowed us to (i) decrease the image analysis time by 73% and (ii) extract meaningful architectural traits based on image descriptors. We also show that these traits are sufficient to identify the quantitative trait loci that had previously been discovered using a semi-automated method. We have shown that combining semi-automated image analysis with machine learning algorithms has the power to increase the throughput of large-scale root studies. We expect that such an approach will enable the quantification of more complex root systems for genetic studies. We also believe that our approach could be extended to other areas of plant phenotyping. © The Authors 2017. Published by Oxford University Press.

Combining semi-automated image analysis techniques with machine learning algorithms to accelerate large-scale genetic studies

PubMed Central

Atkinson, Jonathan A.; Lobet, Guillaume; Noll, Manuel; Meyer, Patrick E.; Griffiths, Marcus

2017-01-01

Abstract Genetic analyses of plant root systems require large datasets of extracted architectural traits. To quantify such traits from images of root systems, researchers often have to choose between automated tools (that are prone to error and extract only a limited number of architectural traits) or semi-automated ones (that are highly time consuming). We trained a Random Forest algorithm to infer architectural traits from automatically extracted image descriptors. The training was performed on a subset of the dataset, then applied to its entirety. This strategy allowed us to (i) decrease the image analysis time by 73% and (ii) extract meaningful architectural traits based on image descriptors. We also show that these traits are sufficient to identify the quantitative trait loci that had previously been discovered using a semi-automated method. We have shown that combining semi-automated image analysis with machine learning algorithms has the power to increase the throughput of large-scale root studies. We expect that such an approach will enable the quantification of more complex root systems for genetic studies. We also believe that our approach could be extended to other areas of plant phenotyping. PMID:29020748

Human-level control through deep reinforcement learning.

PubMed

Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David; Rusu, Andrei A; Veness, Joel; Bellemare, Marc G; Graves, Alex; Riedmiller, Martin; Fidjeland, Andreas K; Ostrovski, Georg; Petersen, Stig; Beattie, Charles; Sadik, Amir; Antonoglou, Ioannis; King, Helen; Kumaran, Dharshan; Wierstra, Daan; Legg, Shane; Hassabis, Demis

2015-02-26

The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

Human-level control through deep reinforcement learning

NASA Astrophysics Data System (ADS)

Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David; Rusu, Andrei A.; Veness, Joel; Bellemare, Marc G.; Graves, Alex; Riedmiller, Martin; Fidjeland, Andreas K.; Ostrovski, Georg; Petersen, Stig; Beattie, Charles; Sadik, Amir; Antonoglou, Ioannis; King, Helen; Kumaran, Dharshan; Wierstra, Daan; Legg, Shane; Hassabis, Demis

2015-02-01

The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

A parameter control method in reinforcement learning to rapidly follow unexpected environmental changes.

PubMed

Murakoshi, Kazushi; Mizuno, Junya

2004-11-01

In order to rapidly follow unexpected environmental changes, we propose a parameter control method in reinforcement learning that changes each of learning parameters in appropriate directions. We determine each appropriate direction on the basis of relationships between behaviors and neuromodulators by considering an emergency as a key word. Computer experiments show that the agents using our proposed method could rapidly respond to unexpected environmental changes, not depending on either two reinforcement learning algorithms (Q-learning and actor-critic (AC) architecture) or two learning problems (discontinuous and continuous state-action problems).

PANDA: Protein function prediction using domain architecture and affinity propagation.

PubMed

Wang, Zheng; Zhao, Chenguang; Wang, Yiheng; Sun, Zheng; Wang, Nan

2018-02-22

We developed PANDA (Propagation of Affinity and Domain Architecture) to predict protein functions in the format of Gene Ontology (GO) terms. PANDA at first executes profile-profile alignment algorithm to search against PfamA, KOG, COG, and SwissProt databases, and then launches PSI-BLAST against UniProt for homologue search. PANDA integrates a domain architecture inference algorithm based on the Bayesian statistics that calculates the probability of having a GO term. All the candidate GO terms are pooled and filtered based on Z-score. After that, the remaining GO terms are clustered using an affinity propagation algorithm based on the GO directed acyclic graph, followed by a second round of filtering on the clusters of GO terms. We benchmarked the performance of all the baseline predictors PANDA integrates and also for every pooling and filtering step of PANDA. It can be found that PANDA achieves better performances in terms of area under the curve for precision and recall compared to the baseline predictors. PANDA can be accessed from http://dna.cs.miami.edu/PANDA/ .

ARCH: Adaptive recurrent-convolutional hybrid networks for long-term action recognition

PubMed Central

Xin, Miao; Zhang, Hong; Wang, Helong; Sun, Mingui; Yuan, Ding

2017-01-01

Recognition of human actions from digital video is a challenging task due to complex interfering factors in uncontrolled realistic environments. In this paper, we propose a learning framework using static, dynamic and sequential mixed features to solve three fundamental problems: spatial domain variation, temporal domain polytrope, and intra- and inter-class diversities. Utilizing a cognitive-based data reduction method and a hybrid “network upon networks” architecture, we extract human action representations which are robust against spatial and temporal interferences and adaptive to variations in both action speed and duration. We evaluated our method on the UCF101 and other three challenging datasets. Our results demonstrated a superior performance of the proposed algorithm in human action recognition. PMID:29290647

Q&A: Defining Internet Architecture for Learning.

ERIC Educational Resources Information Center

Hernandez-Ramos, Pedro

1999-01-01

Presents Pedro Hernandez-Ramos's thoughts on Educom's Instructional Management Systems (IMS), a global coalition of organizations working together to create standards for software development in distributed learning. Focuses on the organization's relevance to community colleges, the benefits of participation, why IMS is a global effort, and how…

TSI-Enhanced Pedagogical Agents to Engage Learners in Virtual Worlds

ERIC Educational Resources Information Center

Leung, Steve; Virwaney, Sandeep; Lin, Fuhua; Armstrong, AJ; Dubbelboer, Adien

2013-01-01

Building pedagogical applications in virtual worlds is a multi-disciplinary endeavor that involves learning theories, application development framework, and mediated communication theories. This paper presents a project that integrates game-based learning, multi-agent system architecture (MAS), and the theory of Transformed Social Interaction…

Semantic Services in e-Learning: An Argumentation Case Study

ERIC Educational Resources Information Center

Moreale, Emanuela; Vargas-Vera, Maria

2004-01-01

This paper outlines an e-Learning services architecture offering semantic-based services to students and tutors, in particular ways to browse and obtain information through web services. Services could include registration, authentication, tutoring systems, smart question answering for students' queries, automated marking systems and a student…

HELPR: Hybrid Evolutionary Learning for Pattern Recognition

DTIC Science & Technology

2005-12-01

to a new approach called memetic algorithms that combines machine learning systems with human expertise to create new tools that have the advantage...architecture could form the foundation for a memetic system capable of solving ATR problems faster and more accurately than possible using pure human expertise

Practice Architectures and Sustainable Curriculum Renewal

ERIC Educational Resources Information Center

Goodyear, Victoria A.; Casey, Ashley; Kirk, David

2017-01-01

While there are numerous pedagogical innovations and varying forms of professional learning to support change, teachers rarely move beyond the initial implementation of new ideas and policies and few innovations reach the institutionalized stage. Building on both site ontologies and situated learning in communities of practice perspectives, this…

An Architecture for Learning in Projects?

ERIC Educational Resources Information Center

Sense, Andrew J.

2004-01-01

This paper reports upon a two-year, qualitative, case study action research investigation into "learning within a project team". This project team undertook a significant socio-technical redesign project within a major Australian heavy engineering/manufacturing operation. The paper identifies and elaborates upon a number of elements that…

The Design of Learning Environments.

ERIC Educational Resources Information Center

Stueck, Lawrence E.

This study, using the Eisner's Educational Criticism Model, examines the role school architecture plays in eliciting creative, self-directed, child-centered responses in elementary school students. An evaluation of 11 play environments; 7 learning environments; an integrated third grade curriculum known as the City Classroom is presented; and the…

(Re)Designing Learning Environments.

ERIC Educational Resources Information Center

Edutopia, 2002

2002-01-01

This 20-page issue explores the opportunity for creating 21st century learning environments that not only focus on different kinds of educational architecture but also emphasize how time is used, teacher-student relationships, collaboration, the benefits of real-world projects, and community involvement. In Minnesota, high school juniors and…

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.

7 CFR 1724.21 - Architectural services contracts.

Code of Federal Regulations, 2013 CFR

2013-01-01

... the architect furnishes or obtains all architectural services related to the design and construction management of the facilities. (c) Reasonable modifications or additions to the terms and conditions in the...

7 CFR 1724.21 - Architectural services contracts.

Code of Federal Regulations, 2012 CFR

2012-01-01

... the architect furnishes or obtains all architectural services related to the design and construction management of the facilities. (c) Reasonable modifications or additions to the terms and conditions in the...

«

21

22

23

24

25

»

Some links on this page may take you to non-federal websites. Their policies may differ from this site.