A mathematical analysis of the effects of Hebbian learning rules on the dynamics and structure of discrete-time random recurrent neural networks.

PubMed

Siri, Benoît; Berry, Hugues; Cessac, Bruno; Delord, Bruno; Quoy, Mathias

2008-12-01

We present a mathematical analysis of the effects of Hebbian learning in random recurrent neural networks, with a generic Hebbian learning rule, including passive forgetting and different timescales, for neuronal activity and learning dynamics. Previous numerical work has reported that Hebbian learning drives the system from chaos to a steady state through a sequence of bifurcations. Here, we interpret these results mathematically and show that these effects, involving a complex coupling between neuronal dynamics and synaptic graph structure, can be analyzed using Jacobian matrices, which introduce both a structural and a dynamical point of view on neural network evolution. Furthermore, we show that sensitivity to a learned pattern is maximal when the largest Lyapunov exponent is close to 0. We discuss how neural networks may take advantage of this regime of high functional interest.

Resolution of Singularities Introduced by Hierarchical Structure in Deep Neural Networks.

PubMed

Nitta, Tohru

2017-10-01

We present a theoretical analysis of singular points of artificial deep neural networks, resulting in providing deep neural network models having no critical points introduced by a hierarchical structure. It is considered that such deep neural network models have good nature for gradient-based optimization. First, we show that there exist a large number of critical points introduced by a hierarchical structure in deep neural networks as straight lines, depending on the number of hidden layers and the number of hidden neurons. Second, we derive a sufficient condition for deep neural networks having no critical points introduced by a hierarchical structure, which can be applied to general deep neural networks. It is also shown that the existence of critical points introduced by a hierarchical structure is determined by the rank and the regularity of weight matrices for a specific class of deep neural networks. Finally, two kinds of implementation methods of the sufficient conditions to have no critical points are provided. One is a learning algorithm that can avoid critical points introduced by the hierarchical structure during learning (called avoidant learning algorithm). The other is a neural network that does not have some critical points introduced by the hierarchical structure as an inherent property (called avoidant neural network).

Learning Orthographic Structure With Sequential Generative Neural Networks.

PubMed

Testolin, Alberto; Stoianov, Ivilin; Sperduti, Alessandro; Zorzi, Marco

2016-04-01

Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in connectionist modeling. Here, we investigated a sequential version of the restricted Boltzmann machine (RBM), a stochastic recurrent neural network that extracts high-order structure from sensory data through unsupervised generative learning and can encode contextual information in the form of internal, distributed representations. We assessed whether this type of network can extract the orthographic structure of English monosyllables by learning a generative model of the letter sequences forming a word training corpus. We show that the network learned an accurate probabilistic model of English graphotactics, which can be used to make predictions about the letter following a given context as well as to autonomously generate high-quality pseudowords. The model was compared to an extended version of simple recurrent networks, augmented with a stochastic process that allows autonomous generation of sequences, and to non-connectionist probabilistic models (n-grams and hidden Markov models). We conclude that sequential RBMs and stochastic simple recurrent networks are promising candidates for modeling cognition in the temporal domain. Copyright © 2015 Cognitive Science Society, Inc.

Social learning strategies modify the effect of network structure on group performance.

PubMed

Barkoczi, Daniel; Galesic, Mirta

2016-10-07

The structure of communication networks is an important determinant of the capacity of teams, organizations and societies to solve policy, business and science problems. Yet, previous studies reached contradictory results about the relationship between network structure and performance, finding support for the superiority of both well-connected efficient and poorly connected inefficient network structures. Here we argue that understanding how communication networks affect group performance requires taking into consideration the social learning strategies of individual team members. We show that efficient networks outperform inefficient networks when individuals rely on conformity by copying the most frequent solution among their contacts. However, inefficient networks are superior when individuals follow the best member by copying the group member with the highest payoff. In addition, groups relying on conformity based on a small sample of others excel at complex tasks, while groups following the best member achieve greatest performance for simple tasks. Our findings reconcile contradictory results in the literature and have broad implications for the study of social learning across disciplines.

Social learning strategies modify the effect of network structure on group performance

NASA Astrophysics Data System (ADS)

Barkoczi, Daniel; Galesic, Mirta

2016-10-01

The structure of communication networks is an important determinant of the capacity of teams, organizations and societies to solve policy, business and science problems. Yet, previous studies reached contradictory results about the relationship between network structure and performance, finding support for the superiority of both well-connected efficient and poorly connected inefficient network structures. Here we argue that understanding how communication networks affect group performance requires taking into consideration the social learning strategies of individual team members. We show that efficient networks outperform inefficient networks when individuals rely on conformity by copying the most frequent solution among their contacts. However, inefficient networks are superior when individuals follow the best member by copying the group member with the highest payoff. In addition, groups relying on conformity based on a small sample of others excel at complex tasks, while groups following the best member achieve greatest performance for simple tasks. Our findings reconcile contradictory results in the literature and have broad implications for the study of social learning across disciplines.

A Social Network Analysis of Teaching and Research Collaboration in a Teachers' Virtual Learning Community

ERIC Educational Resources Information Center

Lin, Xiaofan; Hu, Xiaoyong; Hu, Qintai; Liu, Zhichun

2016-01-01

Analysing the structure of a social network can help us understand the key factors influencing interaction and collaboration in a virtual learning community (VLC). Here, we describe the mechanisms used in social network analysis (SNA) to analyse the social network structure of a VLC for teachers and discuss the relationship between face-to-face…

System level mechanisms of adaptation, learning, memory formation and evolvability: the role of chaperone and other networks.

PubMed

Gyurko, David M; Soti, Csaba; Stetak, Attila; Csermely, Peter

2014-05-01

During the last decade, network approaches became a powerful tool to describe protein structure and dynamics. Here, we describe first the protein structure networks of molecular chaperones, then characterize chaperone containing sub-networks of interactomes called as chaperone-networks or chaperomes. We review the role of molecular chaperones in short-term adaptation of cellular networks in response to stress, and in long-term adaptation discussing their putative functions in the regulation of evolvability. We provide a general overview of possible network mechanisms of adaptation, learning and memory formation. We propose that changes of network rigidity play a key role in learning and memory formation processes. Flexible network topology provides ' learning-competent' state. Here, networks may have much less modular boundaries than locally rigid, highly modular networks, where the learnt information has already been consolidated in a memory formation process. Since modular boundaries are efficient filters of information, in the 'learning-competent' state information filtering may be much smaller, than after memory formation. This mechanism restricts high information transfer to the 'learning competent' state. After memory formation, modular boundary-induced segregation and information filtering protect the stored information. The flexible networks of young organisms are generally in a 'learning competent' state. On the contrary, locally rigid networks of old organisms have lost their 'learning competent' state, but store and protect their learnt information efficiently. We anticipate that the above mechanism may operate at the level of both protein-protein interaction and neuronal networks.

Geometrical structure of Neural Networks: Geodesics, Jeffrey's Prior and Hyper-ribbons

NASA Astrophysics Data System (ADS)

Hayden, Lorien; Alemi, Alex; Sethna, James

2014-03-01

Neural networks are learning algorithms which are employed in a host of Machine Learning problems including speech recognition, object classification and data mining. In practice, neural networks learn a low dimensional representation of high dimensional data and define a model manifold which is an embedding of this low dimensional structure in the higher dimensional space. In this work, we explore the geometrical structure of a neural network model manifold. A Stacked Denoising Autoencoder and a Deep Belief Network are trained on handwritten digits from the MNIST database. Construction of geodesics along the surface and of slices taken from the high dimensional manifolds reveal a hierarchy of widths corresponding to a hyper-ribbon structure. This property indicates that neural networks fall into the class of sloppy models, in which certain parameter combinations dominate the behavior. Employing this information could prove valuable in designing both neural network architectures and training algorithms. This material is based upon work supported by the National Science Foundation Graduate Research Fellowship under Grant No . DGE-1144153.

Application of structured support vector machine backpropagation to a convolutional neural network for human pose estimation.

PubMed

Witoonchart, Peerajak; Chongstitvatana, Prabhas

2017-08-01

In this study, for the first time, we show how to formulate a structured support vector machine (SSVM) as two layers in a convolutional neural network, where the top layer is a loss augmented inference layer and the bottom layer is the normal convolutional layer. We show that a deformable part model can be learned with the proposed structured SVM neural network by backpropagating the error of the deformable part model to the convolutional neural network. The forward propagation calculates the loss augmented inference and the backpropagation calculates the gradient from the loss augmented inference layer to the convolutional layer. Thus, we obtain a new type of convolutional neural network called an Structured SVM convolutional neural network, which we applied to the human pose estimation problem. This new neural network can be used as the final layers in deep learning. Our method jointly learns the structural model parameters and the appearance model parameters. We implemented our method as a new layer in the existing Caffe library. Copyright © 2017 Elsevier Ltd. All rights reserved.

Establishing a Dynamic Self-Adaptation Learning Algorithm of the BP Neural Network and Its Applications

NASA Astrophysics Data System (ADS)

Li, Xiaofeng; Xiang, Suying; Zhu, Pengfei; Wu, Min

2015-12-01

In order to avoid the inherent deficiencies of the traditional BP neural network, such as slow convergence speed, that easily leading to local minima, poor generalization ability and difficulty in determining the network structure, the dynamic self-adaptive learning algorithm of the BP neural network is put forward to improve the function of the BP neural network. The new algorithm combines the merit of principal component analysis, particle swarm optimization, correlation analysis and self-adaptive model, hence can effectively solve the problems of selecting structural parameters, initial connection weights and thresholds and learning rates of the BP neural network. This new algorithm not only reduces the human intervention, optimizes the topological structures of BP neural networks and improves the network generalization ability, but also accelerates the convergence speed of a network, avoids trapping into local minima, and enhances network adaptation ability and prediction ability. The dynamic self-adaptive learning algorithm of the BP neural network is used to forecast the total retail sale of consumer goods of Sichuan Province, China. Empirical results indicate that the new algorithm is superior to the traditional BP network algorithm in predicting accuracy and time consumption, which shows the feasibility and effectiveness of the new algorithm.

Sparse Regression Based Structure Learning of Stochastic Reaction Networks from Single Cell Snapshot Time Series.

PubMed

Klimovskaia, Anna; Ganscha, Stefan; Claassen, Manfred

2016-12-01

Stochastic chemical reaction networks constitute a model class to quantitatively describe dynamics and cell-to-cell variability in biological systems. The topology of these networks typically is only partially characterized due to experimental limitations. Current approaches for refining network topology are based on the explicit enumeration of alternative topologies and are therefore restricted to small problem instances with almost complete knowledge. We propose the reactionet lasso, a computational procedure that derives a stepwise sparse regression approach on the basis of the Chemical Master Equation, enabling large-scale structure learning for reaction networks by implicitly accounting for billions of topology variants. We have assessed the structure learning capabilities of the reactionet lasso on synthetic data for the complete TRAIL induced apoptosis signaling cascade comprising 70 reactions. We find that the reactionet lasso is able to efficiently recover the structure of these reaction systems, ab initio, with high sensitivity and specificity. With only < 1% false discoveries, the reactionet lasso is able to recover 45% of all true reactions ab initio among > 6000 possible reactions and over 102000 network topologies. In conjunction with information rich single cell technologies such as single cell RNA sequencing or mass cytometry, the reactionet lasso will enable large-scale structure learning, particularly in areas with partial network structure knowledge, such as cancer biology, and thereby enable the detection of pathological alterations of reaction networks. We provide software to allow for wide applicability of the reactionet lasso.

Benefits of Cooperative Learning in Weblog Networks

ERIC Educational Resources Information Center

Wang, Jenny; Fang, Yuehchiu

2005-01-01

The purpose of this study was to explore the benefits of cooperative learning in weblog networks, focusing particularly on learning outcomes in college writing curriculum integrated with computer-mediated learning tool-weblog. The first section addressed the advantages of using weblogs in cooperative learning structure on teaching and learning.…

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

PubMed Central

Spencer, Matt; Eickholt, Jesse; Cheng, Jianlin

2014-01-01

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

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

PubMed

Spencer, Matt; Eickholt, Jesse; Jianlin Cheng

2015-01-01

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

Fast detection of the fuzzy communities based on leader-driven algorithm

NASA Astrophysics Data System (ADS)

Fang, Changjian; Mu, Dejun; Deng, Zhenghong; Hu, Jun; Yi, Chen-He

2018-03-01

In this paper, we present the leader-driven algorithm (LDA) for learning community structure in networks. The algorithm allows one to find overlapping clusters in a network, an important aspect of real networks, especially social networks. The algorithm requires no input parameters and learns the number of clusters naturally from the network. It accomplishes this using leadership centrality in a clever manner. It identifies local minima of leadership centrality as followers which belong only to one cluster, and the remaining nodes are leaders which connect clusters. In this way, the number of clusters can be learned using only the network structure. The LDA is also an extremely fast algorithm, having runtime linear in the network size. Thus, this algorithm can be used to efficiently cluster extremely large networks.

Attentional Bias in Human Category Learning: The Case of Deep Learning.

PubMed

Hanson, Catherine; Caglar, Leyla Roskan; Hanson, Stephen José

2018-01-01

Category learning performance is influenced by both the nature of the category's structure and the way category features are processed during learning. Shepard (1964, 1987) showed that stimuli can have structures with features that are statistically uncorrelated (separable) or statistically correlated (integral) within categories. Humans find it much easier to learn categories having separable features, especially when attention to only a subset of relevant features is required, and harder to learn categories having integral features, which require consideration of all of the available features and integration of all the relevant category features satisfying the category rule (Garner, 1974). In contrast to humans, a single hidden layer backpropagation (BP) neural network has been shown to learn both separable and integral categories equally easily, independent of the category rule (Kruschke, 1993). This "failure" to replicate human category performance appeared to be strong evidence that connectionist networks were incapable of modeling human attentional bias. We tested the presumed limitations of attentional bias in networks in two ways: (1) by having networks learn categories with exemplars that have high feature complexity in contrast to the low dimensional stimuli previously used, and (2) by investigating whether a Deep Learning (DL) network, which has demonstrated humanlike performance in many different kinds of tasks (language translation, autonomous driving, etc.), would display human-like attentional bias during category learning. We were able to show a number of interesting results. First, we replicated the failure of BP to differentially process integral and separable category structures when low dimensional stimuli are used (Garner, 1974; Kruschke, 1993). Second, we show that using the same low dimensional stimuli, Deep Learning (DL), unlike BP but similar to humans, learns separable category structures more quickly than integral category structures. Third, we show that even BP can exhibit human like learning differences between integral and separable category structures when high dimensional stimuli (face exemplars) are used. We conclude, after visualizing the hidden unit representations, that DL appears to extend initial learning due to feature development thereby reducing destructive feature competition by incrementally refining feature detectors throughout later layers until a tipping point (in terms of error) is reached resulting in rapid asymptotic learning.

Distributed learning automata-based algorithm for community detection in complex networks

NASA Astrophysics Data System (ADS)

Khomami, Mohammad Mehdi Daliri; Rezvanian, Alireza; Meybodi, Mohammad Reza

2016-03-01

Community structure is an important and universal topological property of many complex networks such as social and information networks. The detection of communities of a network is a significant technique for understanding the structure and function of networks. In this paper, we propose an algorithm based on distributed learning automata for community detection (DLACD) in complex networks. In the proposed algorithm, each vertex of network is equipped with a learning automation. According to the cooperation among network of learning automata and updating action probabilities of each automaton, the algorithm interactively tries to identify high-density local communities. The performance of the proposed algorithm is investigated through a number of simulations on popular synthetic and real networks. Experimental results in comparison with popular community detection algorithms such as walk trap, Danon greedy optimization, Fuzzy community detection, Multi-resolution community detection and label propagation demonstrated the superiority of DLACD in terms of modularity, NMI, performance, min-max-cut and coverage.

Network reciprocity by coexisting learning and teaching strategies

NASA Astrophysics Data System (ADS)

Tanimoto, Jun; Brede, Markus; Yamauchi, Atsuo

2012-03-01

We propose a network reciprocity model in which an agent probabilistically adopts learning or teaching strategies. In the learning adaptation mechanism, an agent may copy a neighbor's strategy through Fermi pairwise comparison. The teaching adaptation mechanism involves an agent imposing its strategy on a neighbor. Our simulations reveal that the reciprocity is significantly affected by the frequency with which learning and teaching agents coexist in a network and by the structure of the network itself.

Learning in networks: individual teacher learning versus organizational learning in a regional health-promoting schools network.

PubMed

Flaschberger, Edith; Gugglberger, Lisa; Dietscher, Christina

2013-12-01

To change a school into a health-promoting organization, organizational learning is required. The evaluation of an Austrian regional health-promoting schools network provides qualitative data on the views of the different stakeholders on learning in this network (steering group, network coordinator and representatives of the network schools; n = 26). Through thematic analysis and deep-structure analyses, the following three forms of learning in the network were identified: (A) individual learning through input offered by the network coordination, (B) individual learning between the network schools, i.e. through exchange between the representatives of different schools and (C) learning within the participating schools, i.e. organizational learning. Learning between (B) or within the participating schools (C) seems to be rare in the network; concepts of individual teacher learning are prevalent. Difficulties detected relating to the transfer of information from the network to the member schools included barriers to organizational learning such as the lack of collaboration, coordination and communication in the network schools, which might be effects of the school system in which the observed network is located. To ensure connectivity of the information offered by the network, more emphasis should be put on linking health promotion to school development and the core processes of schools.

Online Learning of Genetic Network Programming and its Application to Prisoner’s Dilemma Game

NASA Astrophysics Data System (ADS)

Mabu, Shingo; Hirasawa, Kotaro; Hu, Jinglu; Murata, Junichi

A new evolutionary model with the network structure named Genetic Network Programming (GNP) has been proposed recently. GNP, that is, an expansion of GA and GP, represents solutions as a network structure and evolves it by using “offline learning (selection, mutation, crossover)”. GNP can memorize the past action sequences in the network flow, so it can deal with Partially Observable Markov Decision Process (POMDP) well. In this paper, in order to improve the ability of GNP, Q learning (an off-policy TD control algorithm) that is one of the famous online methods is introduced for online learning of GNP. Q learning is suitable for GNP because (1) in reinforcement learning, the rewards an agent will get in the future can be estimated, (2) TD control doesn’t need much memory and can learn quickly, and (3) off-policy is suitable in order to search for an optimal solution independently of the policy. Finally, in the simulations, online learning of GNP is applied to a player for “Prisoner’s dilemma game” and its ability for online adaptation is confirmed.

Frame prediction using recurrent convolutional encoder with residual learning

NASA Astrophysics Data System (ADS)

Yue, Boxuan; Liang, Jun

2018-05-01

The prediction for the frame of a video is difficult but in urgent need in auto-driving. Conventional methods can only predict some abstract trends of the region of interest. The boom of deep learning makes the prediction for frames possible. In this paper, we propose a novel recurrent convolutional encoder and DE convolutional decoder structure to predict frames. We introduce the residual learning in the convolution encoder structure to solve the gradient issues. The residual learning can transform the gradient back propagation to an identity mapping. It can reserve the whole gradient information and overcome the gradient issues in Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN). Besides, compared with the branches in CNNs and the gated structures in RNNs, the residual learning can save the training time significantly. In the experiments, we use UCF101 dataset to train our networks, the predictions are compared with some state-of-the-art methods. The results show that our networks can predict frames fast and efficiently. Furthermore, our networks are used for the driving video to verify the practicability.

Hybrid computing using a neural network with dynamic external memory.

PubMed

Graves, Alex; Wayne, Greg; Reynolds, Malcolm; Harley, Tim; Danihelka, Ivo; Grabska-Barwińska, Agnieszka; Colmenarejo, Sergio Gómez; Grefenstette, Edward; Ramalho, Tiago; Agapiou, John; Badia, Adrià Puigdomènech; Hermann, Karl Moritz; Zwols, Yori; Ostrovski, Georg; Cain, Adam; King, Helen; Summerfield, Christopher; Blunsom, Phil; Kavukcuoglu, Koray; Hassabis, Demis

2016-10-27

Artificial neural networks are remarkably adept at sensory processing, sequence learning and reinforcement learning, but are limited in their ability to represent variables and data structures and to store data over long timescales, owing to the lack of an external memory. Here we introduce a machine learning model called a differentiable neural computer (DNC), which consists of a neural network that can read from and write to an external memory matrix, analogous to the random-access memory in a conventional computer. Like a conventional computer, it can use its memory to represent and manipulate complex data structures, but, like a neural network, it can learn to do so from data. When trained with supervised learning, we demonstrate that a DNC can successfully answer synthetic questions designed to emulate reasoning and inference problems in natural language. We show that it can learn tasks such as finding the shortest path between specified points and inferring the missing links in randomly generated graphs, and then generalize these tasks to specific graphs such as transport networks and family trees. When trained with reinforcement learning, a DNC can complete a moving blocks puzzle in which changing goals are specified by sequences of symbols. Taken together, our results demonstrate that DNCs have the capacity to solve complex, structured tasks that are inaccessible to neural networks without external read-write memory.

Functional brain networks reconstruction using group sparsity-regularized learning.

PubMed

Zhao, Qinghua; Li, Will X Y; Jiang, Xi; Lv, Jinglei; Lu, Jianfeng; Liu, Tianming

2018-06-01

Investigating functional brain networks and patterns using sparse representation of fMRI data has received significant interests in the neuroimaging community. It has been reported that sparse representation is effective in reconstructing concurrent and interactive functional brain networks. To date, most of data-driven network reconstruction approaches rarely take consideration of anatomical structures, which are the substrate of brain function. Furthermore, it has been rarely explored whether structured sparse representation with anatomical guidance could facilitate functional networks reconstruction. To address this problem, in this paper, we propose to reconstruct brain networks utilizing the structure guided group sparse regression (S2GSR) in which 116 anatomical regions from the AAL template, as prior knowledge, are employed to guide the network reconstruction when performing sparse representation of whole-brain fMRI data. Specifically, we extract fMRI signals from standard space aligned with the AAL template. Then by learning a global over-complete dictionary, with the learned dictionary as a set of features (regressors), the group structured regression employs anatomical structures as group information to regress whole brain signals. Finally, the decomposition coefficients matrix is mapped back to the brain volume to represent functional brain networks and patterns. We use the publicly available Human Connectome Project (HCP) Q1 dataset as the test bed, and the experimental results indicate that the proposed anatomically guided structure sparse representation is effective in reconstructing concurrent functional brain networks.

Categorical Structure among Shared Features in Networks of Early-Learned Nouns

ERIC Educational Resources Information Center

Hills, Thomas T.; Maouene, Mounir; Maouene, Josita; Sheya, Adam; Smith, Linda

2009-01-01

The shared features that characterize the noun categories that young children learn first are a formative basis of the human category system. To investigate the potential categorical information contained in the features of early-learned nouns, we examine the graph-theoretic properties of noun-feature networks. The networks are built from the…

Python Environment for Bayesian Learning: Inferring the Structure of Bayesian Networks from Knowledge and Data

PubMed Central

Shah, Abhik; Woolf, Peter

2009-01-01

Summary In this paper, we introduce pebl, a Python library and application for learning Bayesian network structure from data and prior knowledge that provides features unmatched by alternative software packages: the ability to use interventional data, flexible specification of structural priors, modeling with hidden variables and exploitation of parallel processing. PMID:20161541

Evolutionary neural networks for anomaly detection based on the behavior of a program.

PubMed

Han, Sang-Jun; Cho, Sung-Bae

2006-06-01

The process of learning the behavior of a given program by using machine-learning techniques (based on system-call audit data) is effective to detect intrusions. Rule learning, neural networks, statistics, and hidden Markov models (HMMs) are some of the kinds of representative methods for intrusion detection. Among them, neural networks are known for good performance in learning system-call sequences. In order to apply this knowledge to real-world problems successfully, it is important to determine the structures and weights of these call sequences. However, finding the appropriate structures requires very long time periods because there are no suitable analytical solutions. In this paper, a novel intrusion-detection technique based on evolutionary neural networks (ENNs) is proposed. One advantage of using ENNs is that it takes less time to obtain superior neural networks than when using conventional approaches. This is because they discover the structures and weights of the neural networks simultaneously. Experimental results with the 1999 Defense Advanced Research Projects Agency (DARPA) Intrusion Detection Evaluation (IDEVAL) data confirm that ENNs are promising tools for intrusion detection.

Facilitative Components of Collaborative Learning: A Review of Nine Health Research Networks.

PubMed

Leroy, Lisa; Rittner, Jessica Levin; Johnson, Karin E; Gerteis, Jessie; Miller, Therese

2017-02-01

Collaborative research networks are increasingly used as an effective mechanism for accelerating knowledge transfer into policy and practice. This paper explored the characteristics and collaborative learning approaches of nine health research networks. Semi-structured interviews with representatives from eight diverse US health services research networks conducted between November 2012 and January 2013 and program evaluation data from a ninth. The qualitative analysis assessed each network's purpose, duration, funding sources, governance structure, methods used to foster collaboration, and barriers and facilitators to collaborative learning. The authors reviewed detailed notes from the interviews to distill salient themes. Face-to-face meetings, intentional facilitation and communication, shared vision, trust among members and willingness to work together were key facilitators of collaborative learning. Competing priorities for members, limited funding and lack of long-term support and geographic dispersion were the main barriers to coordination and collaboration across research network members. The findings illustrate the importance of collaborative learning in research networks and the challenges to evaluating the success of research network functionality. Conducting readiness assessments and developing process and outcome evaluation metrics will advance the design and show the impact of collaborative research networks. Copyright © 2017 Longwoods Publishing.

Bayesian networks in neuroscience: a survey.

PubMed

Bielza, Concha; Larrañaga, Pedro

2014-01-01

Bayesian networks are a type of probabilistic graphical models lie at the intersection between statistics and machine learning. They have been shown to be powerful tools to encode dependence relationships among the variables of a domain under uncertainty. Thanks to their generality, Bayesian networks can accommodate continuous and discrete variables, as well as temporal processes. In this paper we review Bayesian networks and how they can be learned automatically from data by means of structure learning algorithms. Also, we examine how a user can take advantage of these networks for reasoning by exact or approximate inference algorithms that propagate the given evidence through the graphical structure. Despite their applicability in many fields, they have been little used in neuroscience, where they have focused on specific problems, like functional connectivity analysis from neuroimaging data. Here we survey key research in neuroscience where Bayesian networks have been used with different aims: discover associations between variables, perform probabilistic reasoning over the model, and classify new observations with and without supervision. The networks are learned from data of any kind-morphological, electrophysiological, -omics and neuroimaging-, thereby broadening the scope-molecular, cellular, structural, functional, cognitive and medical- of the brain aspects to be studied.

Bayesian networks in neuroscience: a survey

PubMed Central

Bielza, Concha; Larrañaga, Pedro

2014-01-01

Bayesian networks are a type of probabilistic graphical models lie at the intersection between statistics and machine learning. They have been shown to be powerful tools to encode dependence relationships among the variables of a domain under uncertainty. Thanks to their generality, Bayesian networks can accommodate continuous and discrete variables, as well as temporal processes. In this paper we review Bayesian networks and how they can be learned automatically from data by means of structure learning algorithms. Also, we examine how a user can take advantage of these networks for reasoning by exact or approximate inference algorithms that propagate the given evidence through the graphical structure. Despite their applicability in many fields, they have been little used in neuroscience, where they have focused on specific problems, like functional connectivity analysis from neuroimaging data. Here we survey key research in neuroscience where Bayesian networks have been used with different aims: discover associations between variables, perform probabilistic reasoning over the model, and classify new observations with and without supervision. The networks are learned from data of any kind–morphological, electrophysiological, -omics and neuroimaging–, thereby broadening the scope–molecular, cellular, structural, functional, cognitive and medical– of the brain aspects to be studied. PMID:25360109

Environmental Design for a Structured Network Learning Society

ERIC Educational Resources Information Center

Chang, Ben; Cheng, Nien-Heng; Deng, Yi-Chan; Chan, Tak-Wai

2007-01-01

Social interactions profoundly impact the learning processes of learners in traditional societies. The rapid rise of the Internet using population has been the establishment of numerous different styles of network communities. Network societies form when more Internet communities are established, but the basic form of a network society, especially…

Physics textbooks from the viewpoint of network structures

NASA Astrophysics Data System (ADS)

Králiková, Petra; Teleki, Aba

2017-01-01

We can observe self-organized networks all around us. These networks are, in general, scale invariant networks described by the Bianconi-Barabasi model. The self-organized networks (networks formed naturally when feedback acts on the system) show certain universality. These networks, in simplified models, have scale invariant distribution (Pareto distribution type I) and parameter α has value between 2 and 5. The textbooks are extremely important in the learning process and from this reason we studied physics textbook at the level of sentences and physics terms (bipartite network). The nodes represent physics terms, sentences, and pictures, tables, connected by links (by physics terms and transitional words and transitional phrases). We suppose that learning process are more robust and goes faster and easier if the physics textbook has a structure similar to structures of self-organized networks.

Immune allied genetic algorithm for Bayesian network structure learning

NASA Astrophysics Data System (ADS)

Song, Qin; Lin, Feng; Sun, Wei; Chang, KC

2012-06-01

Bayesian network (BN) structure learning is a NP-hard problem. In this paper, we present an improved approach to enhance efficiency of BN structure learning. To avoid premature convergence in traditional single-group genetic algorithm (GA), we propose an immune allied genetic algorithm (IAGA) in which the multiple-population and allied strategy are introduced. Moreover, in the algorithm, we apply prior knowledge by injecting immune operator to individuals which can effectively prevent degeneration. To illustrate the effectiveness of the proposed technique, we present some experimental results.

Knowledge sharing and organizational learning in the context of hospital infection prevention.

PubMed

Rangachari, Pavani

2010-01-01

Recently, hospitals that have been successful in preventing infections have labeled their improvement approaches as either the Toyota Production System (TPS) approach or the Positive Deviance (PD) approach. PD has been distinguished from TPS as being a bottom-up approach to improvement, as against top-down. Facilities that have employed both approaches have suggested that PD may be more effective than TPS for infection prevention. This article integrates organizational learning, institutional, and knowledge network theories to develop a theoretical framework for understanding the structure and evolution of effective knowledge-sharing networks in health care organizations, that is, networks most conducive to learning and improvement. Contrary to arguments put forth by hospital success stories, the framework suggests that networks rich in brokerage and hierarchy (ie, top-down, "TPS-like" structures) may be more effective for learning and improvement in health care organizations, compared with a networks rich in density (ie, bottom-up, "PD-like" structures). The theoretical framework and ensuing analysis help identify several gaps in the literature related to organization learning and improvement in the infection prevention context. This, in turn, helps put forth recommendations for health management research and practice.

What Online Networks Offer: "Online Network Compositions and Online Learning Experiences of Three Ethnic Groups"

ERIC Educational Resources Information Center

Lecluijze, Suzanne Elisabeth; de Haan, Mariëtte; Ünlüsoy, Asli

2015-01-01

This exploratory study examines ethno-cultural diversity in youth's narratives regarding their "online" learning experiences while also investigating how these narratives can be understood from the analysis of their online network structure and composition. Based on ego-network data of 79 respondents this study compared the…

Facilitative Components of Collaborative Learning: A Review of Nine Health Research Networks

PubMed Central

Rittner, Jessica Levin; Johnson, Karin E.; Gerteis, Jessie; Miller, Therese

2017-01-01

Objective: Collaborative research networks are increasingly used as an effective mechanism for accelerating knowledge transfer into policy and practice. This paper explored the characteristics and collaborative learning approaches of nine health research networks. Data sources/study setting: Semi-structured interviews with representatives from eight diverse US health services research networks conducted between November 2012 and January 2013 and program evaluation data from a ninth. Study design: The qualitative analysis assessed each network's purpose, duration, funding sources, governance structure, methods used to foster collaboration, and barriers and facilitators to collaborative learning. Data collection: The authors reviewed detailed notes from the interviews to distill salient themes. Principal findings: Face-to-face meetings, intentional facilitation and communication, shared vision, trust among members and willingness to work together were key facilitators of collaborative learning. Competing priorities for members, limited funding and lack of long-term support and geographic dispersion were the main barriers to coordination and collaboration across research network members. Conclusion: The findings illustrate the importance of collaborative learning in research networks and the challenges to evaluating the success of research network functionality. Conducting readiness assessments and developing process and outcome evaluation metrics will advance the design and show the impact of collaborative research networks. PMID:28277202

Information Resources Usage in Project Management Digital Learning System

ERIC Educational Resources Information Center

Davidovitch, Nitza; Belichenko, Margarita; Kravchenko, Yurii

2017-01-01

The article combines a theoretical approach to structuring knowledge that is based on the integrated use of fuzzy semantic network theory predicates, Boolean functions, theory of complexity of network structures and some practical aspects to be considered in the distance learning at the university. The paper proposes a methodological approach that…

Experimental Verification of Electric Drive Technologies Based on Artificial Intelligence Tools

NASA Technical Reports Server (NTRS)

Rubaai, Ahmed; Ricketts, Daniel; Kotaru, Raj; Thomas, Robert; Noga, Donald F. (Technical Monitor); Kankam, Mark D. (Technical Monitor)

2000-01-01

In this report, a fully integrated prototype of a flight servo control system is successfully developed and implemented using brushless dc motors. The control system is developed by the fuzzy logic theory, and implemented with a multilayer neural network. First, a neural network-based architecture is introduced for fuzzy logic control. The characteristic rules and their membership functions of fuzzy systems are represented as the processing nodes in the neural network structure. The network structure and the parameter learning are performed simultaneously and online in the fuzzy-neural network system. The structure learning is based on the partition of input space. The parameter learning is based on the supervised gradient decent method, using a delta adaptation law. Using experimental setup, the performance of the proposed control system is evaluated under various operating conditions. Test results are presented and discussed in the report. The proposed learning control system has several advantages, namely, simple structure and learning capability, robustness and high tracking performance and few nodes at hidden layers. In comparison with the PI controller, the proposed fuzzy-neural network system can yield a better dynamic performance with shorter settling time, and without overshoot. Experimental results have shown that the proposed control system is adaptive and robust in responding to a wide range of operating conditions. In summary, the goal of this study is to design and implement-advanced servosystems to actuate control surfaces for flight vehicles, namely, aircraft and helicopters, missiles and interceptors, and mini- and micro-air vehicles.

Network Learning for Educational Change. Professional Learning

ERIC Educational Resources Information Center

Veugelers, Wiel, Ed.; O'Hair, Mary John, Ed.

2005-01-01

School-university networks are becoming an important method to enhance educational renewal and student achievement. Networks go beyond tensions of top-down versus bottom-up, school development and professional development of individuals, theory and practice, and formal and informal organizational structures. The theoretical base of networking…

Artificial Intelligence in Prediction of Secondary Protein Structure Using CB513 Database

PubMed Central

Avdagic, Zikrija; Purisevic, Elvir; Omanovic, Samir; Coralic, Zlatan

2009-01-01

In this paper we describe CB513 a non-redundant dataset, suitable for development of algorithms for prediction of secondary protein structure. A program was made in Borland Delphi for transforming data from our dataset to make it suitable for learning of neural network for prediction of secondary protein structure implemented in MATLAB Neural-Network Toolbox. Learning (training and testing) of neural network is researched with different sizes of windows, different number of neurons in the hidden layer and different number of training epochs, while using dataset CB513. PMID:21347158

Discriminative Learning with Markov Logic Networks

DTIC Science & Technology

2009-10-01

Discriminative Learning with Markov Logic Networks Tuyen N. Huynh Department of Computer Sciences University of Texas at Austin Austin, TX 78712...emerging area of research that addresses the problem of learning from noisy structured/relational data. Markov logic networks (MLNs), sets of weighted...TASK NUMBER 5f. WORK UNIT NUMBER 7. PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES) University of Texas at Austin,Department of Computer

Structural Conditions for Collaboration and Learning in Innovation Networks: Using an Innovation System Performance Lens to Analyse Agricultural Knowledge Systems

ERIC Educational Resources Information Center

Hermans, Frans; Klerkx, Laurens; Roep, Dirk

2015-01-01

Purpose: We investigate how the structural conditions of eight different European agricultural innovation systems can facilitate or hinder collaboration and social learning in multidisciplinary innovation networks. Methodology: We have adapted the Innovation System Failure Matrix to investigate the main barriers and enablers eight countries…

Structuring and Regulating Collaborative Learning in Higher Education with Wireless Networks and Mobile Tools

ERIC Educational Resources Information Center

Jarvela, Sanna; Naykki, Piia; Laru, Jari; Luokkanen, Tiina

2007-01-01

In our recent research we have explored possibilities to scaffold collaborative learning in higher education with wireless networks and mobile tools. The pedagogical ideas are grounded on concepts of collaborative learning, including the socially shared origin of cognition, as well as self-regulated learning theory. This paper presents our three…

Using Social Networks to Enhance Teaching and Learning Experiences in Higher Learning Institutions

ERIC Educational Resources Information Center

Balakrishnan, Vimala

2014-01-01

The paper first explores the factors that affect the use of social networks to enhance teaching and learning experiences among students and lecturers, using structured questionnaires prepared based on the Push-Pull-Mooring framework. A total of 455 students and lecturers from higher learning institutions in Malaysia participated in this study.…

Prediction in Health Domain Using Bayesian Networks Optimization Based on Induction Learning Techniques

NASA Astrophysics Data System (ADS)

Felgaer, Pablo; Britos, Paola; García-Martínez, Ramón

A Bayesian network is a directed acyclic graph in which each node represents a variable and each arc a probabilistic dependency; they are used to provide: a compact form to represent the knowledge and flexible methods of reasoning. Obtaining it from data is a learning process that is divided in two steps: structural learning and parametric learning. In this paper we define an automatic learning method that optimizes the Bayesian networks applied to classification, using a hybrid method of learning that combines the advantages of the induction techniques of the decision trees (TDIDT-C4.5) with those of the Bayesian networks. The resulting method is applied to prediction in health domain.

Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture.

PubMed

Chen, C L Philip; Liu, Zhulin

2018-01-01

Broad Learning System (BLS) that aims to offer an alternative way of learning in deep structure is proposed in this paper. Deep structure and learning suffer from a time-consuming training process because of a large number of connecting parameters in filters and layers. Moreover, it encounters a complete retraining process if the structure is not sufficient to model the system. The BLS is established in the form of a flat network, where the original inputs are transferred and placed as "mapped features" in feature nodes and the structure is expanded in wide sense in the "enhancement nodes." The incremental learning algorithms are developed for fast remodeling in broad expansion without a retraining process if the network deems to be expanded. Two incremental learning algorithms are given for both the increment of the feature nodes (or filters in deep structure) and the increment of the enhancement nodes. The designed model and algorithms are very versatile for selecting a model rapidly. In addition, another incremental learning is developed for a system that has been modeled encounters a new incoming input. Specifically, the system can be remodeled in an incremental way without the entire retraining from the beginning. Satisfactory result for model reduction using singular value decomposition is conducted to simplify the final structure. Compared with existing deep neural networks, experimental results on the Modified National Institute of Standards and Technology database and NYU NORB object recognition dataset benchmark data demonstrate the effectiveness of the proposed BLS.

Deep learning for computational chemistry.

PubMed

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

2017-06-15

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

Kohonen and counterpropagation neural networks applied for mapping and interpretation of IR spectra.

PubMed

Novic, Marjana

2008-01-01

The principles of learning strategy of Kohonen and counterpropagation neural networks are introduced. The advantages of unsupervised learning are discussed. The self-organizing maps produced in both methods are suitable for a wide range of applications. Here, we present an example of Kohonen and counterpropagation neural networks used for mapping, interpretation, and simulation of infrared (IR) spectra. The artificial neural network models were trained for prediction of structural fragments of an unknown compound from its infrared spectrum. The training set contained over 3,200 IR spectra of diverse compounds of known chemical structure. The structure-spectra relationship was encompassed by the counterpropagation neural network, which assigned structural fragments to individual compounds within certain probability limits, assessed from the predictions of test compounds. The counterpropagation neural network model for prediction of fragments of chemical structure is reversible, which means that, for a given structural domain, limited to the training data set in the study, it can be used to simulate the IR spectrum of a chemical defined with a set of structural fragments.

Inference of time-delayed gene regulatory networks based on dynamic Bayesian network hybrid learning method

PubMed Central

Yu, Bin; Xu, Jia-Meng; Li, Shan; Chen, Cheng; Chen, Rui-Xin; Wang, Lei; Zhang, Yan; Wang, Ming-Hui

2017-01-01

Gene regulatory networks (GRNs) research reveals complex life phenomena from the perspective of gene interaction, which is an important research field in systems biology. Traditional Bayesian networks have a high computational complexity, and the network structure scoring model has a single feature. Information-based approaches cannot identify the direction of regulation. In order to make up for the shortcomings of the above methods, this paper presents a novel hybrid learning method (DBNCS) based on dynamic Bayesian network (DBN) to construct the multiple time-delayed GRNs for the first time, combining the comprehensive score (CS) with the DBN model. DBNCS algorithm first uses CMI2NI (conditional mutual inclusive information-based network inference) algorithm for network structure profiles learning, namely the construction of search space. Then the redundant regulations are removed by using the recursive optimization algorithm (RO), thereby reduce the false positive rate. Secondly, the network structure profiles are decomposed into a set of cliques without loss, which can significantly reduce the computational complexity. Finally, DBN model is used to identify the direction of gene regulation within the cliques and search for the optimal network structure. The performance of DBNCS algorithm is evaluated by the benchmark GRN datasets from DREAM challenge as well as the SOS DNA repair network in Escherichia coli, and compared with other state-of-the-art methods. The experimental results show the rationality of the algorithm design and the outstanding performance of the GRNs. PMID:29113310

Inference of time-delayed gene regulatory networks based on dynamic Bayesian network hybrid learning method.

PubMed

Yu, Bin; Xu, Jia-Meng; Li, Shan; Chen, Cheng; Chen, Rui-Xin; Wang, Lei; Zhang, Yan; Wang, Ming-Hui

2017-10-06

Gene regulatory networks (GRNs) research reveals complex life phenomena from the perspective of gene interaction, which is an important research field in systems biology. Traditional Bayesian networks have a high computational complexity, and the network structure scoring model has a single feature. Information-based approaches cannot identify the direction of regulation. In order to make up for the shortcomings of the above methods, this paper presents a novel hybrid learning method (DBNCS) based on dynamic Bayesian network (DBN) to construct the multiple time-delayed GRNs for the first time, combining the comprehensive score (CS) with the DBN model. DBNCS algorithm first uses CMI2NI (conditional mutual inclusive information-based network inference) algorithm for network structure profiles learning, namely the construction of search space. Then the redundant regulations are removed by using the recursive optimization algorithm (RO), thereby reduce the false positive rate. Secondly, the network structure profiles are decomposed into a set of cliques without loss, which can significantly reduce the computational complexity. Finally, DBN model is used to identify the direction of gene regulation within the cliques and search for the optimal network structure. The performance of DBNCS algorithm is evaluated by the benchmark GRN datasets from DREAM challenge as well as the SOS DNA repair network in Escherichia coli , and compared with other state-of-the-art methods. The experimental results show the rationality of the algorithm design and the outstanding performance of the GRNs.

The interplay between social networks and culture: theoretically and among whales and dolphins.

PubMed

Cantor, Mauricio; Whitehead, Hal

2013-05-19

Culture is increasingly being understood as a driver of mammalian phenotypes. Defined as group-specific behaviour transmitted by social learning, culture is shaped by social structure. However, culture can itself affect social structure if individuals preferentially interact with others whose behaviour is similar, or cultural symbols are used to mark groups. Using network formalism, this interplay can be depicted by the coevolution of nodes and edges together with the coevolution of network topology and transmission patterns. We review attempts to model the links between the spread, persistence and diversity of culture and the network topology of non-human societies. We illustrate these processes using cetaceans. The spread of socially learned begging behaviour within a population of bottlenose dolphins followed the topology of the social network, as did the evolution of the song of the humpback whale between breeding areas. In three bottlenose dolphin populations, individuals preferentially associated with animals using the same socially learned foraging behaviour. Homogeneous behaviour within the tight, nearly permanent social structures of the large matrilineal whales seems to result from transmission bias, with cultural symbols marking social structures. We recommend the integration of studies of culture and society in species for which social learning is an important determinant of behaviour.

The interplay between social networks and culture: theoretically and among whales and dolphins

PubMed Central

Cantor, Mauricio; Whitehead, Hal

2013-01-01

Culture is increasingly being understood as a driver of mammalian phenotypes. Defined as group-specific behaviour transmitted by social learning, culture is shaped by social structure. However, culture can itself affect social structure if individuals preferentially interact with others whose behaviour is similar, or cultural symbols are used to mark groups. Using network formalism, this interplay can be depicted by the coevolution of nodes and edges together with the coevolution of network topology and transmission patterns. We review attempts to model the links between the spread, persistence and diversity of culture and the network topology of non-human societies. We illustrate these processes using cetaceans. The spread of socially learned begging behaviour within a population of bottlenose dolphins followed the topology of the social network, as did the evolution of the song of the humpback whale between breeding areas. In three bottlenose dolphin populations, individuals preferentially associated with animals using the same socially learned foraging behaviour. Homogeneous behaviour within the tight, nearly permanent social structures of the large matrilineal whales seems to result from transmission bias, with cultural symbols marking social structures. We recommend the integration of studies of culture and society in species for which social learning is an important determinant of behaviour. PMID:23569288

Quantitative learning strategies based on word networks

NASA Astrophysics Data System (ADS)

Zhao, Yue-Tian-Yi; Jia, Zi-Yang; Tang, Yong; Xiong, Jason Jie; Zhang, Yi-Cheng

2018-02-01

Learning English requires a considerable effort, but the way that vocabulary is introduced in textbooks is not optimized for learning efficiency. With the increasing population of English learners, learning process optimization will have significant impact and improvement towards English learning and teaching. The recent developments of big data analysis and complex network science provide additional opportunities to design and further investigate the strategies in English learning. In this paper, quantitative English learning strategies based on word network and word usage information are proposed. The strategies integrate the words frequency with topological structural information. By analyzing the influence of connected learned words, the learning weights for the unlearned words and dynamically updating of the network are studied and analyzed. The results suggest that quantitative strategies significantly improve learning efficiency while maintaining effectiveness. Especially, the optimized-weight-first strategy and segmented strategies outperform other strategies. The results provide opportunities for researchers and practitioners to reconsider the way of English teaching and designing vocabularies quantitatively by balancing the efficiency and learning costs based on the word network.

Learning polynomial feedforward neural networks by genetic programming and backpropagation.

PubMed

Nikolaev, N Y; Iba, H

2003-01-01

This paper presents an approach to learning polynomial feedforward neural networks (PFNNs). The approach suggests, first, finding the polynomial network structure by means of a population-based search technique relying on the genetic programming paradigm, and second, further adjustment of the best discovered network weights by an especially derived backpropagation algorithm for higher order networks with polynomial activation functions. These two stages of the PFNN learning process enable us to identify networks with good training as well as generalization performance. Empirical results show that this approach finds PFNN which outperform considerably some previous constructive polynomial network algorithms on processing benchmark time series.

Optimal Learning Paths in Information Networks

PubMed Central

Rodi, G. C.; Loreto, V.; Servedio, V. D. P.; Tria, F.

2015-01-01

Each sphere of knowledge and information could be depicted as a complex mesh of correlated items. By properly exploiting these connections, innovative and more efficient navigation strategies could be defined, possibly leading to a faster learning process and an enduring retention of information. In this work we investigate how the topological structure embedding the items to be learned can affect the efficiency of the learning dynamics. To this end we introduce a general class of algorithms that simulate the exploration of knowledge/information networks standing on well-established findings on educational scheduling, namely the spacing and lag effects. While constructing their learning schedules, individuals move along connections, periodically revisiting some concepts, and sometimes jumping on very distant ones. In order to investigate the effect of networked information structures on the proposed learning dynamics we focused both on synthetic and real-world graphs such as subsections of Wikipedia and word-association graphs. We highlight the existence of optimal topological structures for the simulated learning dynamics whose efficiency is affected by the balance between hubs and the least connected items. Interestingly, the real-world graphs we considered lead naturally to almost optimal learning performances. PMID:26030508

Relationship Governance and Learning in Partnerships

ERIC Educational Resources Information Center

Kohtamaki, Marko

2010-01-01

Purpose: Relationship learning is a topic of considerable importance for industrial networks, yet a lack of empirical research on the impact of relationship governance structures on relationship learning remains. The purpose of this paper is to analyze the impact of relationship governance structures on learning in partnerships.…

A tree-like Bayesian structure learning algorithm for small-sample datasets from complex biological model systems.

PubMed

Yin, Weiwei; Garimalla, Swetha; Moreno, Alberto; Galinski, Mary R; Styczynski, Mark P

2015-08-28

There are increasing efforts to bring high-throughput systems biology techniques to bear on complex animal model systems, often with a goal of learning about underlying regulatory network structures (e.g., gene regulatory networks). However, complex animal model systems typically have significant limitations on cohort sizes, number of samples, and the ability to perform follow-up and validation experiments. These constraints are particularly problematic for many current network learning approaches, which require large numbers of samples and may predict many more regulatory relationships than actually exist. Here, we test the idea that by leveraging the accuracy and efficiency of classifiers, we can construct high-quality networks that capture important interactions between variables in datasets with few samples. We start from a previously-developed tree-like Bayesian classifier and generalize its network learning approach to allow for arbitrary depth and complexity of tree-like networks. Using four diverse sample networks, we demonstrate that this approach performs consistently better at low sample sizes than the Sparse Candidate Algorithm, a representative approach for comparison because it is known to generate Bayesian networks with high positive predictive value. We develop and demonstrate a resampling-based approach to enable the identification of a viable root for the learned tree-like network, important for cases where the root of a network is not known a priori. We also develop and demonstrate an integrated resampling-based approach to the reduction of variable space for the learning of the network. Finally, we demonstrate the utility of this approach via the analysis of a transcriptional dataset of a malaria challenge in a non-human primate model system, Macaca mulatta, suggesting the potential to capture indicators of the earliest stages of cellular differentiation during leukopoiesis. We demonstrate that by starting from effective and efficient approaches for creating classifiers, we can identify interesting tree-like network structures with significant ability to capture the relationships in the training data. This approach represents a promising strategy for inferring networks with high positive predictive value under the constraint of small numbers of samples, meeting a need that will only continue to grow as more high-throughput studies are applied to complex model systems.

Social Inclusion and Learning Networks: A "Wider Notion of Learning" or Taking Things in a Different Direction?

ERIC Educational Resources Information Center

O'Brien, Mark; Atkinson, Amanda; Burton, Diana; Campbell, Anne; Qualter, Anne; Varga-Atkins, Tunde

2009-01-01

This article has been produced from the work of a research project conducted in the context of a city-wide education service in the United Kingdom. This was the Liverpool Learning Networks Research Project, which began in July 2005. The researchers carried out semi-structured interviews with education practitioners--learning network…

A Dynamic Bayesian Network Based Structural Learning towards Automated Handwritten Digit Recognition

NASA Astrophysics Data System (ADS)

Pauplin, Olivier; Jiang, Jianmin

Pattern recognition using Dynamic Bayesian Networks (DBNs) is currently a growing area of study. In this paper, we present DBN models trained for classification of handwritten digit characters. The structure of these models is partly inferred from the training data of each class of digit before performing parameter learning. Classification results are presented for the four described models.

How Social Network Position Relates to Knowledge Building in Online Learning Communities

ERIC Educational Resources Information Center

Wang, Lu

2010-01-01

Social Network Analysis, Statistical Analysis, Content Analysis and other research methods were used to research online learning communities at Capital Normal University, Beijing. Analysis of the two online courses resulted in the following conclusions: (1) Social networks of the two online courses form typical core-periphery structures; (2)…

Wavefront cellular learning automata.

PubMed

Moradabadi, Behnaz; Meybodi, Mohammad Reza

2018-02-01

This paper proposes a new cellular learning automaton, called a wavefront cellular learning automaton (WCLA). The proposed WCLA has a set of learning automata mapped to a connected structure and uses this structure to propagate the state changes of the learning automata over the structure using waves. In the WCLA, after one learning automaton chooses its action, if this chosen action is different from the previous action, it can send a wave to its neighbors and activate them. Each neighbor receiving the wave is activated and must choose a new action. This structure for the WCLA is necessary in many dynamic areas such as social networks, computer networks, grid computing, and web mining. In this paper, we introduce the WCLA framework as an optimization tool with diffusion capability, study its behavior over time using ordinary differential equation solutions, and present its accuracy using expediency analysis. To show the superiority of the proposed WCLA, we compare the proposed method with some other types of cellular learning automata using two benchmark problems.

Wavefront cellular learning automata

NASA Astrophysics Data System (ADS)

Moradabadi, Behnaz; Meybodi, Mohammad Reza

2018-02-01

This paper proposes a new cellular learning automaton, called a wavefront cellular learning automaton (WCLA). The proposed WCLA has a set of learning automata mapped to a connected structure and uses this structure to propagate the state changes of the learning automata over the structure using waves. In the WCLA, after one learning automaton chooses its action, if this chosen action is different from the previous action, it can send a wave to its neighbors and activate them. Each neighbor receiving the wave is activated and must choose a new action. This structure for the WCLA is necessary in many dynamic areas such as social networks, computer networks, grid computing, and web mining. In this paper, we introduce the WCLA framework as an optimization tool with diffusion capability, study its behavior over time using ordinary differential equation solutions, and present its accuracy using expediency analysis. To show the superiority of the proposed WCLA, we compare the proposed method with some other types of cellular learning automata using two benchmark problems.

Model-free distributed learning

NASA Technical Reports Server (NTRS)

Dembo, Amir; Kailath, Thomas

1990-01-01

Model-free learning for synchronous and asynchronous quasi-static networks is presented. The network weights are continuously perturbed, while the time-varying performance index is measured and correlated with the perturbation signals; the correlation output determines the changes in the weights. The perturbation may be either via noise sources or orthogonal signals. The invariance to detailed network structure mitigates large variability between supposedly identical networks as well as implementation defects. This local, regular, and completely distributed mechanism requires no central control and involves only a few global signals. Thus it allows for integrated on-chip learning in large analog and optical networks.

SUSTAIN: a network model of category learning.

PubMed

Love, Bradley C; Medin, Douglas L; Gureckis, Todd M

2004-04-01

SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a model of how humans learn categories from examples. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes-attractors-rules. SUSTAIN's discovery of category substructure is affected not only by the structure of the world but by the nature of the learning task and the learner's goals. SUSTAIN successfully extends category learning models to studies of inference learning, unsupervised learning, category construction, and contexts in which identification learning is faster than classification learning.

A Structure-Adaptive Hybrid RBF-BP Classifier with an Optimized Learning Strategy

PubMed Central

Wen, Hui; Xie, Weixin; Pei, Jihong

2016-01-01

This paper presents a structure-adaptive hybrid RBF-BP (SAHRBF-BP) classifier with an optimized learning strategy. SAHRBF-BP is composed of a structure-adaptive RBF network and a BP network of cascade, where the number of RBF hidden nodes is adjusted adaptively according to the distribution of sample space, the adaptive RBF network is used for nonlinear kernel mapping and the BP network is used for nonlinear classification. The optimized learning strategy is as follows: firstly, a potential function is introduced into training sample space to adaptively determine the number of initial RBF hidden nodes and node parameters, and a form of heterogeneous samples repulsive force is designed to further optimize each generated RBF hidden node parameters, the optimized structure-adaptive RBF network is used for adaptively nonlinear mapping the sample space; then, according to the number of adaptively generated RBF hidden nodes, the number of subsequent BP input nodes can be determined, and the overall SAHRBF-BP classifier is built up; finally, different training sample sets are used to train the BP network parameters in SAHRBF-BP. Compared with other algorithms applied to different data sets, experiments show the superiority of SAHRBF-BP. Especially on most low dimensional and large number of data sets, the classification performance of SAHRBF-BP outperforms other training SLFNs algorithms. PMID:27792737

SAN-RL: combining spreading activation networks and reinforcement learning to learn configurable behaviors

NASA Technical Reports Server (NTRS)

White, J.; Gaines, D. M.; Wilkes, M.; Kusumalnukool, K.; Thongchai, S.; Kawamura, K.

2001-01-01

This approach provides the agent with a causal structure, the spreading activation network, relating goals to the actions that can achieve those goals. This enables the agent to select actions relative to the goal priorities.

Structured Semantic Knowledge Can Emerge Automatically from Predicting Word Sequences in Child-Directed Speech

PubMed Central

Huebner, Philip A.; Willits, Jon A.

2018-01-01

Previous research has suggested that distributional learning mechanisms may contribute to the acquisition of semantic knowledge. However, distributional learning mechanisms, statistical learning, and contemporary “deep learning” approaches have been criticized for being incapable of learning the kind of abstract and structured knowledge that many think is required for acquisition of semantic knowledge. In this paper, we show that recurrent neural networks, trained on noisy naturalistic speech to children, do in fact learn what appears to be abstract and structured knowledge. We trained two types of recurrent neural networks (Simple Recurrent Network, and Long Short-Term Memory) to predict word sequences in a 5-million-word corpus of speech directed to children ages 0–3 years old, and assessed what semantic knowledge they acquired. We found that learned internal representations are encoding various abstract grammatical and semantic features that are useful for predicting word sequences. Assessing the organization of semantic knowledge in terms of the similarity structure, we found evidence of emergent categorical and hierarchical structure in both models. We found that the Long Short-term Memory (LSTM) and SRN are both learning very similar kinds of representations, but the LSTM achieved higher levels of performance on a quantitative evaluation. We also trained a non-recurrent neural network, Skip-gram, on the same input to compare our results to the state-of-the-art in machine learning. We found that Skip-gram achieves relatively similar performance to the LSTM, but is representing words more in terms of thematic compared to taxonomic relations, and we provide reasons why this might be the case. Our findings show that a learning system that derives abstract, distributed representations for the purpose of predicting sequential dependencies in naturalistic language may provide insight into emergence of many properties of the developing semantic system. PMID:29520243

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule.

PubMed

Liu, Hui; Song, Yongduan; Xue, Fangzheng; Li, Xiumin

2015-11-01

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than the SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.

Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule

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

Liu, Hui; Song, Yongduan; Xue, Fangzheng

In this paper, the generation of multi-clustered structure of self-organized neural network with different neuronal firing patterns, i.e., bursting or spiking, has been investigated. The initially all-to-all-connected spiking neural network or bursting neural network can be self-organized into clustered structure through the symmetric spike-timing-dependent plasticity learning for both bursting and spiking neurons. However, the time consumption of this clustering procedure of the burst-based self-organized neural network (BSON) is much shorter than the spike-based self-organized neural network (SSON). Our results show that the BSON network has more obvious small-world properties, i.e., higher clustering coefficient and smaller shortest path length than themore » SSON network. Also, the results of larger structure entropy and activity entropy of the BSON network demonstrate that this network has higher topological complexity and dynamical diversity, which benefits for enhancing information transmission of neural circuits. Hence, we conclude that the burst firing can significantly enhance the efficiency of clustering procedure and the emergent clustered structure renders the whole network more synchronous and therefore more sensitive to weak input. This result is further confirmed from its improved performance on stochastic resonance. Therefore, we believe that the multi-clustered neural network which self-organized from the bursting dynamics has high efficiency in information processing.« less

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.

Building a Global Learning Organization: Lessons from the World's Top Corporations.

ERIC Educational Resources Information Center

Marquardt, Michael J.

1995-01-01

Research on 50 organizations elicited 19 attributes of learning organizations: individual learning, group learning, streamlined structure, corporate learning culture, empowerment, environmental scanning, knowledge creation/transfer, learning technology, quality, learning strategy, supportive atmosphere, teamwork/networking, vision, acculturation,…

A novel time series link prediction method: Learning automata approach

NASA Astrophysics Data System (ADS)

Moradabadi, Behnaz; Meybodi, Mohammad Reza

2017-09-01

Link prediction is a main social network challenge that uses the network structure to predict future links. The common link prediction approaches to predict hidden links use a static graph representation where a snapshot of the network is analyzed to find hidden or future links. For example, similarity metric based link predictions are a common traditional approach that calculates the similarity metric for each non-connected link and sort the links based on their similarity metrics and label the links with higher similarity scores as the future links. Because people activities in social networks are dynamic and uncertainty, and the structure of the networks changes over time, using deterministic graphs for modeling and analysis of the social network may not be appropriate. In the time-series link prediction problem, the time series link occurrences are used to predict the future links In this paper, we propose a new time series link prediction based on learning automata. In the proposed algorithm for each link that must be predicted there is one learning automaton and each learning automaton tries to predict the existence or non-existence of the corresponding link. To predict the link occurrence in time T, there is a chain consists of stages 1 through T - 1 and the learning automaton passes from these stages to learn the existence or non-existence of the corresponding link. Our preliminary link prediction experiments with co-authorship and email networks have provided satisfactory results when time series link occurrences are considered.

Cooperation-Controlled Learning for Explicit Class Structure in Self-Organizing Maps

PubMed Central

Kamimura, Ryotaro

2014-01-01

We attempt to demonstrate the effectiveness of multiple points of view toward neural networks. By restricting ourselves to two points of view of a neuron, we propose a new type of information-theoretic method called “cooperation-controlled learning.” In this method, individual and collective neurons are distinguished from one another, and we suppose that the characteristics of individual and collective neurons are different. To implement individual and collective neurons, we prepare two networks, namely, cooperative and uncooperative networks. The roles of these networks and the roles of individual and collective neurons are controlled by the cooperation parameter. As the parameter is increased, the role of cooperative networks becomes more important in learning, and the characteristics of collective neurons become more dominant. On the other hand, when the parameter is small, individual neurons play a more important role. We applied the method to the automobile and housing data from the machine learning database and examined whether explicit class boundaries could be obtained. Experimental results showed that cooperation-controlled learning, in particular taking into account information on input units, could be used to produce clearer class structure than conventional self-organizing maps. PMID:25309950

Dissociable changes in functional network topology underlie early category learning and development of automaticity

PubMed Central

Soto, Fabian A.; Bassett, Danielle S.; Ashby, F. Gregory

2016-01-01

Recent work has shown that multimodal association areas–including frontal, temporal and parietal cortex–are focal points of functional network reconfiguration during human learning and performance of cognitive tasks. On the other hand, neurocomputational theories of category learning suggest that the basal ganglia and related subcortical structures are focal points of functional network reconfiguration during early learning of some categorization tasks, but become less so with the development of automatic categorization performance. Using a combination of network science and multilevel regression, we explore how changes in the connectivity of small brain regions can predict behavioral changes during training in a visual categorization task. We find that initial category learning, as indexed by changes in accuracy, is predicted by increasingly efficient integrative processing in subcortical areas, with higher functional specialization, more efficient integration across modules, but a lower cost in terms of redundancy of information processing. The development of automaticity, as indexed by changes in the speed of correct responses, was predicted by lower clustering (particularly in subcortical areas), higher strength (highest in cortical areas) and higher betweenness centrality. By combining neurocomputational theories and network scientific methods, these results synthesize the dissociative roles of multimodal association areas and subcortical structures in the development of automaticity during category learning. PMID:27453156

A neural network construction method for surrogate modeling of physics-based analysis

NASA Astrophysics Data System (ADS)

Sung, Woong Je

In this thesis existing methodologies related to the developmental methods of neural networks have been surveyed and their approaches to network sizing and structuring are carefully observed. This literature review covers the constructive methods, the pruning methods, and the evolutionary methods and questions about the basic assumption intrinsic to the conventional neural network learning paradigm, which is primarily devoted to optimization of connection weights (or synaptic strengths) for the pre-determined connection structure of the network. The main research hypothesis governing this thesis is that, without breaking a prevailing dichotomy between weights and connectivity of the network during learning phase, the efficient design of a task-specific neural network is hard to achieve because, as long as connectivity and weights are searched by separate means, a structural optimization of the neural network requires either repetitive re-training procedures or computationally expensive topological meta-search cycles. The main contribution of this thesis is designing and testing a novel learning mechanism which efficiently learns not only weight parameters but also connection structure from a given training data set, and positioning this learning mechanism within the surrogate modeling practice. In this work, a simple and straightforward extension to the conventional error Back-Propagation (BP) algorithm has been formulated to enable a simultaneous learning for both connectivity and weights of the Generalized Multilayer Perceptron (GMLP) in supervised learning tasks. A particular objective is to achieve a task-specific network having reasonable generalization performance with a minimal training time. The dichotomy between architectural design and weight optimization is reconciled by a mechanism establishing a new connection for a neuron pair which has potentially higher error-gradient than one of the existing connections. Interpreting an instance of the absence of connection as a zero-weight connection, the potential contribution to training error reduction of any present or absent connection can readily be evaluated using the BP algorithm. Instead of being broken, the connections that contribute less remain frozen with constant weight values optimized to that point but they are excluded from further weight optimization until reselected. In this way, a selective weight optimization is executed only for the dynamically maintained pool of high gradient connections. By searching the rapidly changing weights and concentrating optimization resources on them, the learning process is accelerated without either a significant increase in computational cost or a need for re-training. This results in a more task-adapted network connection structure. Combined with another important criterion for the division of a neuron which adds a new computational unit to a network, a highly fitted network can be grown out of the minimal random structure. This particular learning strategy can belong to a more broad class of the variable connectivity learning scheme and the devised algorithm has been named Optimal Brain Growth (OBG). The OBG algorithm has been tested on two canonical problems; a regression analysis using the Complicated Interaction Regression Function and a classification of the Two-Spiral Problem. A comparative study with conventional Multilayer Perceptrons (MLPs) consisting of single- and double-hidden layers shows that OBG is less sensitive to random initial conditions and generalizes better with only a minimal increase in computational time. This partially proves that a variable connectivity learning scheme has great potential to enhance computational efficiency and reduce efforts to select proper network architecture. To investigate the applicability of the OBG to more practical surrogate modeling tasks, the geometry-to-pressure mapping of a particular class of airfoils in the transonic flow regime has been sought using both the conventional MLP networks with pre-defined architecture and the OBG-developed networks started from the same initial MLP networks. Considering wide variety in airfoil geometry and diversity of flow conditions distributed over a range of flow Mach numbers and angles of attack, the new method shows a great potential to capture fundamentally nonlinear flow phenomena especially related to the occurrence of shock waves on airfoil surfaces in transonic flow regime. (Abstract shortened by UMI.).

Neural networks involved in learning lexical-semantic and syntactic information in a second language.

PubMed

Mueller, Jutta L; Rueschemeyer, Shirley-Ann; Ono, Kentaro; Sugiura, Motoaki; Sadato, Norihiro; Nakamura, Akinori

2014-01-01

The present study used functional magnetic resonance imaging (fMRI) to investigate the neural correlates of language acquisition in a realistic learning environment. Japanese native speakers were trained in a miniature version of German prior to fMRI scanning. During scanning they listened to (1) familiar sentences, (2) sentences including a novel sentence structure, and (3) sentences containing a novel word while visual context provided referential information. Learning-related decreases of brain activation over time were found in a mainly left-hemispheric network comprising classical frontal and temporal language areas as well as parietal and subcortical regions and were largely overlapping for novel words and the novel sentence structure in initial stages of learning. Differences occurred at later stages of learning during which content-specific activation patterns in prefrontal, parietal and temporal cortices emerged. The results are taken as evidence for a domain-general network supporting the initial stages of language learning which dynamically adapts as learners become proficient.

NCI National Clinical Trials Network Structure

Cancer.gov

Learn about how the National Clinical Trials Network (NCTN) is structured. The NCTN is a program of the National Cancer Institute that gives funds and other support to cancer research organizations to conduct cancer clinical trials.

Synchronization of heteroclinic circuits through learning in coupled neural networks

NASA Astrophysics Data System (ADS)

Selskii, Anton; Makarov, Valeri A.

2016-01-01

The synchronization of oscillatory activity in neural networks is usually implemented by coupling the state variables describing neuronal dynamics. Here we study another, but complementary mechanism based on a learning process with memory. A driver network, acting as a teacher, exhibits winner-less competition (WLC) dynamics, while a driven network, a learner, tunes its internal couplings according to the oscillations observed in the teacher. We show that under appropriate training the learner can "copy" the coupling structure and thus synchronize oscillations with the teacher. The replication of the WLC dynamics occurs for intermediate memory lengths only, consequently, the learner network exhibits a phenomenon of learning resonance.

High-throughput Bayesian Network Learning using Heterogeneous Multicore Computers

PubMed Central

Linderman, Michael D.; Athalye, Vivek; Meng, Teresa H.; Asadi, Narges Bani; Bruggner, Robert; Nolan, Garry P.

2017-01-01

Aberrant intracellular signaling plays an important role in many diseases. The causal structure of signal transduction networks can be modeled as Bayesian Networks (BNs), and computationally learned from experimental data. However, learning the structure of Bayesian Networks (BNs) is an NP-hard problem that, even with fast heuristics, is too time consuming for large, clinically important networks (20–50 nodes). In this paper, we present a novel graphics processing unit (GPU)-accelerated implementation of a Monte Carlo Markov Chain-based algorithm for learning BNs that is up to 7.5-fold faster than current general-purpose processor (GPP)-based implementations. The GPU-based implementation is just one of several implementations within the larger application, each optimized for a different input or machine configuration. We describe the methodology we use to build an extensible application, assembled from these variants, that can target a broad range of heterogeneous systems, e.g., GPUs, multicore GPPs. Specifically we show how we use the Merge programming model to efficiently integrate, test and intelligently select among the different potential implementations. PMID:28819655

Influence of Learning Styles on Social Structures in Online Learning Environments

ERIC Educational Resources Information Center

Cela, Karina; Sicilia, Miguel-Ángel; Sánchez-Alonso, Salvador

2016-01-01

In e-learning settings, the interactions of students with one another, with the course content and with the instructors generate a considerable amount of information that may be useful for understanding how people learn online. The objective of the present research was to use social network analysis to explore the social structure of an e-learning…

Distributed synaptic weights in a LIF neural network and learning rules

NASA Astrophysics Data System (ADS)

Perthame, Benoît; Salort, Delphine; Wainrib, Gilles

2017-09-01

Leaky integrate-and-fire (LIF) models are mean-field limits, with a large number of neurons, used to describe neural networks. We consider inhomogeneous networks structured by a connectivity parameter (strengths of the synaptic weights) with the effect of processing the input current with different intensities. We first study the properties of the network activity depending on the distribution of synaptic weights and in particular its discrimination capacity. Then, we consider simple learning rules and determine the synaptic weight distribution it generates. We outline the role of noise as a selection principle and the capacity to memorize a learned signal.

A proposal of fuzzy connective with learning function and its application to fuzzy retrieval system

NASA Technical Reports Server (NTRS)

Hayashi, Isao; Naito, Eiichi; Ozawa, Jun; Wakami, Noboru

1993-01-01

A new fuzzy connective and a structure of network constructed by fuzzy connectives are proposed to overcome a drawback of conventional fuzzy retrieval systems. This network represents a retrieval query and the fuzzy connectives in networks have a learning function to adjust its parameters by data from a database and outputs of a user. The fuzzy retrieval systems employing this network are also constructed. Users can retrieve results even with a query whose attributes do not exist in a database schema and can get satisfactory results for variety of thinkings by learning function.

Learning Orthographic Structure with Sequential Generative Neural Networks

ERIC Educational Resources Information Center

Testolin, Alberto; Stoianov, Ivilin; Sperduti, Alessandro; Zorzi, Marco

2016-01-01

Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in…

Learning the Relationship between the Primary Structure of HIV Envelope Glycoproteins and Neutralization Activity of Particular Antibodies by Using Artificial Neural Networks

PubMed Central

Buiu, Cătălin; Putz, Mihai V.; Avram, Speranta

2016-01-01

The dependency between the primary structure of HIV envelope glycoproteins (ENV) and the neutralization data for given antibodies is very complicated and depends on a large number of factors, such as the binding affinity of a given antibody for a given ENV protein, and the intrinsic infection kinetics of the viral strain. This paper presents a first approach to learning these dependencies using an artificial feedforward neural network which is trained to learn from experimental data. The results presented here demonstrate that the trained neural network is able to generalize on new viral strains and to predict reliable values of neutralizing activities of given antibodies against HIV-1. PMID:27727189

Cooperation enhanced by indirect reciprocity in spatial prisoner's dilemma games for social P2P systems

NASA Astrophysics Data System (ADS)

Tian, Lin-Lin; Li, Ming-Chu; Wang, Zhen

2016-11-01

With the growing interest in social Peer-to-Peer (P2P) applications, relationships of individuals are further exploited to improve the performances of reputation systems. It is an on-going challenge to investigate how spatial reciprocity aids indirect reciprocity in sustaining cooperation in practical P2P environments. This paper describes the construction of an extended prisoner's dilemma game on square lattice networks with three strategies, i.e., defection, unconditional cooperation, and reciprocal cooperation. Reciprocators discriminate partners according to their reputations based on image scoring, where mistakes in judgment of reputations may occur. The independent structures of interaction and learning neighborhood are discussed, with respect to the situation in which learning environments differ from interaction networks. The simulation results have indicated that the incentive mechanism enhances cooperation better in structured peers than among a well-mixed population. Given the realistic condition of inaccurate reputation scores, defection is still successfully held down when the players interact and learn within the unified neighborhoods. Extensive simulations have further confirmed the positive impact of spatial structure on cooperation with different sizes of lattice neighborhoods. And similar conclusions can also be drawn on regular random networks and scale-free networks. Moreover, for the separated structures of the neighborhoods, the interaction network has a critical effect on the evolution dynamics of cooperation and learning environments only have weaker impacts on the process. Our findings further provide some insights concerning the evolution of collective behaviors in social systems.

Evolutionary image simplification for lung nodule classification with convolutional neural networks.

PubMed

Lückehe, Daniel; von Voigt, Gabriele

2018-05-29

Understanding decisions of deep learning techniques is important. Especially in the medical field, the reasons for a decision in a classification task are as crucial as the pure classification results. In this article, we propose a new approach to compute relevant parts of a medical image. Knowing the relevant parts makes it easier to understand decisions. In our approach, a convolutional neural network is employed to learn structures of images of lung nodules. Then, an evolutionary algorithm is applied to compute a simplified version of an unknown image based on the learned structures by the convolutional neural network. In the simplified version, irrelevant parts are removed from the original image. In the results, we show simplified images which allow the observer to focus on the relevant parts. In these images, more than 50% of the pixels are simplified. The simplified pixels do not change the meaning of the images based on the learned structures by the convolutional neural network. An experimental analysis shows the potential of the approach. Besides the examples of simplified images, we analyze the run time development. Simplified images make it easier to focus on relevant parts and to find reasons for a decision. The combination of an evolutionary algorithm employing a learned convolutional neural network is well suited for the simplification task. From a research perspective, it is interesting which areas of the images are simplified and which parts are taken as relevant.

How to Trigger Emergence and Self-Organisation in Learning Networks

NASA Astrophysics Data System (ADS)

Brouns, Francis; Fetter, Sibren; van Rosmalen, Peter

The previous chapters of this section discussed why the social structure of Learning Networks is important and present guidelines on how to maintain and allow the emergence of communities in Learning Networks. Chapter 2 explains how Learning Networks rely on social interaction and active participations of the participants. Chapter 3 then continues by presenting guidelines and policies that should be incorporated into Learning Network Services in order to maintain existing communities by creating conditions that promote social interaction and knowledge sharing. Chapter 4 discusses the necessary conditions required for knowledge sharing to occur and to trigger communities to self-organise and emerge. As pointed out in Chap. 4, ad-hoc transient communities facilitate the emergence of social interaction in Learning Networks, self-organising them into communities, taking into account personal characteristics, community characteristics and general guidelines. As explained in Chap. 4 community members would benefit from a service that brings suitable people together for a specific purpose, because it will allow the participant to focus on the knowledge sharing process by reducing the effort or costs. In the current chapter, we describe an example of a peer support Learning Network Service based on the mechanism of peer tutoring in ad-hoc transient communities.

Reverse engineering highlights potential principles of large gene regulatory network design and learning.

PubMed

Carré, Clément; Mas, André; Krouk, Gabriel

2017-01-01

Inferring transcriptional gene regulatory networks from transcriptomic datasets is a key challenge of systems biology, with potential impacts ranging from medicine to agronomy. There are several techniques used presently to experimentally assay transcription factors to target relationships, defining important information about real gene regulatory networks connections. These techniques include classical ChIP-seq, yeast one-hybrid, or more recently, DAP-seq or target technologies. These techniques are usually used to validate algorithm predictions. Here, we developed a reverse engineering approach based on mathematical and computer simulation to evaluate the impact that this prior knowledge on gene regulatory networks may have on training machine learning algorithms. First, we developed a gene regulatory networks-simulating engine called FRANK (Fast Randomizing Algorithm for Network Knowledge) that is able to simulate large gene regulatory networks (containing 10 4 genes) with characteristics of gene regulatory networks observed in vivo. FRANK also generates stable or oscillatory gene expression directly produced by the simulated gene regulatory networks. The development of FRANK leads to important general conclusions concerning the design of large and stable gene regulatory networks harboring scale free properties (built ex nihilo). In combination with supervised (accepting prior knowledge) support vector machine algorithm we (i) address biologically oriented questions concerning our capacity to accurately reconstruct gene regulatory networks and in particular we demonstrate that prior-knowledge structure is crucial for accurate learning, and (ii) draw conclusions to inform experimental design to performed learning able to solve gene regulatory networks in the future. By demonstrating that our predictions concerning the influence of the prior-knowledge structure on support vector machine learning capacity holds true on real data ( Escherichia coli K14 network reconstruction using network and transcriptomic data), we show that the formalism used to build FRANK can to some extent be a reasonable model for gene regulatory networks in real cells.

Modelling unsupervised online-learning of artificial grammars: linking implicit and statistical learning.

PubMed

Rohrmeier, Martin A; Cross, Ian

2014-07-01

Humans rapidly learn complex structures in various domains. Findings of above-chance performance of some untrained control groups in artificial grammar learning studies raise questions about the extent to which learning can occur in an untrained, unsupervised testing situation with both correct and incorrect structures. The plausibility of unsupervised online-learning effects was modelled with n-gram, chunking and simple recurrent network models. A novel evaluation framework was applied, which alternates forced binary grammaticality judgments and subsequent learning of the same stimulus. Our results indicate a strong online learning effect for n-gram and chunking models and a weaker effect for simple recurrent network models. Such findings suggest that online learning is a plausible effect of statistical chunk learning that is possible when ungrammatical sequences contain a large proportion of grammatical chunks. Such common effects of continuous statistical learning may underlie statistical and implicit learning paradigms and raise implications for study design and testing methodologies. Copyright © 2014 Elsevier Inc. All rights reserved.

bnstruct: an R package for Bayesian Network structure learning in the presence of missing data.

PubMed

Franzin, Alberto; Sambo, Francesco; Di Camillo, Barbara

2017-04-15

A Bayesian Network is a probabilistic graphical model that encodes probabilistic dependencies between a set of random variables. We introduce bnstruct, an open source R package to (i) learn the structure and the parameters of a Bayesian Network from data in the presence of missing values and (ii) perform reasoning and inference on the learned Bayesian Networks. To the best of our knowledge, there is no other open source software that provides methods for all of these tasks, particularly the manipulation of missing data, which is a common situation in practice. The software is implemented in R and C and is available on CRAN under a GPL licence. francesco.sambo@unipd.it. Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com

Support-vector-machine tree-based domain knowledge learning toward automated sports video classification

NASA Astrophysics Data System (ADS)

Xiao, Guoqiang; Jiang, Yang; Song, Gang; Jiang, Jianmin

2010-12-01

We propose a support-vector-machine (SVM) tree to hierarchically learn from domain knowledge represented by low-level features toward automatic classification of sports videos. The proposed SVM tree adopts a binary tree structure to exploit the nature of SVM's binary classification, where each internal node is a single SVM learning unit, and each external node represents the classified output type. Such a SVM tree presents a number of advantages, which include: 1. low computing cost; 2. integrated learning and classification while preserving individual SVM's learning strength; and 3. flexibility in both structure and learning modules, where different numbers of nodes and features can be added to address specific learning requirements, and various learning models can be added as individual nodes, such as neural networks, AdaBoost, hidden Markov models, dynamic Bayesian networks, etc. Experiments support that the proposed SVM tree achieves good performances in sports video classifications.

A Self-Organizing Incremental Neural Network based on local distribution learning.

PubMed

Xing, Youlu; Shi, Xiaofeng; Shen, Furao; Zhou, Ke; Zhao, Jinxi

2016-12-01

In this paper, we propose an unsupervised incremental learning neural network based on local distribution learning, which is called Local Distribution Self-Organizing Incremental Neural Network (LD-SOINN). The LD-SOINN combines the advantages of incremental learning and matrix learning. It can automatically discover suitable nodes to fit the learning data in an incremental way without a priori knowledge such as the structure of the network. The nodes of the network store rich local information regarding the learning data. The adaptive vigilance parameter guarantees that LD-SOINN is able to add new nodes for new knowledge automatically and the number of nodes will not grow unlimitedly. While the learning process continues, nodes that are close to each other and have similar principal components are merged to obtain a concise local representation, which we call a relaxation data representation. A denoising process based on density is designed to reduce the influence of noise. Experiments show that the LD-SOINN performs well on both artificial and real-word data. Copyright © 2016 Elsevier Ltd. All rights reserved.

The Student Experience of Learning Using Networked Technologies: An Emergent Progression of Expanding Awareness

ERIC Educational Resources Information Center

Cutajar, Maria

2017-01-01

This article reports on phenomenographic research which explored the qualitative differences in post-secondary students' accounts of their networked learning experiences. Data was generated using semi-structured interviews with a purposive sample of participants. Phenomenographic analysis led to a configuration of variation in students' accounts…

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

PubMed Central

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

2013-01-01

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

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

PubMed

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

2013-01-01

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

Networked Learning and Network Science: Potential Applications to Health Professionals' Continuing Education and Development.

PubMed

Margolis, Alvaro; Parboosingh, John

2015-01-01

Prior interpersonal relationships and interactivity among members of professional associations may impact the learning process in continuing medical education (CME). On the other hand, CME programs that encourage interactivity between participants may impact structures and behaviors in these professional associations. With the advent of information and communication technologies, new communication spaces have emerged that have the potential to enhance networked learning in national and international professional associations and increase the effectiveness of CME for health professionals. In this article, network science, based on the application of network theory and other theories, is proposed as an approach to better understand the contribution networking and interactivity between health professionals in professional communities make to their learning and adoption of new practices over time. © 2015 The Alliance for Continuing Education in the Health Professions, the Society for Academic Continuing Medical Education, and the Council on Continuing Medical Education, Association for Hospital Medical Education.

Relationship between neuronal network architecture and naming performance in temporal lobe epilepsy: A connectome based approach using machine learning.

PubMed

Munsell, B C; Wu, G; Fridriksson, J; Thayer, K; Mofrad, N; Desisto, N; Shen, D; Bonilha, L

2017-09-09

Impaired confrontation naming is a common symptom of temporal lobe epilepsy (TLE). The neurobiological mechanisms underlying this impairment are poorly understood but may indicate a structural disorganization of broadly distributed neuronal networks that support naming ability. Importantly, naming is frequently impaired in other neurological disorders and by contrasting the neuronal structures supporting naming in TLE with other diseases, it will become possible to elucidate the common systems supporting naming. We aimed to evaluate the neuronal networks that support naming in TLE by using a machine learning algorithm intended to predict naming performance in subjects with medication refractory TLE using only the structural brain connectome reconstructed from diffusion tensor imaging. A connectome-based prediction framework was developed using network properties from anatomically defined brain regions across the entire brain, which were used in a multi-task machine learning algorithm followed by support vector regression. Nodal eigenvector centrality, a measure of regional network integration, predicted approximately 60% of the variance in naming. The nodes with the highest regression weight were bilaterally distributed among perilimbic sub-networks involving mainly the medial and lateral temporal lobe regions. In the context of emerging evidence regarding the role of large structural networks that support language processing, our results suggest intact naming relies on the integration of sub-networks, as opposed to being dependent on isolated brain areas. In the case of TLE, these sub-networks may be disproportionately indicative naming processes that are dependent semantic integration from memory and lexical retrieval, as opposed to multi-modal perception or motor speech production. Copyright © 2017. Published by Elsevier Inc.

Prediction of protein tertiary structure from sequences using a very large back-propagation neural network

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

Liu, X.; Wilcox, G.L.

1993-12-31

We have implemented large scale back-propagation neural networks on a 544 node Connection Machine, CM-5, using the C language in MIMD mode. The program running on 512 processors performs backpropagation learning at 0.53 Gflops, which provides 76 million connection updates per second. We have applied the network to the prediction of protein tertiary structure from sequence information alone. A neural network with one hidden layer and 40 million connections is trained to learn the relationship between sequence and tertiary structure. The trained network yields predicted structures of some proteins on which it has not been trained given only their sequences.more » Presentation of the Fourier transform of the sequences accentuates periodicity in the sequence and yields good generalization with greatly increased training efficiency. Training simulations with a large, heterologous set of protein structures (111 proteins from CM-5 time) to solutions with under 2% RMS residual error within the training set (random responses give an RMS error of about 20%). Presentation of 15 sequences of related proteins in a testing set of 24 proteins yields predicted structures with less than 8% RMS residual error, indicating good apparent generalization.« less

Biologically Inspired SNN for Robot Control.

PubMed

Nichols, Eric; McDaid, Liam J; Siddique, Nazmul

2013-02-01

This paper proposes a spiking-neural-network-based robot controller inspired by the control structures of biological systems. Information is routed through the network using facilitating dynamic synapses with short-term plasticity. Learning occurs through long-term synaptic plasticity which is implemented using the temporal difference learning rule to enable the robot to learn to associate the correct movement with the appropriate input conditions. The network self-organizes to provide memories of environments that the robot encounters. A Pioneer robot simulator with laser and sonar proximity sensors is used to verify the performance of the network with a wall-following task, and the results are presented.

Equilibria of perceptrons for simple contingency problems.

PubMed

Dawson, Michael R W; Dupuis, Brian

2012-08-01

The contingency between cues and outcomes is fundamentally important to theories of causal reasoning and to theories of associative learning. Researchers have computed the equilibria of Rescorla-Wagner models for a variety of contingency problems, and have used these equilibria to identify situations in which the Rescorla-Wagner model is consistent, or inconsistent, with normative models of contingency. Mathematical analyses that directly compare artificial neural networks to contingency theory have not been performed, because of the assumed equivalence between the Rescorla-Wagner learning rule and the delta rule training of artificial neural networks. However, recent results indicate that this equivalence is not as straightforward as typically assumed, suggesting a strong need for mathematical accounts of how networks deal with contingency problems. One such analysis is presented here, where it is proven that the structure of the equilibrium for a simple network trained on a basic contingency problem is quite different from the structure of the equilibrium for a Rescorla-Wagner model faced with the same problem. However, these structural differences lead to functionally equivalent behavior. The implications of this result for the relationships between associative learning, contingency theory, and connectionism are discussed.

Holography as deep learning

NASA Astrophysics Data System (ADS)

Gan, Wen-Cong; Shu, Fu-Wen

Quantum many-body problem with exponentially large degrees of freedom can be reduced to a tractable computational form by neural network method [G. Carleo and M. Troyer, Science 355 (2017) 602, arXiv:1606.02318.] The power of deep neural network (DNN) based on deep learning is clarified by mapping it to renormalization group (RG), which may shed lights on holographic principle by identifying a sequence of RG transformations to the AdS geometry. In this paper, we show that any network which reflects RG process has intrinsic hyperbolic geometry, and discuss the structure of entanglement encoded in the graph of DNN. We find the entanglement structure of DNN is of Ryu-Takayanagi form. Based on these facts, we argue that the emergence of holographic gravitational theory is related to deep learning process of the quantum-field theory.

Frontostriatal anatomical connections predict age- and difficulty-related differences in reinforcement learning.

PubMed

van de Vijver, Irene; Ridderinkhof, K Richard; Harsay, Helga; Reneman, Liesbeth; Cavanagh, James F; Buitenweg, Jessika I V; Cohen, Michael X

2016-10-01

Reinforcement learning (RL) is supported by a network of striatal and frontal cortical structures that are connected through white-matter fiber bundles. With age, the integrity of these white-matter connections declines. The role of structural frontostriatal connectivity in individual and age-related differences in RL is unclear, although local white-matter density and diffusivity have been linked to individual differences in RL. Here we show that frontostriatal tract counts in young human adults (aged 18-28), as assessed noninvasively with diffusion-weighted magnetic resonance imaging and probabilistic tractography, positively predicted individual differences in RL when learning was difficult (70% valid feedback). In older adults (aged 63-87), in contrast, learning under both easy (90% valid feedback) and difficult conditions was predicted by tract counts in the same frontostriatal network. Furthermore, network-level analyses showed a double dissociation between the task-relevant networks in young and older adults, suggesting that older adults relied on different frontostriatal networks than young adults to obtain the same task performance. These results highlight the importance of successful information integration across striatal and frontal regions during RL, especially with variable outcomes. Copyright © 2016 Elsevier Inc. All rights reserved.

Energy consumption analysis for various memristive networks under different learning strategies

NASA Astrophysics Data System (ADS)

Deng, Lei; Wang, Dong; Zhang, Ziyang; Tang, Pei; Li, Guoqi; Pei, Jing

2016-02-01

Recently, various memristive systems emerge to emulate the efficient computing paradigm of the brain cortex; whereas, how to make them energy efficient still remains unclear, especially from an overall perspective. Here, a systematical and bottom-up energy consumption analysis is demonstrated, including the memristor device level and the network learning level. We propose an energy estimating methodology when modulating the memristive synapses, which is simulated in three typical neural networks with different synaptic structures and learning strategies for both offline and online learning. These results provide an in-depth insight to create energy efficient brain-inspired neuromorphic devices in the future.

DCS-Neural-Network Program for Aircraft Control and Testing

NASA Technical Reports Server (NTRS)

Jorgensen, Charles C.

2006-01-01

A computer program implements a dynamic-cell-structure (DCS) artificial neural network that can perform such tasks as learning selected aerodynamic characteristics of an airplane from wind-tunnel test data and computing real-time stability and control derivatives of the airplane for use in feedback linearized control. A DCS neural network is one of several types of neural networks that can incorporate additional nodes in order to rapidly learn increasingly complex relationships between inputs and outputs. In the DCS neural network implemented by the present program, the insertion of nodes is based on accumulated error. A competitive Hebbian learning rule (a supervised-learning rule in which connection weights are adjusted to minimize differences between actual and desired outputs for training examples) is used. A Kohonen-style learning rule (derived from a relatively simple training algorithm, implements a Delaunay triangulation layout of neurons) is used to adjust node positions during training. Neighborhood topology determines which nodes are used to estimate new values. The network learns, starting with two nodes, and adds new nodes sequentially in locations chosen to maximize reductions in global error. At any given time during learning, the error becomes homogeneously distributed over all nodes.

SUSTAIN: A Network Model of Category Learning

ERIC Educational Resources Information Center

Love, Bradley C.; Medin, Douglas L.; Gureckis, Todd M.

2004-01-01

SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a model of how humans learn categories from examples. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g., it is told that a bat is a mammal instead of a bird), SUSTAIN…

GA-based fuzzy reinforcement learning for control of a magnetic bearing system.

PubMed

Lin, C T; Jou, C P

2000-01-01

This paper proposes a TD (temporal difference) and GA (genetic algorithm)-based reinforcement (TDGAR) learning method and applies it to the control of a real magnetic bearing system. The TDGAR learning scheme is a new hybrid GA, which integrates the TD prediction method and the GA to perform the reinforcement learning task. The TDGAR learning system is composed of two integrated feedforward networks. One neural network acts as a critic network to guide the learning of the other network (the action network) which determines the outputs (actions) of the TDGAR learning system. The action network can be a normal neural network or a neural fuzzy network. Using the TD prediction method, the critic network can predict the external reinforcement signal and provide a more informative internal reinforcement signal to the action network. The action network uses the GA to adapt itself according to the internal reinforcement signal. The key concept of the TDGAR learning scheme is to formulate the internal reinforcement signal as the fitness function for the GA such that the GA can evaluate the candidate solutions (chromosomes) regularly, even during periods without external feedback from the environment. This enables the GA to proceed to new generations regularly without waiting for the arrival of the external reinforcement signal. This can usually accelerate the GA learning since a reinforcement signal may only be available at a time long after a sequence of actions has occurred in the reinforcement learning problem. The proposed TDGAR learning system has been used to control an active magnetic bearing (AMB) system in practice. A systematic design procedure is developed to achieve successful integration of all the subsystems including magnetic suspension, mechanical structure, and controller training. The results show that the TDGAR learning scheme can successfully find a neural controller or a neural fuzzy controller for a self-designed magnetic bearing system.

Impact of censoring on learning Bayesian networks in survival modelling.

PubMed

Stajduhar, Ivan; Dalbelo-Basić, Bojana; Bogunović, Nikola

2009-11-01

Bayesian networks are commonly used for presenting uncertainty and covariate interactions in an easily interpretable way. Because of their efficient inference and ability to represent causal relationships, they are an excellent choice for medical decision support systems in diagnosis, treatment, and prognosis. Although good procedures for learning Bayesian networks from data have been defined, their performance in learning from censored survival data has not been widely studied. In this paper, we explore how to use these procedures to learn about possible interactions between prognostic factors and their influence on the variate of interest. We study how censoring affects the probability of learning correct Bayesian network structures. Additionally, we analyse the potential usefulness of the learnt models for predicting the time-independent probability of an event of interest. We analysed the influence of censoring with a simulation on synthetic data sampled from randomly generated Bayesian networks. We used two well-known methods for learning Bayesian networks from data: a constraint-based method and a score-based method. We compared the performance of each method under different levels of censoring to those of the naive Bayes classifier and the proportional hazards model. We did additional experiments on several datasets from real-world medical domains. The machine-learning methods treated censored cases in the data as event-free. We report and compare results for several commonly used model evaluation metrics. On average, the proportional hazards method outperformed other methods in most censoring setups. As part of the simulation study, we also analysed structural similarities of the learnt networks. Heavy censoring, as opposed to no censoring, produces up to a 5% surplus and up to 10% missing total arcs. It also produces up to 50% missing arcs that should originally be connected to the variate of interest. Presented methods for learning Bayesian networks from data can be used to learn from censored survival data in the presence of light censoring (up to 20%) by treating censored cases as event-free. Given intermediate or heavy censoring, the learnt models become tuned to the majority class and would thus require a different approach.

Neural constraints on learning.

PubMed

Sadtler, Patrick T; Quick, Kristin M; Golub, Matthew D; Chase, Steven M; Ryu, Stephen I; Tyler-Kabara, Elizabeth C; Yu, Byron M; Batista, Aaron P

2014-08-28

Learning, whether motor, sensory or cognitive, requires networks of neurons to generate new activity patterns. As some behaviours are easier to learn than others, we asked if some neural activity patterns are easier to generate than others. Here we investigate whether an existing network constrains the patterns that a subset of its neurons is capable of exhibiting, and if so, what principles define this constraint. We employed a closed-loop intracortical brain-computer interface learning paradigm in which Rhesus macaques (Macaca mulatta) controlled a computer cursor by modulating neural activity patterns in the primary motor cortex. Using the brain-computer interface paradigm, we could specify and alter how neural activity mapped to cursor velocity. At the start of each session, we observed the characteristic activity patterns of the recorded neural population. The activity of a neural population can be represented in a high-dimensional space (termed the neural space), wherein each dimension corresponds to the activity of one neuron. These characteristic activity patterns comprise a low-dimensional subspace (termed the intrinsic manifold) within the neural space. The intrinsic manifold presumably reflects constraints imposed by the underlying neural circuitry. Here we show that the animals could readily learn to proficiently control the cursor using neural activity patterns that were within the intrinsic manifold. However, animals were less able to learn to proficiently control the cursor using activity patterns that were outside of the intrinsic manifold. These results suggest that the existing structure of a network can shape learning. On a timescale of hours, it seems to be difficult to learn to generate neural activity patterns that are not consistent with the existing network structure. These findings offer a network-level explanation for the observation that we are more readily able to learn new skills when they are related to the skills that we already possess.

Developing Generic Image Search Strategies for Large Astronomical Data Sets and Archives using Convolutional Neural Networks and Transfer Learning

NASA Astrophysics Data System (ADS)

Peek, Joshua E. G.; Hargis, Jonathan R.; Jones, Craig K.

2018-01-01

Astronomical instruments produce petabytes of images every year, vastly more than can be inspected by a member of the astronomical community in search of a specific population of structures. Fortunately, the sky is mostly black and source extraction algorithms have been developed to provide searchable catalogs of unconfused sources like stars and galaxies. These tools often fail for studies of more diffuse structures like the interstellar medium and unresolved stellar structures in nearby galaxies, leaving astronomers interested in observations of photodissociation regions, stellar clusters, diffuse interstellar clouds without the crucial ability to search. In this work we present a new path forward for finding structures in large data sets similar to an input structure using convolutional neural networks, transfer learning, and machine learning clustering techniques. We show applications to archival data in the Mikulski Archive for Space Telescopes (MAST).

Synchronization in a noise-driven developing neural network

NASA Astrophysics Data System (ADS)

Lin, I.-H.; Wu, R.-K.; Chen, C.-M.

2011-11-01

We use computer simulations to investigate the structural and dynamical properties of a developing neural network whose activity is driven by noise. Structurally, the constructed neural networks in our simulations exhibit the small-world properties that have been observed in several neural networks. The dynamical change of neuronal membrane potential is described by the Hodgkin-Huxley model, and two types of learning rules, including spike-timing-dependent plasticity (STDP) and inverse STDP, are considered to restructure the synaptic strength between neurons. Clustered synchronized firing (SF) of the network is observed when the network connectivity (number of connections/maximal connections) is about 0.75, in which the firing rate of neurons is only half of the network frequency. At the connectivity of 0.86, all neurons fire synchronously at the network frequency. The network SF frequency increases logarithmically with the culturing time of a growing network and decreases exponentially with the delay time in signal transmission. These conclusions are consistent with experimental observations. The phase diagrams of SF in a developing network are investigated for both learning rules.

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.

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.

Application of dynamic recurrent neural networks in nonlinear system identification

NASA Astrophysics Data System (ADS)

Du, Yun; Wu, Xueli; Sun, Huiqin; Zhang, Suying; Tian, Qiang

2006-11-01

An adaptive identification method of simple dynamic recurrent neural network (SRNN) for nonlinear dynamic systems is presented in this paper. This method based on the theory that by using the inner-states feed-back of dynamic network to describe the nonlinear kinetic characteristics of system can reflect the dynamic characteristics more directly, deduces the recursive prediction error (RPE) learning algorithm of SRNN, and improves the algorithm by studying topological structure on recursion layer without the weight values. The simulation results indicate that this kind of neural network can be used in real-time control, due to its less weight values, simpler learning algorithm, higher identification speed, and higher precision of model. It solves the problems of intricate in training algorithm and slow rate in convergence caused by the complicate topological structure in usual dynamic recurrent neural network.

A Deep Neural Network Model for Rainfall Estimation UsingPolarimetric WSR-88DP Radar Observations

NASA Astrophysics Data System (ADS)

Tan, H.; Chandra, C. V.; Chen, H.

2016-12-01

Rainfall estimation based on radar measurements has been an important topic for a few decades. Generally, radar rainfall estimation is conducted through parametric algorisms such as reflectivity-rainfall relation (i.e., Z-R relation). On the other hand, neural networks are developed for ground rainfall estimation based on radar measurements. This nonparametric method, which takes into account of both radar observations and rainfall measurements from ground rain gauges, has been demonstrated successfully for rainfall rate estimation. However, the neural network-based rainfall estimation is limited in practice due to the model complexity and structure, data quality, as well as different rainfall microphysics. Recently, the deep learning approach has been introduced in pattern recognition and machine learning areas. Compared to traditional neural networks, the deep learning based methodologies have larger number of hidden layers and more complex structure for data representation. Through a hierarchical learning process, the high level structured information and knowledge can be extracted automatically from low level features of the data. In this paper, we introduce a novel deep neural network model for rainfall estimation based on ground polarimetric radar measurements .The model is designed to capture the complex abstractions of radar measurements at different levels using multiple layers feature identification and extraction. The abstractions at different levels can be used independently or fused with other data resource such as satellite-based rainfall products and/or topographic data to represent the rain characteristics at certain location. In particular, the WSR-88DP radar and rain gauge data collected in Dallas - Fort Worth Metroplex and Florida are used extensively to train the model, and for demonstration purposes. Quantitative evaluation of the deep neural network based rainfall products will also be presented, which is based on an independent rain gauge network.

A new similarity measure for link prediction based on local structures in social networks

NASA Astrophysics Data System (ADS)

Aghabozorgi, Farshad; Khayyambashi, Mohammad Reza

2018-07-01

Link prediction is a fundamental problem in social network analysis. There exist a variety of techniques for link prediction which applies the similarity measures to estimate proximity of vertices in the network. Complex networks like social networks contain structural units named network motifs. In this study, a newly developed similarity measure is proposed where these structural units are applied as the source of similarity estimation. This similarity measure is tested through a supervised learning experiment framework, where other similarity measures are compared with this similarity measure. The classification model trained with this similarity measure outperforms others of its kind.

A review of active learning approaches to experimental design for uncovering biological networks

PubMed Central

2017-01-01

Various types of biological knowledge describe networks of interactions among elementary entities. For example, transcriptional regulatory networks consist of interactions among proteins and genes. Current knowledge about the exact structure of such networks is highly incomplete, and laboratory experiments that manipulate the entities involved are conducted to test hypotheses about these networks. In recent years, various automated approaches to experiment selection have been proposed. Many of these approaches can be characterized as active machine learning algorithms. Active learning is an iterative process in which a model is learned from data, hypotheses are generated from the model to propose informative experiments, and the experiments yield new data that is used to update the model. This review describes the various models, experiment selection strategies, validation techniques, and successful applications described in the literature; highlights common themes and notable distinctions among methods; and identifies likely directions of future research and open problems in the area. PMID:28570593

Neurocomputing

NASA Technical Reports Server (NTRS)

Hecht-Nielsen, Robert

1990-01-01

The present work is intended to give technologists, research scientists, and mathematicians a graduate-level overview of the field of neurocomputing. After exploring the relationship of this field to general neuroscience, attention is given to neural network building blocks, the self-adaptation equations of learning laws, the data-transformation structures of associative networks, and the multilayer data-transformation structures of mapping networks. Also treated are the neurocomputing frontiers of spatiotemporal, stochastic, and hierarchical networks, 'neurosoftware', the creation of neural network-based computers, and neurocomputing applications in sensor processing, control, and data analysis.

Adaptive neural network/expert system that learns fault diagnosis for different structures

NASA Astrophysics Data System (ADS)

Simon, Solomon H.

1992-08-01

Corporations need better real-time monitoring and control systems to improve productivity by watching quality and increasing production flexibility. The innovative technology to achieve this goal is evolving in the form artificial intelligence and neural networks applied to sensor processing, fusion, and interpretation. By using these advanced Al techniques, we can leverage existing systems and add value to conventional techniques. Neural networks and knowledge-based expert systems can be combined into intelligent sensor systems which provide real-time monitoring, control, evaluation, and fault diagnosis for production systems. Neural network-based intelligent sensor systems are more reliable because they can provide continuous, non-destructive monitoring and inspection. Use of neural networks can result in sensor fusion and the ability to model highly, non-linear systems. Improved models can provide a foundation for more accurate performance parameters and predictions. We discuss a research software/hardware prototype which integrates neural networks, expert systems, and sensor technologies and which can adapt across a variety of structures to perform fault diagnosis. The flexibility and adaptability of the prototype in learning two structures is presented. Potential applications are discussed.

Order priors for Bayesian network discovery with an application to malware phylogeny

DOE PAGES

Oyen, Diane; Anderson, Blake; Sentz, Kari; ...

2017-09-15

Here, Bayesian networks have been used extensively to model and discover dependency relationships among sets of random variables. We learn Bayesian network structure with a combination of human knowledge about the partial ordering of variables and statistical inference of conditional dependencies from observed data. Our approach leverages complementary information from human knowledge and inference from observed data to produce networks that reflect human beliefs about the system as well as to fit the observed data. Applying prior beliefs about partial orderings of variables is an approach distinctly different from existing methods that incorporate prior beliefs about direct dependencies (or edges)more » in a Bayesian network. We provide an efficient implementation of the partial-order prior in a Bayesian structure discovery learning algorithm, as well as an edge prior, showing that both priors meet the local modularity requirement necessary for an efficient Bayesian discovery algorithm. In benchmark studies, the partial-order prior improves the accuracy of Bayesian network structure learning as well as the edge prior, even though order priors are more general. Our primary motivation is in characterizing the evolution of families of malware to aid cyber security analysts. For the problem of malware phylogeny discovery, we find that our algorithm, compared to existing malware phylogeny algorithms, more accurately discovers true dependencies that are missed by other algorithms.« less

Order priors for Bayesian network discovery with an application to malware phylogeny

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

Oyen, Diane; Anderson, Blake; Sentz, Kari

Here, Bayesian networks have been used extensively to model and discover dependency relationships among sets of random variables. We learn Bayesian network structure with a combination of human knowledge about the partial ordering of variables and statistical inference of conditional dependencies from observed data. Our approach leverages complementary information from human knowledge and inference from observed data to produce networks that reflect human beliefs about the system as well as to fit the observed data. Applying prior beliefs about partial orderings of variables is an approach distinctly different from existing methods that incorporate prior beliefs about direct dependencies (or edges)more » in a Bayesian network. We provide an efficient implementation of the partial-order prior in a Bayesian structure discovery learning algorithm, as well as an edge prior, showing that both priors meet the local modularity requirement necessary for an efficient Bayesian discovery algorithm. In benchmark studies, the partial-order prior improves the accuracy of Bayesian network structure learning as well as the edge prior, even though order priors are more general. Our primary motivation is in characterizing the evolution of families of malware to aid cyber security analysts. For the problem of malware phylogeny discovery, we find that our algorithm, compared to existing malware phylogeny algorithms, more accurately discovers true dependencies that are missed by other algorithms.« less

A Co-Citation Network of Young Children's Learning with Technology

ERIC Educational Resources Information Center

Tang, Kai-Yu; Li, Ming-Chaun; Hsin, Ching-Ting; Tsai, Chin-Chung

2016-01-01

This paper used a novel literature review approach--co-citation network analysis--to illuminate the latent structure of 87 empirical papers in the field of young children's learning with technology (YCLT). Based on the document co-citation analysis, a total of 206 co-citation relationships among the 87 papers were identified and then graphically…

Modeling a Neural Network as a Teaching Tool for the Learning of the Structure-Function Relationship

ERIC Educational Resources Information Center

Salinas, Dino G.; Acevedo, Cristian; Gomez, Christian R.

2010-01-01

The authors describe an activity they have created in which students can visualize a theoretical neural network whose states evolve according to a well-known simple law. This activity provided an uncomplicated approach to a paradigm commonly represented through complex mathematical formulation. From their observations, students learned many basic…

Are Student Evaluations of Teaching Effectiveness Valid for Measuring Student Learning Outcomes in Business Related Classes? A Neural Network and Bayesian Analyses

ERIC Educational Resources Information Center

Galbraith, Craig S.; Merrill, Gregory B.; Kline, Doug M.

2012-01-01

In this study we investigate the underlying relational structure between student evaluations of teaching effectiveness (SETEs) and achievement of student learning outcomes in 116 business related courses. Utilizing traditional statistical techniques, a neural network analysis and a Bayesian data reduction and classification algorithm, we find…

A Learning Framework for Winner-Take-All Networks with Stochastic Synapses.

PubMed

Mostafa, Hesham; Cauwenberghs, Gert

2018-06-01

Many recent generative models make use of neural networks to transform the probability distribution of a simple low-dimensional noise process into the complex distribution of the data. This raises the question of whether biological networks operate along similar principles to implement a probabilistic model of the environment through transformations of intrinsic noise processes. The intrinsic neural and synaptic noise processes in biological networks, however, are quite different from the noise processes used in current abstract generative networks. This, together with the discrete nature of spikes and local circuit interactions among the neurons, raises several difficulties when using recent generative modeling frameworks to train biologically motivated models. In this letter, we show that a biologically motivated model based on multilayer winner-take-all circuits and stochastic synapses admits an approximate analytical description. This allows us to use the proposed networks in a variational learning setting where stochastic backpropagation is used to optimize a lower bound on the data log likelihood, thereby learning a generative model of the data. We illustrate the generality of the proposed networks and learning technique by using them in a structured output prediction task and a semisupervised learning task. Our results extend the domain of application of modern stochastic network architectures to networks where synaptic transmission failure is the principal noise mechanism.

Effect of dilution in asymmetric recurrent neural networks.

PubMed

Folli, Viola; Gosti, Giorgio; Leonetti, Marco; Ruocco, Giancarlo

2018-04-16

We study with numerical simulation the possible limit behaviors of synchronous discrete-time deterministic recurrent neural networks composed of N binary neurons as a function of a network's level of dilution and asymmetry. The network dilution measures the fraction of neuron couples that are connected, and the network asymmetry measures to what extent the underlying connectivity matrix is asymmetric. For each given neural network, we study the dynamical evolution of all the different initial conditions, thus characterizing the full dynamical landscape without imposing any learning rule. Because of the deterministic dynamics, each trajectory converges to an attractor, that can be either a fixed point or a limit cycle. These attractors form the set of all the possible limit behaviors of the neural network. For each network we then determine the convergence times, the limit cycles' length, the number of attractors, and the sizes of the attractors' basin. We show that there are two network structures that maximize the number of possible limit behaviors. The first optimal network structure is fully-connected and symmetric. On the contrary, the second optimal network structure is highly sparse and asymmetric. The latter optimal is similar to what observed in different biological neuronal circuits. These observations lead us to hypothesize that independently from any given learning model, an efficient and effective biologic network that stores a number of limit behaviors close to its maximum capacity tends to develop a connectivity structure similar to one of the optimal networks we found. Copyright © 2018 The Author(s). Published by Elsevier Ltd.. All rights reserved.

Functional brain networks for learning predictive statistics.

PubMed

Giorgio, Joseph; Karlaftis, Vasilis M; Wang, Rui; Shen, Yuan; Tino, Peter; Welchman, Andrew; Kourtzi, Zoe

2017-08-18

Making predictions about future events relies on interpreting streams of information that may initially appear incomprehensible. This skill relies on extracting regular patterns in space and time by mere exposure to the environment (i.e., without explicit feedback). Yet, we know little about the functional brain networks that mediate this type of statistical learning. Here, we test whether changes in the processing and connectivity of functional brain networks due to training relate to our ability to learn temporal regularities. By combining behavioral training and functional brain connectivity analysis, we demonstrate that individuals adapt to the environment's statistics as they change over time from simple repetition to probabilistic combinations. Further, we show that individual learning of temporal structures relates to decision strategy. Our fMRI results demonstrate that learning-dependent changes in fMRI activation within and functional connectivity between brain networks relate to individual variability in strategy. In particular, extracting the exact sequence statistics (i.e., matching) relates to changes in brain networks known to be involved in memory and stimulus-response associations, while selecting the most probable outcomes in a given context (i.e., maximizing) relates to changes in frontal and striatal networks. Thus, our findings provide evidence that dissociable brain networks mediate individual ability in learning behaviorally-relevant statistics. Copyright © 2017 The Authors. Published by Elsevier Ltd.. All rights reserved.

Anatomy and histology as socially networked learning environments: some preliminary findings.

PubMed

Hafferty, Frederic W; Castellani, Brian; Hafferty, Philip K; Pawlina, Wojciech

2013-09-01

An exploratory study to better understand the "networked" life of the medical school as a learning environment. In a recent academic year, the authors gathered data during two six-week blocks of a sequential histology and anatomy course at a U.S. medical college. An eight-item questionnaire captured different dimensions of student interactions. The student cohort/network was 48 first-year medical students. Using social network analysis (SNA), the authors focused on (1) the initial structure and the evolution of informal class networks over time, (2) how informal class networks compare to formal in-class small-group assignments in influencing student information gathering, and (3) how peer assignment of professionalism role model status is shaped more by informal than formal ties. In examining these latter two issues, the authors explored not only how formal group assignment persisted over time but also how it functioned to prevent the tendency for groupings based on gender or ethnicity. The study revealed an evolving dynamic between the formal small-group learning structure of the course blocks and the emergence of informal student networks. For example, whereas formal group membership did influence in-class questions and did prevent formation of groups of like gender and ethnicity, outside-class questions and professionalism were influenced more by informal group ties where gender and, to a much lesser extent, ethnicity influence student information gathering. The richness of these preliminary findings suggests that SNA may be a useful tool in examining an array of medical student learning encounters.

Evaluation of Deep Learning Representations of Spatial Storm Data

NASA Astrophysics Data System (ADS)

Gagne, D. J., II; Haupt, S. E.; Nychka, D. W.

2017-12-01

The spatial structure of a severe thunderstorm and its surrounding environment provide useful information about the potential for severe weather hazards, including tornadoes, hail, and high winds. Statistics computed over the area of a storm or from the pre-storm environment can provide descriptive information but fail to capture structural information. Because the storm environment is a complex, high-dimensional space, identifying methods to encode important spatial storm information in a low-dimensional form should aid analysis and prediction of storms by statistical and machine learning models. Principal component analysis (PCA), a more traditional approach, transforms high-dimensional data into a set of linearly uncorrelated, orthogonal components ordered by the amount of variance explained by each component. The burgeoning field of deep learning offers two potential approaches to this problem. Convolutional Neural Networks are a supervised learning method for transforming spatial data into a hierarchical set of feature maps that correspond with relevant combinations of spatial structures in the data. Generative Adversarial Networks (GANs) are an unsupervised deep learning model that uses two neural networks trained against each other to produce encoded representations of spatial data. These different spatial encoding methods were evaluated on the prediction of severe hail for a large set of storm patches extracted from the NCAR convection-allowing ensemble. Each storm patch contains information about storm structure and the near-storm environment. Logistic regression and random forest models were trained using the PCA and GAN encodings of the storm data and were compared against the predictions from a convolutional neural network. All methods showed skill over climatology at predicting the probability of severe hail. However, the verification scores among the methods were very similar and the predictions were highly correlated. Further evaluations are being performed to determine how the choice of input variables affects the results.

Self-organizing adaptive map: autonomous learning of curves and surfaces from point samples.

PubMed

Piastra, Marco

2013-05-01

Competitive Hebbian Learning (CHL) (Martinetz, 1993) is a simple and elegant method for estimating the topology of a manifold from point samples. The method has been adopted in a number of self-organizing networks described in the literature and has given rise to related studies in the fields of geometry and computational topology. Recent results from these fields have shown that a faithful reconstruction can be obtained using the CHL method only for curves and surfaces. Within these limitations, these findings constitute a basis for defining a CHL-based, growing self-organizing network that produces a faithful reconstruction of an input manifold. The SOAM (Self-Organizing Adaptive Map) algorithm adapts its local structure autonomously in such a way that it can match the features of the manifold being learned. The adaptation process is driven by the defects arising when the network structure is inadequate, which cause a growth in the density of units. Regions of the network undergo a phase transition and change their behavior whenever a simple, local condition of topological regularity is met. The phase transition is eventually completed across the entire structure and the adaptation process terminates. In specific conditions, the structure thus obtained is homeomorphic to the input manifold. During the adaptation process, the network also has the capability to focus on the acquisition of input point samples in critical regions, with a substantial increase in efficiency. The behavior of the network has been assessed experimentally with typical data sets for surface reconstruction, including suboptimal conditions, e.g. with undersampling and noise. Copyright © 2012 Elsevier Ltd. All rights reserved.

CA1 cell activity sequences emerge after reorganization of network correlation structure during associative learning

PubMed Central

Modi, Mehrab N; Dhawale, Ashesh K; Bhalla, Upinder S

2014-01-01

Animals can learn causal relationships between pairs of stimuli separated in time and this ability depends on the hippocampus. Such learning is believed to emerge from alterations in network connectivity, but large-scale connectivity is difficult to measure directly, especially during learning. Here, we show that area CA1 cells converge to time-locked firing sequences that bridge the two stimuli paired during training, and this phenomenon is coupled to a reorganization of network correlations. Using two-photon calcium imaging of mouse hippocampal neurons we find that co-time-tuned neurons exhibit enhanced spontaneous activity correlations that increase just prior to learning. While time-tuned cells are not spatially organized, spontaneously correlated cells do fall into distinct spatial clusters that change as a result of learning. We propose that the spatial re-organization of correlation clusters reflects global network connectivity changes that are responsible for the emergence of the sequentially-timed activity of cell-groups underlying the learned behavior. DOI: http://dx.doi.org/10.7554/eLife.01982.001 PMID:24668171

Deep learning for computational chemistry

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

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

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

Sparse dictionary learning of resting state fMRI networks.

PubMed

Eavani, Harini; Filipovych, Roman; Davatzikos, Christos; Satterthwaite, Theodore D; Gur, Raquel E; Gur, Ruben C

2012-07-02

Research in resting state fMRI (rsfMRI) has revealed the presence of stable, anti-correlated functional subnetworks in the brain. Task-positive networks are active during a cognitive process and are anti-correlated with task-negative networks, which are active during rest. In this paper, based on the assumption that the structure of the resting state functional brain connectivity is sparse, we utilize sparse dictionary modeling to identify distinct functional sub-networks. We propose two ways of formulating the sparse functional network learning problem that characterize the underlying functional connectivity from different perspectives. Our results show that the whole-brain functional connectivity can be concisely represented with highly modular, overlapping task-positive/negative pairs of sub-networks.

Facilitating the Development of School-Based Learning Networks

ERIC Educational Resources Information Center

Kubiak, Chris; Bertram, Joan

2010-01-01

Purpose: This paper aims to contribute to the knowledge base on leading and facilitating the growth of school improvement networks by describing the activities and challenges faced by network leaders. Design/methodology/approach: A total of 19 co-leaders from 12 networks were interviewed using a semi-structured schedule about the growth of their…

Can Learning Collaboratives Support Implementation by Rewiring Professional Networks?

PubMed

Bunger, Alicia C; Hanson, Rochelle F; Doogan, Nathan J; Powell, Byron J; Cao, Yiwen; Dunn, Jerry

2016-01-01

This study examined how a learning collaborative focusing on trauma-focused CBT (TF-CBT) impacted advice-seeking patterns between clinicians and three key learning sources: (1) training experts who share technical knowledge about TF-CBT, (2) peers from other participating organizations who share their implementation experiences, and (3) colleagues from their own agency who provide social and professional support. Based on surveys administered to 132 clinicians from 32 agencies, participants' professional networks changed slightly over time by forming new advice-seeking relationships with training experts. While small, these changes at the clinician-level yielded substantial changes in the structure of the regional advice network.

Can Learning Collaboratives Support Implementation By Rewiring Professional Networks?

PubMed Central

Hanson, Rochelle F.; Doogan, Nathan J.; Powell, Byron J.; Cao, Yiwen; Dunn, Jerry

2015-01-01

This study examined how a learning collaborative focusing on Trauma-Focused CBT (TF-CBT) impacted advice-seeking patterns between clinicians and three key learning sources: (1) training experts who share technical knowledge about TF-CBT, (2) peers from other participating organizations who share their implementation experiences, and (3) colleagues from their own agency who provide social and professional support. Based on surveys administered to 132 clinicians from 32 agencies, participants’ professional networks changed slightly over time by forming new advice-seeking relationships with training experts. While small, these changes at the clinician-level yielded substantial changes in the structure of the regional advice network. PMID:25542237

Structural network heterogeneities and network dynamics: a possible dynamical mechanism for hippocampal memory reactivation.

NASA Astrophysics Data System (ADS)

Jablonski, Piotr; Poe, Gina; Zochowski, Michal

2007-03-01

The hippocampus has the capacity for reactivating recently acquired memories and it is hypothesized that one of the functions of sleep reactivation is the facilitation of consolidation of novel memory traces. The dynamic and network processes underlying such a reactivation remain, however, unknown. We show that such a reactivation characterized by local, self-sustained activity of a network region may be an inherent property of the recurrent excitatory-inhibitory network with a heterogeneous structure. The entry into the reactivation phase is mediated through a physiologically feasible regulation of global excitability and external input sources, while the reactivated component of the network is formed through induced network heterogeneities during learning. We show that structural changes needed for robust reactivation of a given network region are well within known physiological parameters.

Structural network heterogeneities and network dynamics: A possible dynamical mechanism for hippocampal memory reactivation

NASA Astrophysics Data System (ADS)

Jablonski, Piotr; Poe, Gina R.; Zochowski, Michal

2007-01-01

The hippocampus has the capacity for reactivating recently acquired memories and it is hypothesized that one of the functions of sleep reactivation is the facilitation of consolidation of novel memory traces. The dynamic and network processes underlying such a reactivation remain, however, unknown. We show that such a reactivation characterized by local, self-sustained activity of a network region may be an inherent property of the recurrent excitatory-inhibitory network with a heterogeneous structure. The entry into the reactivation phase is mediated through a physiologically feasible regulation of global excitability and external input sources, while the reactivated component of the network is formed through induced network heterogeneities during learning. We show that structural changes needed for robust reactivation of a given network region are well within known physiological parameters.

Expert networks in CLIPS

NASA Technical Reports Server (NTRS)

Hruska, S. I.; Dalke, A.; Ferguson, J. J.; Lacher, R. C.

1991-01-01

Rule-based expert systems may be structurally and functionally mapped onto a special class of neural networks called expert networks. This mapping lends itself to adaptation of connectionist learning strategies for the expert networks. A parsing algorithm to translate C Language Integrated Production System (CLIPS) rules into a network of interconnected assertion and operation nodes has been developed. The translation of CLIPS rules to an expert network and back again is illustrated. Measures of uncertainty similar to those rules in MYCIN-like systems are introduced into the CLIPS system and techniques for combining and hiring nodes in the network based on rule-firing with these certainty factors in the expert system are presented. Several learning algorithms are under study which automate the process of attaching certainty factors to rules.

Discussion Tool Effects on Collaborative Learning and Social Network Structure

ERIC Educational Resources Information Center

Tomsic, Astrid; Suthers, Daniel D.

2006-01-01

This study investigated the social network structure of booking officers at the Honolulu Police Department and how the introduction of an online discussion tool affected knowledge about operation of a booking module. Baseline data provided evidence for collaboration among officers in the same district using e-mail, telephone and face-to-face media…

Reconstruction of three-dimensional porous media using generative adversarial neural networks

NASA Astrophysics Data System (ADS)

Mosser, Lukas; Dubrule, Olivier; Blunt, Martin J.

2017-10-01

To evaluate the variability of multiphase flow properties of porous media at the pore scale, it is necessary to acquire a number of representative samples of the void-solid structure. While modern x-ray computer tomography has made it possible to extract three-dimensional images of the pore space, assessment of the variability in the inherent material properties is often experimentally not feasible. We present a method to reconstruct the solid-void structure of porous media by applying a generative neural network that allows an implicit description of the probability distribution represented by three-dimensional image data sets. We show, by using an adversarial learning approach for neural networks, that this method of unsupervised learning is able to generate representative samples of porous media that honor their statistics. We successfully compare measures of pore morphology, such as the Euler characteristic, two-point statistics, and directional single-phase permeability of synthetic realizations with the calculated properties of a bead pack, Berea sandstone, and Ketton limestone. Results show that generative adversarial networks can be used to reconstruct high-resolution three-dimensional images of porous media at different scales that are representative of the morphology of the images used to train the neural network. The fully convolutional nature of the trained neural network allows the generation of large samples while maintaining computational efficiency. Compared to classical stochastic methods of image reconstruction, the implicit representation of the learned data distribution can be stored and reused to generate multiple realizations of the pore structure very rapidly.

Neural model of gene regulatory network: a survey on supportive meta-heuristics.

PubMed

Biswas, Surama; Acharyya, Sriyankar

2016-06-01

Gene regulatory network (GRN) is produced as a result of regulatory interactions between different genes through their coded proteins in cellular context. Having immense importance in disease detection and drug finding, GRN has been modelled through various mathematical and computational schemes and reported in survey articles. Neural and neuro-fuzzy models have been the focus of attraction in bioinformatics. Predominant use of meta-heuristic algorithms in training neural models has proved its excellence. Considering these facts, this paper is organized to survey neural modelling schemes of GRN and the efficacy of meta-heuristic algorithms towards parameter learning (i.e. weighting connections) within the model. This survey paper renders two different structure-related approaches to infer GRN which are global structure approach and substructure approach. It also describes two neural modelling schemes, such as artificial neural network/recurrent neural network based modelling and neuro-fuzzy modelling. The meta-heuristic algorithms applied so far to learn the structure and parameters of neutrally modelled GRN have been reviewed here.

Deinterlacing using modular neural network

NASA Astrophysics Data System (ADS)

Woo, Dong H.; Eom, Il K.; Kim, Yoo S.

2004-05-01

Deinterlacing is the conversion process from the interlaced scan to progressive one. While many previous algorithms that are based on weighted-sum cause blurring in edge region, deinterlacing using neural network can reduce the blurring through recovering of high frequency component by learning process, and is found robust to noise. In proposed algorithm, input image is divided into edge and smooth region, and then, to each region, one neural network is assigned. Through this process, each neural network learns only patterns that are similar, therefore it makes learning more effective and estimation more accurate. But even within each region, there are various patterns such as long edge and texture in edge region. To solve this problem, modular neural network is proposed. In proposed modular neural network, two modules are combined in output node. One is for low frequency feature of local area of input image, and the other is for high frequency feature. With this structure, each modular neural network can learn different patterns with compensating for drawback of counterpart. Therefore it can adapt to various patterns within each region effectively. In simulation, the proposed algorithm shows better performance compared with conventional deinterlacing methods and single neural network method.

A recurrent self-organizing neural fuzzy inference network.

PubMed

Juang, C F; Lin, C T

1999-01-01

A recurrent self-organizing neural fuzzy inference network (RSONFIN) is proposed in this paper. The RSONFIN is inherently a recurrent multilayered connectionist network for realizing the basic elements and functions of dynamic fuzzy inference, and may be considered to be constructed from a series of dynamic fuzzy rules. The temporal relations embedded in the network are built by adding some feedback connections representing the memory elements to a feedforward neural fuzzy network. Each weight as well as node in the RSONFIN has its own meaning and represents a special element in a fuzzy rule. There are no hidden nodes (i.e., no membership functions and fuzzy rules) initially in the RSONFIN. They are created on-line via concurrent structure identification (the construction of dynamic fuzzy if-then rules) and parameter identification (the tuning of the free parameters of membership functions). The structure learning together with the parameter learning forms a fast learning algorithm for building a small, yet powerful, dynamic neural fuzzy network. Two major characteristics of the RSONFIN can thus be seen: 1) the recurrent property of the RSONFIN makes it suitable for dealing with temporal problems and 2) no predetermination, like the number of hidden nodes, must be given, since the RSONFIN can find its optimal structure and parameters automatically and quickly. Moreover, to reduce the number of fuzzy rules generated, a flexible input partition method, the aligned clustering-based algorithm, is proposed. Various simulations on temporal problems are done and performance comparisons with some existing recurrent networks are also made. Efficiency of the RSONFIN is verified from these results.

On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks

PubMed Central

Tonelli, Paul; Mouret, Jean-Baptiste

2013-01-01

A major goal of bio-inspired artificial intelligence is to design artificial neural networks with abilities that resemble those of animal nervous systems. It is commonly believed that two keys for evolving nature-like artificial neural networks are (1) the developmental process that links genes to nervous systems, which enables the evolution of large, regular neural networks, and (2) synaptic plasticity, which allows neural networks to change during their lifetime. So far, these two topics have been mainly studied separately. The present paper shows that they are actually deeply connected. Using a simple operant conditioning task and a classic evolutionary algorithm, we compare three ways to encode plastic neural networks: a direct encoding, a developmental encoding inspired by computational neuroscience models, and a developmental encoding inspired by morphogen gradients (similar to HyperNEAT). Our results suggest that using a developmental encoding could improve the learning abilities of evolved, plastic neural networks. Complementary experiments reveal that this result is likely the consequence of the bias of developmental encodings towards regular structures: (1) in our experimental setup, encodings that tend to produce more regular networks yield networks with better general learning abilities; (2) whatever the encoding is, networks that are the more regular are statistically those that have the best learning abilities. PMID:24236099

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

NASA Astrophysics Data System (ADS)

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

2018-03-01

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

Three learning phases for radial-basis-function networks.

PubMed

Schwenker, F; Kestler, H A; Palm, G

2001-05-01

In this paper, learning algorithms for radial basis function (RBF) networks are discussed. Whereas multilayer perceptrons (MLP) are typically trained with backpropagation algorithms, starting the training procedure with a random initialization of the MLP's parameters, an RBF network may be trained in many different ways. We categorize these RBF training methods into one-, two-, and three-phase learning schemes. Two-phase RBF learning is a very common learning scheme. The two layers of an RBF network are learnt separately; first the RBF layer is trained, including the adaptation of centers and scaling parameters, and then the weights of the output layer are adapted. RBF centers may be trained by clustering, vector quantization and classification tree algorithms, and the output layer by supervised learning (through gradient descent or pseudo inverse solution). Results from numerical experiments of RBF classifiers trained by two-phase learning are presented in three completely different pattern recognition applications: (a) the classification of 3D visual objects; (b) the recognition hand-written digits (2D objects); and (c) the categorization of high-resolution electrocardiograms given as a time series (ID objects) and as a set of features extracted from these time series. In these applications, it can be observed that the performance of RBF classifiers trained with two-phase learning can be improved through a third backpropagation-like training phase of the RBF network, adapting the whole set of parameters (RBF centers, scaling parameters, and output layer weights) simultaneously. This, we call three-phase learning in RBF networks. A practical advantage of two- and three-phase learning in RBF networks is the possibility to use unlabeled training data for the first training phase. Support vector (SV) learning in RBF networks is a different learning approach. SV learning can be considered, in this context of learning, as a special type of one-phase learning, where only the output layer weights of the RBF network are calculated, and the RBF centers are restricted to be a subset of the training data. Numerical experiments with several classifier schemes including k-nearest-neighbor, learning vector quantization and RBF classifiers trained through two-phase, three-phase and support vector learning are given. The performance of the RBF classifiers trained through SV learning and three-phase learning are superior to the results of two-phase learning, but SV learning often leads to complex network structures, since the number of support vectors is not a small fraction of the total number of data points.

A Worldwide Intercultural Network: Exploring Electronic Messaging for Instruction.

ERIC Educational Resources Information Center

Cohen, Moshe; Miyake, Naomi

1986-01-01

Discusses the Intercultural Learning Network, an international computer network designed to enable students from different cultures to work with one another. Questions addressed include whether it is technically possible, economically feasible, and useful for instructional purposes; what organizational structures are required; and whether it can…

Markov models for fMRI correlation structure: Is brain functional connectivity small world, or decomposable into networks?

PubMed

Varoquaux, G; Gramfort, A; Poline, J B; Thirion, B

2012-01-01

Correlations in the signal observed via functional Magnetic Resonance Imaging (fMRI), are expected to reveal the interactions in the underlying neural populations through hemodynamic response. In particular, they highlight distributed set of mutually correlated regions that correspond to brain networks related to different cognitive functions. Yet graph-theoretical studies of neural connections give a different picture: that of a highly integrated system with small-world properties: local clustering but with short pathways across the complete structure. We examine the conditional independence properties of the fMRI signal, i.e. its Markov structure, to find realistic assumptions on the connectivity structure that are required to explain the observed functional connectivity. In particular we seek a decomposition of the Markov structure into segregated functional networks using decomposable graphs: a set of strongly-connected and partially overlapping cliques. We introduce a new method to efficiently extract such cliques on a large, strongly-connected graph. We compare methods learning different graph structures from functional connectivity by testing the goodness of fit of the model they learn on new data. We find that summarizing the structure as strongly-connected networks can give a good description only for very large and overlapping networks. These results highlight that Markov models are good tools to identify the structure of brain connectivity from fMRI signals, but for this purpose they must reflect the small-world properties of the underlying neural systems. Copyright © 2012 Elsevier Ltd. All rights reserved.

Closer to Learning: Social Networks, Trust, and Professional Communities

ERIC Educational Resources Information Center

Liou, Yi-Hwa; Daly, Alan J.

2014-01-01

Researchers, educators, and policymakers suggest the use of professional learning communities as one important approach to the improvement of teaching and learning. However, relatively little research examines the interplay of professional interactions (structural social capital) around instructional practices and key elements of professional…

A graph-based evolutionary algorithm: Genetic Network Programming (GNP) and its extension using reinforcement learning.

PubMed

Mabu, Shingo; Hirasawa, Kotaro; Hu, Jinglu

2007-01-01

This paper proposes a graph-based evolutionary algorithm called Genetic Network Programming (GNP). Our goal is to develop GNP, which can deal with dynamic environments efficiently and effectively, based on the distinguished expression ability of the graph (network) structure. The characteristics of GNP are as follows. 1) GNP programs are composed of a number of nodes which execute simple judgment/processing, and these nodes are connected by directed links to each other. 2) The graph structure enables GNP to re-use nodes, thus the structure can be very compact. 3) The node transition of GNP is executed according to its node connections without any terminal nodes, thus the past history of the node transition affects the current node to be used and this characteristic works as an implicit memory function. These structural characteristics are useful for dealing with dynamic environments. Furthermore, we propose an extended algorithm, "GNP with Reinforcement Learning (GNPRL)" which combines evolution and reinforcement learning in order to create effective graph structures and obtain better results in dynamic environments. In this paper, we applied GNP to the problem of determining agents' behavior to evaluate its effectiveness. Tileworld was used as the simulation environment. The results show some advantages for GNP over conventional methods.

Not Only Size Matters: Early-Talker and Late-Talker Vocabularies Support Different Word-Learning Biases in Babies and Networks.

PubMed

Colunga, Eliana; Sims, Clare E

2017-02-01

In typical development, word learning goes from slow and laborious to fast and seemingly effortless. Typically developing 2-year-olds seem to intuit the whole range of things in a category from hearing a single instance named-they have word-learning biases. This is not the case for children with relatively small vocabularies (late talkers). We present a computational model that accounts for the emergence of word-learning biases in children at both ends of the vocabulary spectrum based solely on vocabulary structure. The results of Experiment 1 show that late-talkers' and early-talkers' noun vocabularies have different structures and that neural networks trained on the vocabularies of individual late talkers acquire different word-learning biases than those trained on early-talker vocabularies. These models make novel predictions about the word-learning biases in these two populations. Experiment 2 tests these predictions on late- and early-talking toddlers in a novel noun generalization task. Copyright © 2016 Cognitive Science Society, Inc.

Galileo Educational Network: Creating, Researching, and Supporting 21st Century Learning

ERIC Educational Resources Information Center

Friesen, Sharon

2009-01-01

School and classroom structures designed to meet the needs of the industrial past cannot "maintain the temperature required for sustaining life." Recent learning sciences research findings compel educators to invent new learning environments better suited to meet the demands of the 21st century. These new learning environments require…

A Role for Chunk Formation in Statistical Learning of Second Language Syntax

ERIC Educational Resources Information Center

Hamrick, Phillip

2014-01-01

Humans are remarkably sensitive to the statistical structure of language. However, different mechanisms have been proposed to account for such statistical sensitivities. The present study compared adult learning of syntax and the ability of two models of statistical learning to simulate human performance: Simple Recurrent Networks, which learn by…

Spontaneous scale-free structure in adaptive networks with synchronously dynamical linking

NASA Astrophysics Data System (ADS)

Yuan, Wu-Jie; Zhou, Jian-Fang; Li, Qun; Chen, De-Bao; Wang, Zhen

2013-08-01

Inspired by the anti-Hebbian learning rule in neural systems, we study how the feedback from dynamical synchronization shapes network structure by adding new links. Through extensive numerical simulations, we find that an adaptive network spontaneously forms scale-free structure, as confirmed in many real systems. Moreover, the adaptive process produces two nontrivial power-law behaviors of deviation strength from mean activity of the network and negative degree correlation, which exists widely in technological and biological networks. Importantly, these scalings are robust to variation of the adaptive network parameters, which may have meaningful implications in the scale-free formation and manipulation of dynamical networks. Our study thus suggests an alternative adaptive mechanism for the formation of scale-free structure with negative degree correlation, which means that nodes of high degree tend to connect, on average, with others of low degree and vice versa. The relevance of the results to structure formation and dynamical property in neural networks is briefly discussed as well.

Discriminative graph embedding for label propagation.

PubMed

Nguyen, Canh Hao; Mamitsuka, Hiroshi

2011-09-01

In many applications, the available information is encoded in graph structures. This is a common problem in biological networks, social networks, web communities and document citations. We investigate the problem of classifying nodes' labels on a similarity graph given only a graph structure on the nodes. Conventional machine learning methods usually require data to reside in some Euclidean spaces or to have a kernel representation. Applying these methods to nodes on graphs would require embedding the graphs into these spaces. By embedding and then learning the nodes on graphs, most methods are either flexible with different learning objectives or efficient enough for large scale applications. We propose a method to embed a graph into a feature space for a discriminative purpose. Our idea is to include label information into the embedding process, making the space representation tailored to the task. We design embedding objective functions that the following learning formulations become spectral transforms. We then reformulate these spectral transforms into multiple kernel learning problems. Our method, while being tailored to the discriminative tasks, is efficient and can scale to massive data sets. We show the need of discriminative embedding on some simulations. Applying to biological network problems, our method is shown to outperform baselines.

Dynamical Integration of Language and Behavior in a Recurrent Neural Network for Human-Robot Interaction.

PubMed

Yamada, Tatsuro; Murata, Shingo; Arie, Hiroaki; Ogata, Tetsuya

2016-01-01

To work cooperatively with humans by using language, robots must not only acquire a mapping between language and their behavior but also autonomously utilize the mapping in appropriate contexts of interactive tasks online. To this end, we propose a novel learning method linking language to robot behavior by means of a recurrent neural network. In this method, the network learns from correct examples of the imposed task that are given not as explicitly separated sets of language and behavior but as sequential data constructed from the actual temporal flow of the task. By doing this, the internal dynamics of the network models both language-behavior relationships and the temporal patterns of interaction. Here, "internal dynamics" refers to the time development of the system defined on the fixed-dimensional space of the internal states of the context layer. Thus, in the execution phase, by constantly representing where in the interaction context it is as its current state, the network autonomously switches between recognition and generation phases without any explicit signs and utilizes the acquired mapping in appropriate contexts. To evaluate our method, we conducted an experiment in which a robot generates appropriate behavior responding to a human's linguistic instruction. After learning, the network actually formed the attractor structure representing both language-behavior relationships and the task's temporal pattern in its internal dynamics. In the dynamics, language-behavior mapping was achieved by the branching structure. Repetition of human's instruction and robot's behavioral response was represented as the cyclic structure, and besides, waiting to a subsequent instruction was represented as the fixed-point attractor. Thanks to this structure, the robot was able to interact online with a human concerning the given task by autonomously switching phases.

Automated selection of computed tomography display parameters using neural networks

NASA Astrophysics Data System (ADS)

Zhang, Di; Neu, Scott; Valentino, Daniel J.

2001-07-01

A collection of artificial neural networks (ANN's) was trained to identify simple anatomical structures in a set of x-ray computed tomography (CT) images. These neural networks learned to associate a point in an image with the anatomical structure containing the point by using the image pixels located on the horizontal and vertical lines that ran through the point. The neural networks were integrated into a computer software tool whose function is to select an index into a list of CT window/level values from the location of the user's mouse cursor. Based upon the anatomical structure selected by the user, the software tool automatically adjusts the image display to optimally view the structure.

fMRI Syntactic and Lexical Repetition Effects Reveal the Initial Stages of Learning a New Language.

PubMed

Weber, Kirsten; Christiansen, Morten H; Petersson, Karl Magnus; Indefrey, Peter; Hagoort, Peter

2016-06-29

When learning a new language, we build brain networks to process and represent the acquired words and syntax and integrate these with existing language representations. It is an open question whether the same or different neural mechanisms are involved in learning and processing a novel language compared with the native language(s). Here we investigated the neural repetition effects of repeating known and novel word orders while human subjects were in the early stages of learning a new language. Combining a miniature language with a syntactic priming paradigm, we examined the neural correlates of language learning on-line using functional magnetic resonance imaging. In left inferior frontal gyrus and posterior temporal cortex, the repetition of novel syntactic structures led to repetition enhancement, whereas repetition of known structures resulted in repetition suppression. Additional verb repetition led to an increase in the syntactic repetition enhancement effect in language-related brain regions. Similarly, the repetition of verbs led to repetition enhancement effects in areas related to lexical and semantic processing, an effect that continued to increase in a subset of these regions. Repetition enhancement might reflect a mechanism to build and strengthen a neural network to process novel syntactic structures and lexical items. By contrast, the observed repetition suppression points to overlapping neural mechanisms for native and new language constructions when these have sufficient structural similarities. Acquiring a second language entails learning how to interpret novel words and relations between words, and to integrate them with existing language knowledge. To investigate the brain mechanisms involved in this particularly human skill, we combined an artificial language learning task with a syntactic repetition paradigm. We show that the repetition of novel syntactic structures, as well as words in contexts, leads to repetition enhancement, whereas repetition of known structures results in repetition suppression. We thus propose that repetition enhancement might reflect a brain mechanism to build and strengthen a neural network to process novel syntactic regularities and novel words. Importantly, the results also indicate an overlap in neural mechanisms for native and new language constructions with sufficient structural similarities. Copyright © 2016 the authors 0270-6474/16/366872-09$15.00/0.

Computational neural networks in chemistry: Model free mapping devices for predicting chemical reactivity from molecular structure

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

Elrod, D.W.

1992-01-01

Computational neural networks (CNNs) are a computational paradigm inspired by the brain's massively parallel network of highly interconnected neurons. The power of computational neural networks derives not so much from their ability to model the brain as from their ability to learn by example and to map highly complex, nonlinear functions, without the need to explicitly specify the functional relationship. Two central questions about CNNs were investigated in the context of predicting chemical reactions: (1) the mapping properties of neural networks and (2) the representation of chemical information for use in CNNs. Chemical reactivity is here considered an example ofmore » a complex, nonlinear function of molecular structure. CNN's were trained using modifications of the back propagation learning rule to map a three dimensional response surface similar to those typically observed in quantitative structure-activity and structure-property relationships. The computational neural network's mapping of the response surface was found to be robust to the effects of training sample size, noisy data and intercorrelated input variables. The investigation of chemical structure representation led to the development of a molecular structure-based connection-table representation suitable for neural network training. An extension of this work led to a BE-matrix structure representation that was found to be general for several classes of reactions. The CNN prediction of chemical reactivity and regiochemistry was investigated for electrophilic aromatic substitution reactions, Markovnikov addition to alkenes, Saytzeff elimination from haloalkanes, Diels-Alder cycloaddition, and retro Diels-Alder ring opening reactions using these connectivity-matrix derived representations. The reaction predictions made by the CNNs were more accurate than those of an expert system and were comparable to predictions made by chemists.« less

Two-Stage Approach to Image Classification by Deep Neural Networks

NASA Astrophysics Data System (ADS)

Ososkov, Gennady; Goncharov, Pavel

2018-02-01

The paper demonstrates the advantages of the deep learning networks over the ordinary neural networks on their comparative applications to image classifying. An autoassociative neural network is used as a standalone autoencoder for prior extraction of the most informative features of the input data for neural networks to be compared further as classifiers. The main efforts to deal with deep learning networks are spent for a quite painstaking work of optimizing the structures of those networks and their components, as activation functions, weights, as well as the procedures of minimizing their loss function to improve their performances and speed up their learning time. It is also shown that the deep autoencoders develop the remarkable ability for denoising images after being specially trained. Convolutional Neural Networks are also used to solve a quite actual problem of protein genetics on the example of the durum wheat classification. Results of our comparative study demonstrate the undoubted advantage of the deep networks, as well as the denoising power of the autoencoders. In our work we use both GPU and cloud services to speed up the calculations.

CMsearch: simultaneous exploration of protein sequence space and structure space improves not only protein homology detection but also protein structure prediction.

PubMed

Cui, Xuefeng; Lu, Zhiwu; Wang, Sheng; Jing-Yan Wang, Jim; Gao, Xin

2016-06-15

Protein homology detection, a fundamental problem in computational biology, is an indispensable step toward predicting protein structures and understanding protein functions. Despite the advances in recent decades on sequence alignment, threading and alignment-free methods, protein homology detection remains a challenging open problem. Recently, network methods that try to find transitive paths in the protein structure space demonstrate the importance of incorporating network information of the structure space. Yet, current methods merge the sequence space and the structure space into a single space, and thus introduce inconsistency in combining different sources of information. We present a novel network-based protein homology detection method, CMsearch, based on cross-modal learning. Instead of exploring a single network built from the mixture of sequence and structure space information, CMsearch builds two separate networks to represent the sequence space and the structure space. It then learns sequence-structure correlation by simultaneously taking sequence information, structure information, sequence space information and structure space information into consideration. We tested CMsearch on two challenging tasks, protein homology detection and protein structure prediction, by querying all 8332 PDB40 proteins. Our results demonstrate that CMsearch is insensitive to the similarity metrics used to define the sequence and the structure spaces. By using HMM-HMM alignment as the sequence similarity metric, CMsearch clearly outperforms state-of-the-art homology detection methods and the CASP-winning template-based protein structure prediction methods. Our program is freely available for download from http://sfb.kaust.edu.sa/Pages/Software.aspx : xin.gao@kaust.edu.sa Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press.

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.

Structure and inference in annotated networks

PubMed Central

Newman, M. E. J.; Clauset, Aaron

2016-01-01

For many networks of scientific interest we know both the connections of the network and information about the network nodes, such as the age or gender of individuals in a social network. Here we demonstrate how this ‘metadata' can be used to improve our understanding of network structure. We focus in particular on the problem of community detection in networks and develop a mathematically principled approach that combines a network and its metadata to detect communities more accurately than can be done with either alone. Crucially, the method does not assume that the metadata are correlated with the communities we are trying to find. Instead, the method learns whether a correlation exists and correctly uses or ignores the metadata depending on whether they contain useful information. We demonstrate our method on synthetic networks with known structure and on real-world networks, large and small, drawn from social, biological and technological domains. PMID:27306566

Structure and inference in annotated networks

NASA Astrophysics Data System (ADS)

Newman, M. E. J.; Clauset, Aaron

2016-06-01

For many networks of scientific interest we know both the connections of the network and information about the network nodes, such as the age or gender of individuals in a social network. Here we demonstrate how this `metadata' can be used to improve our understanding of network structure. We focus in particular on the problem of community detection in networks and develop a mathematically principled approach that combines a network and its metadata to detect communities more accurately than can be done with either alone. Crucially, the method does not assume that the metadata are correlated with the communities we are trying to find. Instead, the method learns whether a correlation exists and correctly uses or ignores the metadata depending on whether they contain useful information. We demonstrate our method on synthetic networks with known structure and on real-world networks, large and small, drawn from social, biological and technological domains.

Analysis and Visualization of Relations in eLearning

NASA Astrophysics Data System (ADS)

Dráždilová, Pavla; Obadi, Gamila; Slaninová, Kateřina; Martinovič, Jan; Snášel, Václav

The popularity of eLearning systems is growing rapidly; this growth is enabled by the consecutive development in Internet and multimedia technologies. Web-based education became wide spread in the past few years. Various types of learning management systems facilitate development of Web-based courses. Users of these courses form social networks through the different activities performed by them. This chapter focuses on searching the latent social networks in eLearning systems data. These data consist of students activity records wherein latent ties among actors are embedded. The social network studied in this chapter is represented by groups of students who have similar contacts and interact in similar social circles. Different methods of data clustering analysis can be applied to these groups, and the findings show the existence of latent ties among the group members. The second part of this chapter focuses on social network visualization. Graphical representation of social network can describe its structure very efficiently. It can enable social network analysts to determine the network degree of connectivity. Analysts can easily determine individuals with a small or large amount of relationships as well as the amount of independent groups in a given network. When applied to the field of eLearning, data visualization simplifies the process of monitoring the study activities of individuals or groups, as well as the planning of educational curriculum, the evaluation of study processes, etc.

Adaptivity in Agent-Based Routing for Data Networks

NASA Technical Reports Server (NTRS)

Wolpert, David H.; Kirshner, Sergey; Merz, Chris J.; Turner, Kagan

2000-01-01

Adaptivity, both of the individual agents and of the interaction structure among the agents, seems indispensable for scaling up multi-agent systems (MAS s) in noisy environments. One important consideration in designing adaptive agents is choosing their action spaces to be as amenable as possible to machine learning techniques, especially to reinforcement learning (RL) techniques. One important way to have the interaction structure connecting agents itself be adaptive is to have the intentions and/or actions of the agents be in the input spaces of the other agents, much as in Stackelberg games. We consider both kinds of adaptivity in the design of a MAS to control network packet routing. We demonstrate on the OPNET event-driven network simulator the perhaps surprising fact that simply changing the action space of the agents to be better suited to RL can result in very large improvements in their potential performance: at their best settings, our learning-amenable router agents achieve throughputs up to three and one half times better than that of the standard Bellman-Ford routing algorithm, even when the Bellman-Ford protocol traffic is maintained. We then demonstrate that much of that potential improvement can be realized by having the agents learn their settings when the agent interaction structure is itself adaptive.

Les structures de l'apprentissage en Roumanie: unite et diversite

NASA Astrophysics Data System (ADS)

Văideanu, George

1982-06-01

This analysis concerns structures of learning at the pre-university level. The concept of `learning' is used in a wide sense, including the assimilation not only of knowledge but also of know-how and attitudes. That is to say, learning has been analysed as intellectual — but also as moral, aesthetic and physical or sports — education. The author comments on the philosophy underlying the Report to the Club of Rome, No Limits to Learning. Three categories of learning structure are examined: formal, nonformal and informal. Other possibilities of grouping the structures are also indicated, including learning for society and learning for oneself. Various modalities of their articulation are presented, a distinction being made between those appropriate to school-level and those for scholarly research. Among the final conclusions and suggestions are two addressed to Unesco: a. an international round-table conference on the desirable evolution of learning; and b. the organisation of a network of experimental schools to present the desirable learning structures to educators, researchers and decision-makers.

Adaptive control of nonlinear system using online error minimum neural networks.

PubMed

Jia, Chao; Li, Xiaoli; Wang, Kang; Ding, Dawei

2016-11-01

In this paper, a new learning algorithm named OEM-ELM (Online Error Minimized-ELM) is proposed based on ELM (Extreme Learning Machine) neural network algorithm and the spreading of its main structure. The core idea of this OEM-ELM algorithm is: online learning, evaluation of network performance, and increasing of the number of hidden nodes. It combines the advantages of OS-ELM and EM-ELM, which can improve the capability of identification and avoid the redundancy of networks. The adaptive control based on the proposed algorithm OEM-ELM is set up which has stronger adaptive capability to the change of environment. The adaptive control of chemical process Continuous Stirred Tank Reactor (CSTR) is also given for application. The simulation results show that the proposed algorithm with respect to the traditional ELM algorithm can avoid network redundancy and improve the control performance greatly. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.

Protein secondary structure prediction using modular reciprocal bidirectional recurrent neural networks.

PubMed

Babaei, Sepideh; Geranmayeh, Amir; Seyyedsalehi, Seyyed Ali

2010-12-01

The supervised learning of recurrent neural networks well-suited for prediction of protein secondary structures from the underlying amino acids sequence is studied. Modular reciprocal recurrent neural networks (MRR-NN) are proposed to model the strong correlations between adjacent secondary structure elements. Besides, a multilayer bidirectional recurrent neural network (MBR-NN) is introduced to capture the long-range intramolecular interactions between amino acids in formation of the secondary structure. The final modular prediction system is devised based on the interactive integration of the MRR-NN and the MBR-NN structures to arbitrarily engage the neighboring effects of the secondary structure types concurrent with memorizing the sequential dependencies of amino acids along the protein chain. The advanced combined network augments the percentage accuracy (Q₃) to 79.36% and boosts the segment overlap (SOV) up to 70.09% when tested on the PSIPRED dataset in three-fold cross-validation. Copyright © 2010 Elsevier Ireland Ltd. All rights reserved.

A quantitative meta-analysis and review of motor learning in the human brain

PubMed Central

Hardwick, Robert M.; Rottschy, Claudia; Miall, R. Chris; Eickhoff, Simon B.

2013-01-01

Neuroimaging studies have improved our understanding of which brain structures are involved in motor learning. Despite this, questions remain regarding the areas that contribute consistently across paradigms with different task demands. For instance, sensorimotor tasks focus on learning novel movement kinematics and dynamics, while serial response time task (SRTT) variants focus on sequence learning. These differing task demands are likely to elicit quantifiably different patterns of neural activity on top of a potentially consistent core network. The current study identified consistent activations across 70 motor learning experiments using activation likelihood estimation (ALE) meta-analysis. A global analysis of all tasks revealed a bilateral cortical–subcortical network consistently underlying motor learning across tasks. Converging activations were revealed in the dorsal premotor cortex, supplementary motor cortex, primary motor cortex, primary somatosensory cortex, superior parietal lobule, thalamus, putamen and cerebellum. These activations were broadly consistent across task specific analyses that separated sensorimotor tasks and SRTT variants. Contrast analysis indicated that activity in the basal ganglia and cerebellum was significantly stronger for sensorimotor tasks, while activity in cortical structures and the thalamus was significantly stronger for SRTT variants. Additional conjunction analyses then indicated that the left dorsal premotor cortex was activated across all analyses considered, even when controlling for potential motor confounds. The highly consistent activation of the left dorsal premotor cortex suggests it is a critical node in the motor learning network. PMID:23194819

The Structural Connectivity Underpinning Language Aptitude, Working Memory, and IQ in the Perisylvian Language Network

ERIC Educational Resources Information Center

Xiang, Huadong; Dediu, Dan; Roberts, Leah; van Oort, Erik; Norris, David G.; Hagoort, Peter

2012-01-01

In this article, we report the results of a study on the relationship between individual differences in language learning aptitude and the structural connectivity of language pathways in the adult brain, the first of its kind. We measured four components of language aptitude ("vocabulary learning"; "sound recognition"; "sound-symbol…

Detection of pigment network in dermoscopy images using supervised machine learning and structural analysis.

PubMed

García Arroyo, Jose Luis; García Zapirain, Begoña

2014-01-01

By means of this study, a detection algorithm for the "pigment network" in dermoscopic images is presented, one of the most relevant indicators in the diagnosis of melanoma. The design of the algorithm consists of two blocks. In the first one, a machine learning process is carried out, allowing the generation of a set of rules which, when applied over the image, permit the construction of a mask with the pixels candidates to be part of the pigment network. In the second block, an analysis of the structures over this mask is carried out, searching for those corresponding to the pigment network and making the diagnosis, whether it has pigment network or not, and also generating the mask corresponding to this pattern, if any. The method was tested against a database of 220 images, obtaining 86% sensitivity and 81.67% specificity, which proves the reliability of the algorithm. © 2013 The Authors. Published by Elsevier Ltd. All rights reserved.

Quantum Enhanced Inference in Markov Logic Networks

NASA Astrophysics Data System (ADS)

Wittek, Peter; Gogolin, Christian

2017-04-01

Markov logic networks (MLNs) reconcile two opposing schools in machine learning and artificial intelligence: causal networks, which account for uncertainty extremely well, and first-order logic, which allows for formal deduction. An MLN is essentially a first-order logic template to generate Markov networks. Inference in MLNs is probabilistic and it is often performed by approximate methods such as Markov chain Monte Carlo (MCMC) Gibbs sampling. An MLN has many regular, symmetric structures that can be exploited at both first-order level and in the generated Markov network. We analyze the graph structures that are produced by various lifting methods and investigate the extent to which quantum protocols can be used to speed up Gibbs sampling with state preparation and measurement schemes. We review different such approaches, discuss their advantages, theoretical limitations, and their appeal to implementations. We find that a straightforward application of a recent result yields exponential speedup compared to classical heuristics in approximate probabilistic inference, thereby demonstrating another example where advanced quantum resources can potentially prove useful in machine learning.

Quantum Enhanced Inference in Markov Logic Networks.

PubMed

Wittek, Peter; Gogolin, Christian

2017-04-19

Markov logic networks (MLNs) reconcile two opposing schools in machine learning and artificial intelligence: causal networks, which account for uncertainty extremely well, and first-order logic, which allows for formal deduction. An MLN is essentially a first-order logic template to generate Markov networks. Inference in MLNs is probabilistic and it is often performed by approximate methods such as Markov chain Monte Carlo (MCMC) Gibbs sampling. An MLN has many regular, symmetric structures that can be exploited at both first-order level and in the generated Markov network. We analyze the graph structures that are produced by various lifting methods and investigate the extent to which quantum protocols can be used to speed up Gibbs sampling with state preparation and measurement schemes. We review different such approaches, discuss their advantages, theoretical limitations, and their appeal to implementations. We find that a straightforward application of a recent result yields exponential speedup compared to classical heuristics in approximate probabilistic inference, thereby demonstrating another example where advanced quantum resources can potentially prove useful in machine learning.

Quantum Enhanced Inference in Markov Logic Networks

PubMed Central

Wittek, Peter; Gogolin, Christian

2017-01-01

Markov logic networks (MLNs) reconcile two opposing schools in machine learning and artificial intelligence: causal networks, which account for uncertainty extremely well, and first-order logic, which allows for formal deduction. An MLN is essentially a first-order logic template to generate Markov networks. Inference in MLNs is probabilistic and it is often performed by approximate methods such as Markov chain Monte Carlo (MCMC) Gibbs sampling. An MLN has many regular, symmetric structures that can be exploited at both first-order level and in the generated Markov network. We analyze the graph structures that are produced by various lifting methods and investigate the extent to which quantum protocols can be used to speed up Gibbs sampling with state preparation and measurement schemes. We review different such approaches, discuss their advantages, theoretical limitations, and their appeal to implementations. We find that a straightforward application of a recent result yields exponential speedup compared to classical heuristics in approximate probabilistic inference, thereby demonstrating another example where advanced quantum resources can potentially prove useful in machine learning. PMID:28422093

Functional vs. Structural Modularity: do they imply each other?

NASA Astrophysics Data System (ADS)

Toroczkai, Zoltan

2009-03-01

While many deterministic and stochastic processes have been proposed to produce heterogeneous graphs mimicking real-world networks, only a handful of studies attempt to connect structure and dynamics with the function(s) performed by the network. In this talk I will present an approach built on the premise that structure, dynamics, and their observed heterogeneity, are implementations of various functions and their compositions. After a brief review of real-world networks where this connection can explicitly be made, I will focus on biological networks. Biological networks are known to possess functionally specialized modules, which perform tasks almost independently of each other. While proposals have been made for the evolutionary emergence of modularity, it is far from clear that adaptation on evolutionary timescales is the sole mechanism leading to functional specialization. We show that non-evolutionary learning can also lead to the formation of functionally specialized modules in a system exposed to multiple environmental constraints. A natural example suggesting that this is possible is the cerebral cortex, where there are clearly delineated functional areas in spite of the largely uniform anatomical construction of the cortical tissue. However, as numerous experiments show, when damaged, regions specialized for a certain function can be retrained to perform functions normally attributed to other regions. We use the paradigm of neural networks to represent a multitasking system, and use several non-evolutionary learning algorithms as mechanisms for phenotypic adaptation. We show that for a network learning to perform multiple tasks, the degree of independence between the tasks dictates the degree of functional specialization emerging in the network. To uncover the functional modules, we introduce a method of node knockouts that explicitly rates the contribution of each node to different tasks (differential robustness). Through a concrete example we also demonstrate the potential inability of purely topology-based clustering methods to detect functional modules. The robustness of these results suggests that similar mechanisms might be responsible for the emergence of functional specialization in other multitasking networks, as well, including social networks.

Nonlinear dynamic systems identification using recurrent interval type-2 TSK fuzzy neural network - A novel structure.

PubMed

El-Nagar, Ahmad M

2018-01-01

In this study, a novel structure of a recurrent interval type-2 Takagi-Sugeno-Kang (TSK) fuzzy neural network (FNN) is introduced for nonlinear dynamic and time-varying systems identification. It combines the type-2 fuzzy sets (T2FSs) and a recurrent FNN to avoid the data uncertainties. The fuzzy firing strengths in the proposed structure are returned to the network input as internal variables. The interval type-2 fuzzy sets (IT2FSs) is used to describe the antecedent part for each rule while the consequent part is a TSK-type, which is a linear function of the internal variables and the external inputs with interval weights. All the type-2 fuzzy rules for the proposed RIT2TSKFNN are learned on-line based on structure and parameter learning, which are performed using the type-2 fuzzy clustering. The antecedent and consequent parameters of the proposed RIT2TSKFNN are updated based on the Lyapunov function to achieve network stability. The obtained results indicate that our proposed network has a small root mean square error (RMSE) and a small integral of square error (ISE) with a small number of rules and a small computation time compared with other type-2 FNNs. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

Reviewing the Differences in Size, Composition and Structure between the Personal Networks of High-and Low-Performing Students

ERIC Educational Resources Information Center

Casquero, Oskar; Ovelar, Ramón; Romo, Jesús; Benito, Manuel

2015-01-01

An interesting aspect in the current literature about learning networks is the shift of focus from the understanding of the "whole network" of a course to the examination of the "personal networks" of individual students. This line of research is relatively new, based on small-scale studies and diverse analysis techniques,…

Deep learning of the sectional appearances of 3D CT images for anatomical structure segmentation based on an FCN voting method.

PubMed

Zhou, Xiangrong; Takayama, Ryosuke; Wang, Song; Hara, Takeshi; Fujita, Hiroshi

2017-10-01

We propose a single network trained by pixel-to-label deep learning to address the general issue of automatic multiple organ segmentation in three-dimensional (3D) computed tomography (CT) images. Our method can be described as a voxel-wise multiple-class classification scheme for automatically assigning labels to each pixel/voxel in a 2D/3D CT image. We simplify the segmentation algorithms of anatomical structures (including multiple organs) in a CT image (generally in 3D) to a majority voting scheme over the semantic segmentation of multiple 2D slices drawn from different viewpoints with redundancy. The proposed method inherits the spirit of fully convolutional networks (FCNs) that consist of "convolution" and "deconvolution" layers for 2D semantic image segmentation, and expands the core structure with 3D-2D-3D transformations to adapt to 3D CT image segmentation. All parameters in the proposed network are trained pixel-to-label from a small number of CT cases with human annotations as the ground truth. The proposed network naturally fulfills the requirements of multiple organ segmentations in CT cases of different sizes that cover arbitrary scan regions without any adjustment. The proposed network was trained and validated using the simultaneous segmentation of 19 anatomical structures in the human torso, including 17 major organs and two special regions (lumen and content inside of stomach). Some of these structures have never been reported in previous research on CT segmentation. A database consisting of 240 (95% for training and 5% for testing) 3D CT scans, together with their manually annotated ground-truth segmentations, was used in our experiments. The results show that the 19 structures of interest were segmented with acceptable accuracy (88.1% and 87.9% voxels in the training and testing datasets, respectively, were labeled correctly) against the ground truth. We propose a single network based on pixel-to-label deep learning to address the challenging issue of anatomical structure segmentation in 3D CT cases. The novelty of this work is the policy of deep learning of the different 2D sectional appearances of 3D anatomical structures for CT cases and the majority voting of the 3D segmentation results from multiple crossed 2D sections to achieve availability and reliability with better efficiency, generality, and flexibility than conventional segmentation methods, which must be guided by human expertise. © 2017 The Authors. Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.

Unsupervised learning of contextual constraints in neural networks for simultaneous visual processing of multiple objects

NASA Astrophysics Data System (ADS)

Marshall, Jonathan A.

1992-12-01

A simple self-organizing neural network model, called an EXIN network, that learns to process sensory information in a context-sensitive manner, is described. EXIN networks develop efficient representation structures for higher-level visual tasks such as segmentation, grouping, transparency, depth perception, and size perception. Exposure to a perceptual environment during a developmental period serves to configure the network to perform appropriate organization of sensory data. A new anti-Hebbian inhibitory learning rule permits superposition of multiple simultaneous neural activations (multiple winners), while maintaining contextual consistency constraints, instead of forcing winner-take-all pattern classifications. The activations can represent multiple patterns simultaneously and can represent uncertainty. The network performs parallel parsing, credit attribution, and simultaneous constraint satisfaction. EXIN networks can learn to represent multiple oriented edges even where they intersect and can learn to represent multiple transparently overlaid surfaces defined by stereo or motion cues. In the case of stereo transparency, the inhibitory learning implements both a uniqueness constraint and permits coactivation of cells representing multiple disparities at the same image location. Thus two or more disparities can be active simultaneously without interference. This behavior is analogous to that of Prazdny's stereo vision algorithm, with the bonus that each binocular point is assigned a unique disparity. In a large implementation, such a NN would also be able to represent effectively the disparities of a cloud of points at random depths, like human observers, and unlike Prazdny's method

Boolean network identification from perturbation time series data combining dynamics abstraction and logic programming.

PubMed

Ostrowski, M; Paulevé, L; Schaub, T; Siegel, A; Guziolowski, C

2016-11-01

Boolean networks (and more general logic models) are useful frameworks to study signal transduction across multiple pathways. Logic models can be learned from a prior knowledge network structure and multiplex phosphoproteomics data. However, most efficient and scalable training methods focus on the comparison of two time-points and assume that the system has reached an early steady state. In this paper, we generalize such a learning procedure to take into account the time series traces of phosphoproteomics data in order to discriminate Boolean networks according to their transient dynamics. To that end, we identify a necessary condition that must be satisfied by the dynamics of a Boolean network to be consistent with a discretized time series trace. Based on this condition, we use Answer Set Programming to compute an over-approximation of the set of Boolean networks which fit best with experimental data and provide the corresponding encodings. Combined with model-checking approaches, we end up with a global learning algorithm. Our approach is able to learn logic models with a true positive rate higher than 78% in two case studies of mammalian signaling networks; for a larger case study, our method provides optimal answers after 7min of computation. We quantified the gain in our method predictions precision compared to learning approaches based on static data. Finally, as an application, our method proposes erroneous time-points in the time series data with respect to the optimal learned logic models. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

On structure-exploiting trust-region regularized nonlinear least squares algorithms for neural-network learning.

PubMed

Mizutani, Eiji; Demmel, James W

2003-01-01

This paper briefly introduces our numerical linear algebra approaches for solving structured nonlinear least squares problems arising from 'multiple-output' neural-network (NN) models. Our algorithms feature trust-region regularization, and exploit sparsity of either the 'block-angular' residual Jacobian matrix or the 'block-arrow' Gauss-Newton Hessian (or Fisher information matrix in statistical sense) depending on problem scale so as to render a large class of NN-learning algorithms 'efficient' in both memory and operation costs. Using a relatively large real-world nonlinear regression application, we shall explain algorithmic strengths and weaknesses, analyzing simulation results obtained by both direct and iterative trust-region algorithms with two distinct NN models: 'multilayer perceptrons' (MLP) and 'complementary mixtures of MLP-experts' (or neuro-fuzzy modular networks).

Leveraging Value in Doctoral Student Networks through Social Capital

ERIC Educational Resources Information Center

Pilbeam, Colin; Lloyd-Jones, Gaynor; Denyer, David

2013-01-01

UK higher education policy relating to doctoral-level education assumes that student networks provide the basis for informal learning and the acquisition of necessary skills and information. Through semi-structured interviews with 17 doctoral students from a UK management school, this study investigated the value of these networks to students, the…

From Networked Learning to Operational Practice: Constructing and Transferring Superintendent Knowledge in a Regional Instructional Rounds Network

ERIC Educational Resources Information Center

Travis, Timothy J.

2015-01-01

Instructional rounds are an emerging network structure with processes and protocols designed to develop superintendents' knowledge and skills in leading large-scale improvement, to enable superintendents to build an infrastructure that supports the work of improvement, to assist superintendents in distributing leadership throughout their district,…

Dynamic functional connectivity using state-based dynamic community structure: method and application to opioid analgesia.

PubMed

Robinson, Lucy F; Atlas, Lauren Y; Wager, Tor D

2015-03-01

We present a new method, State-based Dynamic Community Structure, that detects time-dependent community structure in networks of brain regions. Most analyses of functional connectivity assume that network behavior is static in time, or differs between task conditions with known timing. Our goal is to determine whether brain network topology remains stationary over time, or if changes in network organization occur at unknown time points. Changes in network organization may be related to shifts in neurological state, such as those associated with learning, drug uptake or experimental conditions. Using a hidden Markov stochastic blockmodel, we define a time-dependent community structure. We apply this approach to data from a functional magnetic resonance imaging experiment examining how contextual factors influence drug-induced analgesia. Results reveal that networks involved in pain, working memory, and emotion show distinct profiles of time-varying connectivity. Copyright © 2014 Elsevier Inc. All rights reserved.

Animal social networks as substrate for cultural behavioural diversity.

PubMed

Whitehead, Hal; Lusseau, David

2012-02-07

We used individual-based stochastic models to examine how social structure influences the diversity of socially learned behaviour within a non-human population. For continuous behavioural variables we modelled three forms of dyadic social learning, averaging the behavioural value of the two individuals, random transfer of information from one individual to the other, and directional transfer from the individual with highest behavioural value to the other. Learning had potential error. We also examined the transfer of categorical behaviour between individuals with random directionality and two forms of error, the adoption of a randomly chosen existing behavioural category or the innovation of a new type of behaviour. In populations without social structuring the diversity of culturally transmitted behaviour increased with learning error and population size. When the populations were structured socially either by making individuals members of permanent social units or by giving them overlapping ranges, behavioural diversity increased with network modularity under all scenarios, although the proportional increase varied considerably between continuous and categorical behaviour, with transmission mechanism, and population size. Although functions of the form e(c)¹(m)⁻(c)² + (c)³(Log(N)) predicted the mean increase in diversity with modularity (m) and population size (N), behavioural diversity could be highly unpredictable both between simulations with the same set of parameters, and within runs. Errors in social learning and social structuring generally promote behavioural diversity. Consequently, social learning may be considered to produce culture in populations whose social structure is sufficiently modular. Copyright © 2011 Elsevier Ltd. All rights reserved.

Artificial Neural Network with Regular Graph for Maximum Air Temperature Forecasting:. the Effect of Decrease in Nodes Degree on Learning

NASA Astrophysics Data System (ADS)

Ghaderi, A. H.; Darooneh, A. H.

The behavior of nonlinear systems can be analyzed by artificial neural networks. Air temperature change is one example of the nonlinear systems. In this work, a new neural network method is proposed for forecasting maximum air temperature in two cities. In this method, the regular graph concept is used to construct some partially connected neural networks that have regular structures. The learning results of fully connected ANN and networks with proposed method are compared. In some case, the proposed method has the better result than conventional ANN. After specifying the best network, the effect of input pattern numbers on the prediction is studied and the results show that the increase of input patterns has a direct effect on the prediction accuracy.

How the study of online collaborative learning can guide teachers and predict students' performance in a medical course.

PubMed

Saqr, Mohammed; Fors, Uno; Tedre, Matti

2018-02-06

Collaborative learning facilitates reflection, diversifies understanding and stimulates skills of critical and higher-order thinking. Although the benefits of collaborative learning have long been recognized, it is still rarely studied by social network analysis (SNA) in medical education, and the relationship of parameters that can be obtained via SNA with students' performance remains largely unknown. The aim of this work was to assess the potential of SNA for studying online collaborative clinical case discussions in a medical course and to find out which activities correlate with better performance and help predict final grade or explain variance in performance. Interaction data were extracted from the learning management system (LMS) forum module of the Surgery course in Qassim University, College of Medicine. The data were analyzed using social network analysis. The analysis included visual as well as a statistical analysis. Correlation with students' performance was calculated, and automatic linear regression was used to predict students' performance. By using social network analysis, we were able to analyze a large number of interactions in online collaborative discussions and gain an overall insight of the course social structure, track the knowledge flow and the interaction patterns, as well as identify the active participants and the prominent discussion moderators. When augmented with calculated network parameters, SNA offered an accurate view of the course network, each user's position, and level of connectedness. Results from correlation coefficients, linear regression, and logistic regression indicated that a student's position and role in information relay in online case discussions, combined with the strength of that student's network (social capital), can be used as predictors of performance in relevant settings. By using social network analysis, researchers can analyze the social structure of an online course and reveal important information about students' and teachers' interactions that can be valuable in guiding teachers, improve students' engagement, and contribute to learning analytics insights.

Learning and diagnosing faults using neural networks

NASA Technical Reports Server (NTRS)

Whitehead, Bruce A.; Kiech, Earl L.; Ali, Moonis

1990-01-01

Neural networks have been employed for learning fault behavior from rocket engine simulator parameters and for diagnosing faults on the basis of the learned behavior. Two problems in applying neural networks to learning and diagnosing faults are (1) the complexity of the sensor data to fault mapping to be modeled by the neural network, which implies difficult and lengthy training procedures; and (2) the lack of sufficient training data to adequately represent the very large number of different types of faults which might occur. Methods are derived and tested in an architecture which addresses these two problems. First, the sensor data to fault mapping is decomposed into three simpler mappings which perform sensor data compression, hypothesis generation, and sensor fusion. Efficient training is performed for each mapping separately. Secondly, the neural network which performs sensor fusion is structured to detect new unknown faults for which training examples were not presented during training. These methods were tested on a task of fault diagnosis by employing rocket engine simulator data. Results indicate that the decomposed neural network architecture can be trained efficiently, can identify faults for which it has been trained, and can detect the occurrence of faults for which it has not been trained.

A neural network with modular hierarchical learning

NASA Technical Reports Server (NTRS)

Baldi, Pierre F. (Inventor); Toomarian, Nikzad (Inventor)

1994-01-01

This invention provides a new hierarchical approach for supervised neural learning of time dependent trajectories. The modular hierarchical methodology leads to architectures which are more structured than fully interconnected networks. The networks utilize a general feedforward flow of information and sparse recurrent connections to achieve dynamic effects. The advantages include the sparsity of units and connections, the modular organization. A further advantage is that the learning is much more circumscribed learning than in fully interconnected systems. The present invention is embodied by a neural network including a plurality of neural modules each having a pre-established performance capability wherein each neural module has an output outputting present results of the performance capability and an input for changing the present results of the performance capabilitiy. For pattern recognition applications, the performance capability may be an oscillation capability producing a repeating wave pattern as the present results. In the preferred embodiment, each of the plurality of neural modules includes a pre-established capability portion and a performance adjustment portion connected to control the pre-established capability portion.

Effects of Prior Knowledge and Concept-Map Structure on Disorientation, Cognitive Load, and Learning

ERIC Educational Resources Information Center

Amadieu, Franck; van Gog, Tamara; Paas, Fred; Tricot, Andre; Marine, Claudette

2009-01-01

This study explored the effects of prior knowledge (high vs. low; HPK and LPK) and concept-map structure (hierarchical vs. network; HS and NS) on disorientation, cognitive load, and learning from non-linear documents on "the infection process of a retrograde virus (HIV)". Participants in the study were 24 adults. Overall subjective ratings of…

Organisational adaptation in an activist network: social networks, leadership, and change in al-Muhajiroun.

PubMed

Kenney, Michael; Horgan, John; Horne, Cale; Vining, Peter; Carley, Kathleen M; Bigrigg, Michael W; Bloom, Mia; Braddock, Kurt

2013-09-01

Social networks are said to facilitate learning and adaptation by providing the connections through which network nodes (or agents) share information and experience. Yet, our understanding of how this process unfolds in real-world networks remains underdeveloped. This paper explores this gap through a case study of al-Muhajiroun, an activist network that continues to call for the establishment of an Islamic state in Britain despite being formally outlawed by British authorities. Drawing on organisation theory and social network analysis, we formulate three hypotheses regarding the learning capacity and social network properties of al-Muhajiroun (AM) and its successor groups. We then test these hypotheses using mixed methods. Our methods combine quantitative analysis of three agent-based networks in AM measured for structural properties that facilitate learning, including connectedness, betweenness centrality and eigenvector centrality, with qualitative analysis of interviews with AM activists focusing organisational adaptation and learning. The results of these analyses confirm that al-Muhajiroun activists respond to government pressure by changing their operations, including creating new platforms under different names and adjusting leadership roles among movement veterans to accommodate their spiritual leader's unwelcome exodus to Lebanon. Simple as they are effective, these adaptations have allowed al-Muhajiroun and its successor groups to continue their activism in an increasingly hostile environment. Copyright © 2012 Elsevier Ltd and The Ergonomics Society. All rights reserved.

Do learning collaboratives strengthen communication? A comparison of organizational team communication networks over time.

PubMed

Bunger, Alicia C; Lengnick-Hall, Rebecca

Collaborative learning models were designed to support quality improvements, such as innovation implementation by promoting communication within organizational teams. Yet the effect of collaborative learning approaches on organizational team communication during implementation is untested. The aim of this study was to explore change in communication patterns within teams from children's mental health organizations during a year-long learning collaborative focused on implementing a new treatment. We adopt a social network perspective to examine intraorganizational communication within each team and assess change in (a) the frequency of communication among team members, (b) communication across organizational hierarchies, and (c) the overall structure of team communication networks. A pretest-posttest design compared communication among 135 participants from 21 organizational teams at the start and end of a learning collaborative. At both time points, participants were asked to list the members of their team and rate the frequency of communication with each along a 7-point Likert scale. Several individual, pair-wise, and team level communication network metrics were calculated and compared over time. At the individual level, participants reported communicating with more team members by the end of the learning collaborative. Cross-hierarchical communication did not change. At the team level, these changes manifested differently depending on team size. In large teams, communication frequency increased, and networks grew denser and slightly less centralized. In small teams, communication frequency declined, growing more sparse and centralized. Results suggest that team communication patterns change minimally but evolve differently depending on size. Learning collaboratives may be more helpful for enhancing communication among larger teams; thus, managers might consider selecting and sending larger staff teams to learning collaboratives. This study highlights key future research directions that can disentangle the relationship between learning collaboratives and team networks.

Temporal entrainment of cognitive functions: musical mnemonics induce brain plasticity and oscillatory synchrony in neural networks underlying memory.

PubMed

Thaut, Michael H; Peterson, David A; McIntosh, Gerald C

2005-12-01

In a series of experiments, we have begun to investigate the effect of music as a mnemonic device on learning and memory and the underlying plasticity of oscillatory neural networks. We used verbal learning and memory tests (standardized word lists, AVLT) in conjunction with electroencephalographic analysis to determine differences between verbal learning in either a spoken or musical (verbal materials as song lyrics) modality. In healthy adults, learning in both the spoken and music condition was associated with significant increases in oscillatory synchrony across all frequency bands. A significant difference between the spoken and music condition emerged in the cortical topography of the learning-related synchronization. When using EEG measures as predictors during learning for subsequent successful memory recall, significantly increased coherence (phase-locked synchronization) within and between oscillatory brain networks emerged for music in alpha and gamma bands. In a similar study with multiple sclerosis patients, superior learning and memory was shown in the music condition when controlled for word order recall, and subjects were instructed to sing back the word lists. Also, the music condition was associated with a significant power increase in the low-alpha band in bilateral frontal networks, indicating increased neuronal synchronization. Musical learning may access compensatory pathways for memory functions during compromised PFC functions associated with learning and recall. Music learning may also confer a neurophysiological advantage through the stronger synchronization of the neuronal cell assemblies underlying verbal learning and memory. Collectively our data provide evidence that melodic-rhythmic templates as temporal structures in music may drive internal rhythm formation in recurrent cortical networks involved in learning and memory.

The Shape of Deeper Learning: Strategies, Structures, and Cultures in Deeper Learning Network High Schools. Findings from the Study of Deeper Learning Opportunities and Outcomes: Report 1

ERIC Educational Resources Information Center

Huberman, Mette; Bitter, Catherine; Anthony, Jennifer; O'Day, Jennifer

2014-01-01

The "Study of Deeper Learning: Opportunities and Outcomes"--funded by the William and Flora Hewlett Foundation--is a proof-of-concept study, the purpose of which was to determine whether students attending high schools with a mature and at least moderately well implemented approach to promoting deeper learning actually experienced…

Neural network to diagnose lining condition

NASA Astrophysics Data System (ADS)

Yemelyanov, V. A.; Yemelyanova, N. Y.; Nedelkin, A. A.; Zarudnaya, M. V.

2018-03-01

The paper presents data on the problem of diagnosing the lining condition at the iron and steel works. The authors describe the neural network structure and software that are designed and developed to determine the lining burnout zones. The simulation results of the proposed neural networks are presented. The authors note the low learning and classification errors of the proposed neural networks. To realize the proposed neural network, the specialized software has been developed.

Computational modeling of neural plasticity for self-organization of neural networks.

PubMed

Chrol-Cannon, Joseph; Jin, Yaochu

2014-11-01

Self-organization in biological nervous systems during the lifetime is known to largely occur through a process of plasticity that is dependent upon the spike-timing activity in connected neurons. In the field of computational neuroscience, much effort has been dedicated to building up computational models of neural plasticity to replicate experimental data. Most recently, increasing attention has been paid to understanding the role of neural plasticity in functional and structural neural self-organization, as well as its influence on the learning performance of neural networks for accomplishing machine learning tasks such as classification and regression. Although many ideas and hypothesis have been suggested, the relationship between the structure, dynamics and learning performance of neural networks remains elusive. The purpose of this article is to review the most important computational models for neural plasticity and discuss various ideas about neural plasticity's role. Finally, we suggest a few promising research directions, in particular those along the line that combines findings in computational neuroscience and systems biology, and their synergetic roles in understanding learning, memory and cognition, thereby bridging the gap between computational neuroscience, systems biology and computational intelligence. Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.

Bio-inspired spiking neural network for nonlinear systems control.

PubMed

Pérez, Javier; Cabrera, Juan A; Castillo, Juan J; Velasco, Juan M

2018-08-01

Spiking neural networks (SNN) are the third generation of artificial neural networks. SNN are the closest approximation to biological neural networks. SNNs make use of temporal spike trains to command inputs and outputs, allowing a faster and more complex computation. As demonstrated by biological organisms, they are a potentially good approach to designing controllers for highly nonlinear dynamic systems in which the performance of controllers developed by conventional techniques is not satisfactory or difficult to implement. SNN-based controllers exploit their ability for online learning and self-adaptation to evolve when transferred from simulations to the real world. SNN's inherent binary and temporary way of information codification facilitates their hardware implementation compared to analog neurons. Biological neural networks often require a lower number of neurons compared to other controllers based on artificial neural networks. In this work, these neuronal systems are imitated to perform the control of non-linear dynamic systems. For this purpose, a control structure based on spiking neural networks has been designed. Particular attention has been paid to optimizing the structure and size of the neural network. The proposed structure is able to control dynamic systems with a reduced number of neurons and connections. A supervised learning process using evolutionary algorithms has been carried out to perform controller training. The efficiency of the proposed network has been verified in two examples of dynamic systems control. Simulations show that the proposed control based on SNN exhibits superior performance compared to other approaches based on Neural Networks and SNNs. Copyright © 2018 Elsevier Ltd. All rights reserved.

Emergence of small-world structure in networks of spiking neurons through STDP plasticity.

PubMed

Basalyga, Gleb; Gleiser, Pablo M; Wennekers, Thomas

2011-01-01

In this work, we use a complex network approach to investigate how a neural network structure changes under synaptic plasticity. In particular, we consider a network of conductance-based, single-compartment integrate-and-fire excitatory and inhibitory neurons. Initially the neurons are connected randomly with uniformly distributed synaptic weights. The weights of excitatory connections can be strengthened or weakened during spiking activity by the mechanism known as spike-timing-dependent plasticity (STDP). We extract a binary directed connection matrix by thresholding the weights of the excitatory connections at every simulation step and calculate its major topological characteristics such as the network clustering coefficient, characteristic path length and small-world index. We numerically demonstrate that, under certain conditions, a nontrivial small-world structure can emerge from a random initial network subject to STDP learning.

Early brain connectivity alterations and cognitive impairment in a rat model of Alzheimer's disease.

PubMed

Muñoz-Moreno, Emma; Tudela, Raúl; López-Gil, Xavier; Soria, Guadalupe

2018-02-07

Animal models of Alzheimer's disease (AD) are essential to understanding the disease progression and to development of early biomarkers. Because AD has been described as a disconnection syndrome, magnetic resonance imaging (MRI)-based connectomics provides a highly translational approach to characterizing the disruption in connectivity associated with the disease. In this study, a transgenic rat model of AD (TgF344-AD) was analyzed to describe both cognitive performance and brain connectivity at an early stage (5 months of age) before a significant concentration of β-amyloid plaques is present. Cognitive abilities were assessed by a delayed nonmatch-to-sample (DNMS) task preceded by a training phase where the animals learned the task. The number of training sessions required to achieve a learning criterion was recorded and evaluated. After DNMS, MRI acquisition was performed, including diffusion-weighted MRI and resting-state functional MRI, which were processed to obtain the structural and functional connectomes, respectively. Global and regional graph metrics were computed to evaluate network organization in both transgenic and control rats. The results pointed to a delay in learning the working memory-related task in the AD rats, which also completed a lower number of trials in the DNMS task. Regarding connectivity properties, less efficient organization of the structural brain networks of the transgenic rats with respect to controls was observed. Specific regional differences in connectivity were identified in both structural and functional networks. In addition, a strong correlation was observed between cognitive performance and brain networks, including whole-brain structural connectivity as well as functional and structural network metrics of regions related to memory and reward processes. In this study, connectivity and neurocognitive impairments were identified in TgF344-AD rats at a very early stage of the disease when most of the pathological hallmarks have not yet been detected. Structural and functional network metrics of regions related to reward, memory, and sensory performance were strongly correlated with the cognitive outcome. The use of animal models is essential for the early identification of these alterations and can contribute to the development of early biomarkers of the disease based on MRI connectomics.

Learning spatially coherent properties of the visual world in connectionist networks

NASA Astrophysics Data System (ADS)

Becker, Suzanna; Hinton, Geoffrey E.

1991-10-01

In the unsupervised learning paradigm, a network of neuron-like units is presented with an ensemble of input patterns from a structured environment, such as the visual world, and learns to represent the regularities in that input. The major goal in developing unsupervised learning algorithms is to find objective functions that characterize the quality of the network's representation without explicitly specifying the desired outputs of any of the units. The sort of objective functions considered cause a unit to become tuned to spatially coherent features of visual images (such as texture, depth, shading, and surface orientation), by learning to predict the outputs of other units which have spatially adjacent receptive fields. Simulations show that using an information-theoretic algorithm called IMAX, a network can be trained to represent depth by observing random dot stereograms of surfaces with continuously varying disparities. Once a layer of depth-tuned units has developed, subsequent layers are trained to perform surface interpolation of curved surfaces, by learning to predict the depth of one image region based on depth measurements in surrounding regions. An extension of the basic model allows a population of competing neurons to learn a distributed code for disparity, which naturally gives rise to a representation of discontinuities.

Learning Bayesian Networks from Correlated Data

NASA Astrophysics Data System (ADS)

Bae, Harold; Monti, Stefano; Montano, Monty; Steinberg, Martin H.; Perls, Thomas T.; Sebastiani, Paola

2016-05-01

Bayesian networks are probabilistic models that represent complex distributions in a modular way and have become very popular in many fields. There are many methods to build Bayesian networks from a random sample of independent and identically distributed observations. However, many observational studies are designed using some form of clustered sampling that introduces correlations between observations within the same cluster and ignoring this correlation typically inflates the rate of false positive associations. We describe a novel parameterization of Bayesian networks that uses random effects to model the correlation within sample units and can be used for structure and parameter learning from correlated data without inflating the Type I error rate. We compare different learning metrics using simulations and illustrate the method in two real examples: an analysis of genetic and non-genetic factors associated with human longevity from a family-based study, and an example of risk factors for complications of sickle cell anemia from a longitudinal study with repeated measures.

Fixed Point Learning Based Intelligent Traffic Control System

NASA Astrophysics Data System (ADS)

Zongyao, Wang; Cong, Sui; Cheng, Shao

2017-10-01

Fixed point learning has become an important tool to analyse large scale distributed system such as urban traffic network. This paper presents a fixed point learning based intelligence traffic network control system. The system applies convergence property of fixed point theorem to optimize the traffic flow density. The intelligence traffic control system achieves maximum road resources usage by averaging traffic flow density among the traffic network. The intelligence traffic network control system is built based on decentralized structure and intelligence cooperation. No central control is needed to manage the system. The proposed system is simple, effective and feasible for practical use. The performance of the system is tested via theoretical proof and simulations. The results demonstrate that the system can effectively solve the traffic congestion problem and increase the vehicles average speed. It also proves that the system is flexible, reliable and feasible for practical use.

A Theory of How Columns in the Neocortex Enable Learning the Structure of the World

PubMed Central

Hawkins, Jeff; Ahmad, Subutai; Cui, Yuwei

2017-01-01

Neocortical regions are organized into columns and layers. Connections between layers run mostly perpendicular to the surface suggesting a columnar functional organization. Some layers have long-range excitatory lateral connections suggesting interactions between columns. Similar patterns of connectivity exist in all regions but their exact role remain a mystery. In this paper, we propose a network model composed of columns and layers that performs robust object learning and recognition. Each column integrates its changing input over time to learn complete predictive models of observed objects. Excitatory lateral connections across columns allow the network to more rapidly infer objects based on the partial knowledge of adjacent columns. Because columns integrate input over time and space, the network learns models of complex objects that extend well beyond the receptive field of individual cells. Our network model introduces a new feature to cortical columns. We propose that a representation of location relative to the object being sensed is calculated within the sub-granular layers of each column. The location signal is provided as an input to the network, where it is combined with sensory data. Our model contains two layers and one or more columns. Simulations show that using Hebbian-like learning rules small single-column networks can learn to recognize hundreds of objects, with each object containing tens of features. Multi-column networks recognize objects with significantly fewer movements of the sensory receptors. Given the ubiquity of columnar and laminar connectivity patterns throughout the neocortex, we propose that columns and regions have more powerful recognition and modeling capabilities than previously assumed. PMID:29118696

Direct heuristic dynamic programming for damping oscillations in a large power system.

PubMed

Lu, Chao; Si, Jennie; Xie, Xiaorong

2008-08-01

This paper applies a neural-network-based approximate dynamic programming method, namely, the direct heuristic dynamic programming (direct HDP), to a large power system stability control problem. The direct HDP is a learning- and approximation-based approach to addressing nonlinear coordinated control under uncertainty. One of the major design parameters, the controller learning objective function, is formulated to directly account for network-wide low-frequency oscillation with the presence of nonlinearity, uncertainty, and coupling effect among system components. Results include a novel learning control structure based on the direct HDP with applications to two power system problems. The first case involves static var compensator supplementary damping control, which is used to provide a comprehensive evaluation of the learning control performance. The second case aims at addressing a difficult complex system challenge by providing a new solution to a large interconnected power network oscillation damping control problem that frequently occurs in the China Southern Power Grid.

Face recognition via Gabor and convolutional neural network

NASA Astrophysics Data System (ADS)

Lu, Tongwei; Wu, Menglu; Lu, Tao

2018-04-01

In recent years, the powerful feature learning and classification ability of convolutional neural network have attracted widely attention. Compared with the deep learning, the traditional machine learning algorithm has a good explanatory which deep learning does not have. Thus, In this paper, we propose a method to extract the feature of the traditional algorithm as the input of convolution neural network. In order to reduce the complexity of the network, the kernel function of Gabor wavelet is used to extract the feature from different position, frequency and direction of target image. It is sensitive to edge of image which can provide good direction and scale selection. The extraction of the image from eight directions on a scale are as the input of network that we proposed. The network have the advantage of weight sharing and local connection and texture feature of the input image can reduce the influence of facial expression, gesture and illumination. At the same time, we introduced a layer which combined the results of the pooling and convolution can extract deeper features. The training network used the open source caffe framework which is beneficial to feature extraction. The experiment results of the proposed method proved that the network structure effectively overcame the barrier of illumination and had a good robustness as well as more accurate and rapid than the traditional algorithm.

A renaissance of neural networks in drug discovery.

PubMed

Baskin, Igor I; Winkler, David; Tetko, Igor V

2016-08-01

Neural networks are becoming a very popular method for solving machine learning and artificial intelligence problems. The variety of neural network types and their application to drug discovery requires expert knowledge to choose the most appropriate approach. In this review, the authors discuss traditional and newly emerging neural network approaches to drug discovery. Their focus is on backpropagation neural networks and their variants, self-organizing maps and associated methods, and a relatively new technique, deep learning. The most important technical issues are discussed including overfitting and its prevention through regularization, ensemble and multitask modeling, model interpretation, and estimation of applicability domain. Different aspects of using neural networks in drug discovery are considered: building structure-activity models with respect to various targets; predicting drug selectivity, toxicity profiles, ADMET and physicochemical properties; characteristics of drug-delivery systems and virtual screening. Neural networks continue to grow in importance for drug discovery. Recent developments in deep learning suggests further improvements may be gained in the analysis of large chemical data sets. It's anticipated that neural networks will be more widely used in drug discovery in the future, and applied in non-traditional areas such as drug delivery systems, biologically compatible materials, and regenerative medicine.

Synthetic Modeling of Autonomous Learning with a Chaotic Neural Network

NASA Astrophysics Data System (ADS)

Funabashi, Masatoshi

We investigate the possible role of intermittent chaotic dynamics called chaotic itinerancy, in interaction with nonsupervised learnings that reinforce and weaken the neural connection depending on the dynamics itself. We first performed hierarchical stability analysis of the Chaotic Neural Network model (CNN) according to the structure of invariant subspaces. Irregular transition between two attractor ruins with positive maximum Lyapunov exponent was triggered by the blowout bifurcation of the attractor spaces, and was associated with riddled basins structure. We secondly modeled two autonomous learnings, Hebbian learning and spike-timing-dependent plasticity (STDP) rule, and simulated the effect on the chaotic itinerancy state of CNN. Hebbian learning increased the residence time on attractor ruins, and produced novel attractors in the minimum higher-dimensional subspace. It also augmented the neuronal synchrony and established the uniform modularity in chaotic itinerancy. STDP rule reduced the residence time on attractor ruins, and brought a wide range of periodicity in emerged attractors, possibly including strange attractors. Both learning rules selectively destroyed and preserved the specific invariant subspaces, depending on the neuron synchrony of the subspace where the orbits are situated. Computational rationale of the autonomous learning is discussed in connectionist perspective.

Computational modeling of spiking neural network with learning rules from STDP and intrinsic plasticity

NASA Astrophysics Data System (ADS)

Li, Xiumin; Wang, Wei; Xue, Fangzheng; Song, Yongduan

2018-02-01

Recently there has been continuously increasing interest in building up computational models of spiking neural networks (SNN), such as the Liquid State Machine (LSM). The biologically inspired self-organized neural networks with neural plasticity can enhance the capability of computational performance, with the characteristic features of dynamical memory and recurrent connection cycles which distinguish them from the more widely used feedforward neural networks. Despite a variety of computational models for brain-like learning and information processing have been proposed, the modeling of self-organized neural networks with multi-neural plasticity is still an important open challenge. The main difficulties lie in the interplay among different forms of neural plasticity rules and understanding how structures and dynamics of neural networks shape the computational performance. In this paper, we propose a novel approach to develop the models of LSM with a biologically inspired self-organizing network based on two neural plasticity learning rules. The connectivity among excitatory neurons is adapted by spike-timing-dependent plasticity (STDP) learning; meanwhile, the degrees of neuronal excitability are regulated to maintain a moderate average activity level by another learning rule: intrinsic plasticity (IP). Our study shows that LSM with STDP+IP performs better than LSM with a random SNN or SNN obtained by STDP alone. The noticeable improvement with the proposed method is due to the better reflected competition among different neurons in the developed SNN model, as well as the more effectively encoded and processed relevant dynamic information with its learning and self-organizing mechanism. This result gives insights to the optimization of computational models of spiking neural networks with neural plasticity.

Visualising the invisible: a network approach to reveal the informal social side of student learning.

PubMed

Hommes, J; Rienties, B; de Grave, W; Bos, G; Schuwirth, L; Scherpbier, A

2012-12-01

World-wide, universities in health sciences have transformed their curriculum to include collaborative learning and facilitate the students' learning process. Interaction has been acknowledged to be the synergistic element in this learning context. However, students spend the majority of their time outside their classroom and interaction does not stop outside the classroom. Therefore we studied how informal social interaction influences student learning. Moreover, to explore what really matters in the students learning process, a model was tested how the generally known important constructs-prior performance, motivation and social integration-relate to informal social interaction and student learning. 301 undergraduate medical students participated in this cross-sectional quantitative study. Informal social interaction was assessed using self-reported surveys following the network approach. Students' individual motivation, social integration and prior performance were assessed by the Academic Motivation Scale, the College Adaption Questionnaire and students' GPA respectively. A factual knowledge test represented student' learning. All social networks were positively associated with student learning significantly: friendships (β = 0.11), providing information to other students (β = 0.16), receiving information from other students (β = 0.25). Structural equation modelling revealed a model in which social networks increased student learning (r = 0.43), followed by prior performance (r = 0.31). In contrast to prior literature, students' academic motivation and social integration were not associated with students' learning. Students' informal social interaction is strongly associated with students' learning. These findings underline the need to change our focus from the formal context (classroom) to the informal context to optimize student learning and deliver modern medics.

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

PubMed Central

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

2014-01-01

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

Machine learning framework for analysis of transport through complex networks in porous, granular media: A focus on permeability

NASA Astrophysics Data System (ADS)

van der Linden, Joost H.; Narsilio, Guillermo A.; Tordesillas, Antoinette

2016-08-01

We present a data-driven framework to study the relationship between fluid flow at the macroscale and the internal pore structure, across the micro- and mesoscales, in porous, granular media. Sphere packings with varying particle size distribution and confining pressure are generated using the discrete element method. For each sample, a finite element analysis of the fluid flow is performed to compute the permeability. We construct a pore network and a particle contact network to quantify the connectivity of the pores and particles across the mesoscopic spatial scales. Machine learning techniques for feature selection are employed to identify sets of microstructural properties and multiscale complex network features that optimally characterize permeability. We find a linear correlation (in log-log scale) between permeability and the average closeness centrality of the weighted pore network. With the pore network links weighted by the local conductance, the average closeness centrality represents a multiscale measure of efficiency of flow through the pore network in terms of the mean geodesic distance (or shortest path) between all pore bodies in the pore network. Specifically, this study objectively quantifies a hypothesized link between high permeability and efficient shortest paths that thread through relatively large pore bodies connected to each other by high conductance pore throats, embodying connectivity and pore structure.

Improving EEG-Based Driver Fatigue Classification Using Sparse-Deep Belief Networks.

PubMed

Chai, Rifai; Ling, Sai Ho; San, Phyo Phyo; Naik, Ganesh R; Nguyen, Tuan N; Tran, Yvonne; Craig, Ashley; Nguyen, Hung T

2017-01-01

This paper presents an improvement of classification performance for electroencephalography (EEG)-based driver fatigue classification between fatigue and alert states with the data collected from 43 participants. The system employs autoregressive (AR) modeling as the features extraction algorithm, and sparse-deep belief networks (sparse-DBN) as the classification algorithm. Compared to other classifiers, sparse-DBN is a semi supervised learning method which combines unsupervised learning for modeling features in the pre-training layer and supervised learning for classification in the following layer. The sparsity in sparse-DBN is achieved with a regularization term that penalizes a deviation of the expected activation of hidden units from a fixed low-level prevents the network from overfitting and is able to learn low-level structures as well as high-level structures. For comparison, the artificial neural networks (ANN), Bayesian neural networks (BNN), and original deep belief networks (DBN) classifiers are used. The classification results show that using AR feature extractor and DBN classifiers, the classification performance achieves an improved classification performance with a of sensitivity of 90.8%, a specificity of 90.4%, an accuracy of 90.6%, and an area under the receiver operating curve (AUROC) of 0.94 compared to ANN (sensitivity at 80.8%, specificity at 77.8%, accuracy at 79.3% with AUC-ROC of 0.83) and BNN classifiers (sensitivity at 84.3%, specificity at 83%, accuracy at 83.6% with AUROC of 0.87). Using the sparse-DBN classifier, the classification performance improved further with sensitivity of 93.9%, a specificity of 92.3%, and an accuracy of 93.1% with AUROC of 0.96. Overall, the sparse-DBN classifier improved accuracy by 13.8, 9.5, and 2.5% over ANN, BNN, and DBN classifiers, respectively.

Improving EEG-Based Driver Fatigue Classification Using Sparse-Deep Belief Networks

PubMed Central

Chai, Rifai; Ling, Sai Ho; San, Phyo Phyo; Naik, Ganesh R.; Nguyen, Tuan N.; Tran, Yvonne; Craig, Ashley; Nguyen, Hung T.

2017-01-01

This paper presents an improvement of classification performance for electroencephalography (EEG)-based driver fatigue classification between fatigue and alert states with the data collected from 43 participants. The system employs autoregressive (AR) modeling as the features extraction algorithm, and sparse-deep belief networks (sparse-DBN) as the classification algorithm. Compared to other classifiers, sparse-DBN is a semi supervised learning method which combines unsupervised learning for modeling features in the pre-training layer and supervised learning for classification in the following layer. The sparsity in sparse-DBN is achieved with a regularization term that penalizes a deviation of the expected activation of hidden units from a fixed low-level prevents the network from overfitting and is able to learn low-level structures as well as high-level structures. For comparison, the artificial neural networks (ANN), Bayesian neural networks (BNN), and original deep belief networks (DBN) classifiers are used. The classification results show that using AR feature extractor and DBN classifiers, the classification performance achieves an improved classification performance with a of sensitivity of 90.8%, a specificity of 90.4%, an accuracy of 90.6%, and an area under the receiver operating curve (AUROC) of 0.94 compared to ANN (sensitivity at 80.8%, specificity at 77.8%, accuracy at 79.3% with AUC-ROC of 0.83) and BNN classifiers (sensitivity at 84.3%, specificity at 83%, accuracy at 83.6% with AUROC of 0.87). Using the sparse-DBN classifier, the classification performance improved further with sensitivity of 93.9%, a specificity of 92.3%, and an accuracy of 93.1% with AUROC of 0.96. Overall, the sparse-DBN classifier improved accuracy by 13.8, 9.5, and 2.5% over ANN, BNN, and DBN classifiers, respectively. PMID:28326009

U.S. stock market interaction network as learned by the Boltzmann machine

DOE PAGES

Borysov, Stanislav S.; Roudi, Yasser; Balatsky, Alexander V.

2015-12-07

Here, we study historical dynamics of joint equilibrium distribution of stock returns in the U.S. stock market using the Boltzmann distribution model being parametrized by external fields and pairwise couplings. Within Boltzmann learning framework for statistical inference, we analyze historical behavior of the parameters inferred using exact and approximate learning algorithms. Since the model and inference methods require use of binary variables, effect of this mapping of continuous returns to the discrete domain is studied. The presented results show that binarization preserves the correlation structure of the market. Properties of distributions of external fields and couplings as well as themore » market interaction network and industry sector clustering structure are studied for different historical dates and moving window sizes. We demonstrate that the observed positive heavy tail in distribution of couplings is related to the sparse clustering structure of the market. We also show that discrepancies between the model’s parameters might be used as a precursor of financial instabilities.« less

Can Online Learning Communities Achieve the Goals of Traditional Professional Learning Communities? What the Literature Says. REL 2013-003

ERIC Educational Resources Information Center

Blitz, Cynthia L.

2013-01-01

For more than a decade practitioners have promoted professional learning communities (PLCs) as an effective structure for providing teachers with professional development (Chappuis, Chappuis, & Stiggins, 2009; DuFour, Eaker, & DuFour, 2005). These collaborative networks are believed to be effective because they expose teachers to new ideas…

Neonatal Odor-Shock Conditioning Alters the Neural Network Involved in Odor Fear Learning at Adulthood

ERIC Educational Resources Information Center

Sevelinges, Yannick; Sullivan, Regina M.; Messaoudi, Belkacem; Mouly, Anne-Marie

2008-01-01

Adult learning and memory functions are strongly dependent on neonatal experiences. We recently showed that neonatal odor-shock learning attenuates later life odor fear conditioning and amygdala activity. In the present work we investigated whether changes observed in adults can also be observed in other structures normally involved, namely…

Time, Space and Structure in an E-Learning and E-Mentoring Project

ERIC Educational Resources Information Center

Loureiro-Koechlin, Cecilia; Allan, Barbara

2010-01-01

This study focuses on a project, "EMPATHY Net-Works," which developed a learning community as a means of encouraging women to progress into employment and management positions in the logistics and supply chain industries (LaSCI). Learning activities were organised in the form of a taught module containing face-to-face and online elements and…

Relationships between music training, speech processing, and word learning: a network perspective.

PubMed

Elmer, Stefan; Jäncke, Lutz

2018-03-15

Numerous studies have documented the behavioral advantages conferred on professional musicians and children undergoing music training in processing speech sounds varying in the spectral and temporal dimensions. These beneficial effects have previously often been associated with local functional and structural changes in the auditory cortex (AC). However, this perspective is oversimplified, in that it does not take into account the intrinsic organization of the human brain, namely, neural networks and oscillatory dynamics. Therefore, we propose a new framework for extending these previous findings to a network perspective by integrating multimodal imaging, electrophysiology, and neural oscillations. In particular, we provide concrete examples of how functional and structural connectivity can be used to model simple neural circuits exerting a modulatory influence on AC activity. In addition, we describe how such a network approach can be used for better comprehending the beneficial effects of music training on more complex speech functions, such as word learning. © 2018 New York Academy of Sciences.

Deep Neural Network for Structural Prediction and Lane Detection in Traffic Scene.

PubMed

Li, Jun; Mei, Xue; Prokhorov, Danil; Tao, Dacheng

2017-03-01

Hierarchical neural networks have been shown to be effective in learning representative image features and recognizing object classes. However, most existing networks combine the low/middle level cues for classification without accounting for any spatial structures. For applications such as understanding a scene, how the visual cues are spatially distributed in an image becomes essential for successful analysis. This paper extends the framework of deep neural networks by accounting for the structural cues in the visual signals. In particular, two kinds of neural networks have been proposed. First, we develop a multitask deep convolutional network, which simultaneously detects the presence of the target and the geometric attributes (location and orientation) of the target with respect to the region of interest. Second, a recurrent neuron layer is adopted for structured visual detection. The recurrent neurons can deal with the spatial distribution of visible cues belonging to an object whose shape or structure is difficult to explicitly define. Both the networks are demonstrated by the practical task of detecting lane boundaries in traffic scenes. The multitask convolutional neural network provides auxiliary geometric information to help the subsequent modeling of the given lane structures. The recurrent neural network automatically detects lane boundaries, including those areas containing no marks, without any explicit prior knowledge or secondary modeling.

The dynamic programming high-order Dynamic Bayesian Networks learning for identifying effective connectivity in human brain from fMRI.

PubMed

Dang, Shilpa; Chaudhury, Santanu; Lall, Brejesh; Roy, Prasun Kumar

2017-06-15

Determination of effective connectivity (EC) among brain regions using fMRI is helpful in understanding the underlying neural mechanisms. Dynamic Bayesian Networks (DBNs) are an appropriate class of probabilistic graphical temporal-models that have been used in past to model EC from fMRI, specifically order-one. High-order DBNs (HO-DBNs) have still not been explored for fMRI data. A fundamental problem faced in the structure-learning of HO-DBN is high computational-burden and low accuracy by the existing heuristic search techniques used for EC detection from fMRI. In this paper, we propose using dynamic programming (DP) principle along with integration of properties of scoring-function in a way to reduce search space for structure-learning of HO-DBNs and finally, for identifying EC from fMRI which has not been done yet to the best of our knowledge. The proposed exact search-&-score learning approach HO-DBN-DP is an extension of the technique which was originally devised for learning a BN's structure from static data (Singh and Moore, 2005). The effectiveness in structure-learning is shown on synthetic fMRI dataset. The algorithm reaches globally-optimal solution in appreciably reduced time-complexity than the static counterpart due to integration of properties. The proof of optimality is provided. The results demonstrate that HO-DBN-DP is comparably more accurate and faster than currently used structure-learning algorithms used for identifying EC from fMRI. The real data EC from HO-DBN-DP shows consistency with previous literature than the classical Granger Causality method. Hence, the DP algorithm can be employed for reliable EC estimates from experimental fMRI data. Copyright © 2017 Elsevier B.V. All rights reserved.

Learning of goal-relevant and -irrelevant complex visual sequences in human V1.

PubMed

Rosenthal, Clive R; Mallik, Indira; Caballero-Gaudes, Cesar; Sereno, Martin I; Soto, David

2018-06-12

Learning and memory are supported by a network involving the medial temporal lobe and linked neocortical regions. Emerging evidence indicates that primary visual cortex (i.e., V1) may contribute to recognition memory, but this has been tested only with a single visuospatial sequence as the target memorandum. The present study used functional magnetic resonance imaging to investigate whether human V1 can support the learning of multiple, concurrent complex visual sequences involving discontinous (second-order) associations. Two peripheral, goal-irrelevant but structured sequences of orientated gratings appeared simultaneously in fixed locations of the right and left visual fields alongside a central, goal-relevant sequence that was in the focus of spatial attention. Pseudorandom sequences were introduced at multiple intervals during the presentation of the three structured visual sequences to provide an online measure of sequence-specific knowledge at each retinotopic location. We found that a network involving the precuneus and V1 was involved in learning the structured sequence presented at central fixation, whereas right V1 was modulated by repeated exposure to the concurrent structured sequence presented in the left visual field. The same result was not found in left V1. These results indicate for the first time that human V1 can support the learning of multiple concurrent sequences involving complex discontinuous inter-item associations, even peripheral sequences that are goal-irrelevant. Copyright © 2018. Published by Elsevier Inc.

Emergence of network structure due to spike-timing-dependent plasticity in recurrent neuronal networks IV: structuring synaptic pathways among recurrent connections.

PubMed

Gilson, Matthieu; Burkitt, Anthony N; Grayden, David B; Thomas, Doreen A; van Hemmen, J Leo

2009-12-01

In neuronal networks, the changes of synaptic strength (or weight) performed by spike-timing-dependent plasticity (STDP) are hypothesized to give rise to functional network structure. This article investigates how this phenomenon occurs for the excitatory recurrent connections of a network with fixed input weights that is stimulated by external spike trains. We develop a theoretical framework based on the Poisson neuron model to analyze the interplay between the neuronal activity (firing rates and the spike-time correlations) and the learning dynamics, when the network is stimulated by correlated pools of homogeneous Poisson spike trains. STDP can lead to both a stabilization of all the neuron firing rates (homeostatic equilibrium) and a robust weight specialization. The pattern of specialization for the recurrent weights is determined by a relationship between the input firing-rate and correlation structures, the network topology, the STDP parameters and the synaptic response properties. We find conditions for feed-forward pathways or areas with strengthened self-feedback to emerge in an initially homogeneous recurrent network.

Developmental Evaluation Framework for Innovation and Learning Networks: Integration of the Structure, Process and Outcomes

ERIC Educational Resources Information Center

Ramstad, Elise

2009-01-01

Purpose: During the past decade new types of broader networks that aim to achieve widespread effects in the working life have emerged. These are typically based on an interactive innovation approach, where knowledge is created jointly together with diverse players. At the moment, the challenge is how to evaluate these complex networks and learning…

Second language social networks and communication-related acculturative stress: the role of interconnectedness

PubMed Central

Doucerain, Marina M.; Varnaamkhaasti, Raheleh S.; Segalowitz, Norman; Ryder, Andrew G.

2015-01-01

Although a substantial amount of cross-cultural psychology research has investigated acculturative stress in general, little attention has been devoted specifically to communication-related acculturative stress (CRAS). In line with the view that cross-cultural adaptation and second language (L2) learning are social and interpersonal phenomena, the present study examines the hypothesis that migrants’ L2 social network size and interconnectedness predict CRAS. The main idea underlying this hypothesis is that L2 social networks play an important role in fostering social and cultural aspects of communicative competence. Specifically, higher interconnectedness may reflect greater access to unmodified natural cultural representations and L2 communication practices, thus fostering communicative competence through observational learning. As such, structural aspects of migrants’ L2 social networks may be protective against acculturative stress arising from chronic communication difficulties. Results from a study of first generation migrant students (N = 100) support this idea by showing that both inclusiveness and density of the participants’ L2 network account for unique variance in CRAS but not in general acculturative stress. These results support the idea that research on cross-cultural adaptation would benefit from disentangling the various facets of acculturative stress and that the structure of migrants’ L2 network matters for language related outcomes. Finally, this study contributes to an emerging body of work that attempts to integrate cultural/cross-cultural research on acculturation and research on intercultural communication and second language learning. PMID:26300809

Second language social networks and communication-related acculturative stress: the role of interconnectedness.

PubMed

Doucerain, Marina M; Varnaamkhaasti, Raheleh S; Segalowitz, Norman; Ryder, Andrew G

2015-01-01

Although a substantial amount of cross-cultural psychology research has investigated acculturative stress in general, little attention has been devoted specifically to communication-related acculturative stress (CRAS). In line with the view that cross-cultural adaptation and second language (L2) learning are social and interpersonal phenomena, the present study examines the hypothesis that migrants' L2 social network size and interconnectedness predict CRAS. The main idea underlying this hypothesis is that L2 social networks play an important role in fostering social and cultural aspects of communicative competence. Specifically, higher interconnectedness may reflect greater access to unmodified natural cultural representations and L2 communication practices, thus fostering communicative competence through observational learning. As such, structural aspects of migrants' L2 social networks may be protective against acculturative stress arising from chronic communication difficulties. Results from a study of first generation migrant students (N = 100) support this idea by showing that both inclusiveness and density of the participants' L2 network account for unique variance in CRAS but not in general acculturative stress. These results support the idea that research on cross-cultural adaptation would benefit from disentangling the various facets of acculturative stress and that the structure of migrants' L2 network matters for language related outcomes. Finally, this study contributes to an emerging body of work that attempts to integrate cultural/cross-cultural research on acculturation and research on intercultural communication and second language learning.

Structural limitations of learning in a crowd: communication vulnerability and information diffusion in MOOCs.

PubMed

Gillani, Nabeel; Yasseri, Taha; Eynon, Rebecca; Hjorth, Isis

2014-09-23

Massive Open Online Courses (MOOCs) bring together a global crowd of thousands of learners for several weeks or months. In theory, the openness and scale of MOOCs can promote iterative dialogue that facilitates group cognition and knowledge construction. Using data from two successive instances of a popular business strategy MOOC, we filter observed communication patterns to arrive at the "significant" interaction networks between learners and use complex network analysis to explore the vulnerability and information diffusion potential of the discussion forums. We find that different discussion topics and pedagogical practices promote varying levels of 1) "significant" peer-to-peer engagement, 2) participant inclusiveness in dialogue, and ultimately, 3) modularity, which impacts information diffusion to prevent a truly "global" exchange of knowledge and learning. These results indicate the structural limitations of large-scale crowd-based learning and highlight the different ways that learners in MOOCs leverage, and learn within, social contexts. We conclude by exploring how these insights may inspire new developments in online education.

Structural limitations of learning in a crowd: communication vulnerability and information diffusion in MOOCs

PubMed Central

Gillani, Nabeel; Yasseri, Taha; Eynon, Rebecca; Hjorth, Isis

2014-01-01

Massive Open Online Courses (MOOCs) bring together a global crowd of thousands of learners for several weeks or months. In theory, the openness and scale of MOOCs can promote iterative dialogue that facilitates group cognition and knowledge construction. Using data from two successive instances of a popular business strategy MOOC, we filter observed communication patterns to arrive at the “significant” interaction networks between learners and use complex network analysis to explore the vulnerability and information diffusion potential of the discussion forums. We find that different discussion topics and pedagogical practices promote varying levels of 1) “significant” peer-to-peer engagement, 2) participant inclusiveness in dialogue, and ultimately, 3) modularity, which impacts information diffusion to prevent a truly “global” exchange of knowledge and learning. These results indicate the structural limitations of large-scale crowd-based learning and highlight the different ways that learners in MOOCs leverage, and learn within, social contexts. We conclude by exploring how these insights may inspire new developments in online education. PMID:25244925

Structural limitations of learning in a crowd: communication vulnerability and information diffusion in MOOCs

NASA Astrophysics Data System (ADS)

Gillani, Nabeel; Yasseri, Taha; Eynon, Rebecca; Hjorth, Isis

2014-09-01

Massive Open Online Courses (MOOCs) bring together a global crowd of thousands of learners for several weeks or months. In theory, the openness and scale of MOOCs can promote iterative dialogue that facilitates group cognition and knowledge construction. Using data from two successive instances of a popular business strategy MOOC, we filter observed communication patterns to arrive at the ``significant'' interaction networks between learners and use complex network analysis to explore the vulnerability and information diffusion potential of the discussion forums. We find that different discussion topics and pedagogical practices promote varying levels of 1) ``significant'' peer-to-peer engagement, 2) participant inclusiveness in dialogue, and ultimately, 3) modularity, which impacts information diffusion to prevent a truly ``global'' exchange of knowledge and learning. These results indicate the structural limitations of large-scale crowd-based learning and highlight the different ways that learners in MOOCs leverage, and learn within, social contexts. We conclude by exploring how these insights may inspire new developments in online education.

Synchrony detection and amplification by silicon neurons with STDP synapses.

PubMed

Bofill-i-petit, Adria; Murray, Alan F

2004-09-01

Spike-timing dependent synaptic plasticity (STDP) is a form of plasticity driven by precise spike-timing differences between presynaptic and postsynaptic spikes. Thus, the learning rules underlying STDP are suitable for learning neuronal temporal phenomena such as spike-timing synchrony. It is well known that weight-independent STDP creates unstable learning processes resulting in balanced bimodal weight distributions. In this paper, we present a neuromorphic analog very large scale integration (VLSI) circuit that contains a feedforward network of silicon neurons with STDP synapses. The learning rule implemented can be tuned to have a moderate level of weight dependence. This helps stabilise the learning process and still generates binary weight distributions. From on-chip learning experiments we show that the chip can detect and amplify hierarchical spike-timing synchrony structures embedded in noisy spike trains. The weight distributions of the network emerging from learning are bimodal.

Real time unsupervised learning of visual stimuli in neuromorphic VLSI systems

NASA Astrophysics Data System (ADS)

Giulioni, Massimiliano; Corradi, Federico; Dante, Vittorio; Del Giudice, Paolo

2015-10-01

Neuromorphic chips embody computational principles operating in the nervous system, into microelectronic devices. In this domain it is important to identify computational primitives that theory and experiments suggest as generic and reusable cognitive elements. One such element is provided by attractor dynamics in recurrent networks. Point attractors are equilibrium states of the dynamics (up to fluctuations), determined by the synaptic structure of the network; a ‘basin’ of attraction comprises all initial states leading to a given attractor upon relaxation, hence making attractor dynamics suitable to implement robust associative memory. The initial network state is dictated by the stimulus, and relaxation to the attractor state implements the retrieval of the corresponding memorized prototypical pattern. In a previous work we demonstrated that a neuromorphic recurrent network of spiking neurons and suitably chosen, fixed synapses supports attractor dynamics. Here we focus on learning: activating on-chip synaptic plasticity and using a theory-driven strategy for choosing network parameters, we show that autonomous learning, following repeated presentation of simple visual stimuli, shapes a synaptic connectivity supporting stimulus-selective attractors. Associative memory develops on chip as the result of the coupled stimulus-driven neural activity and ensuing synaptic dynamics, with no artificial separation between learning and retrieval phases.

Real time unsupervised learning of visual stimuli in neuromorphic VLSI systems.

PubMed

Giulioni, Massimiliano; Corradi, Federico; Dante, Vittorio; del Giudice, Paolo

2015-10-14

Neuromorphic chips embody computational principles operating in the nervous system, into microelectronic devices. In this domain it is important to identify computational primitives that theory and experiments suggest as generic and reusable cognitive elements. One such element is provided by attractor dynamics in recurrent networks. Point attractors are equilibrium states of the dynamics (up to fluctuations), determined by the synaptic structure of the network; a 'basin' of attraction comprises all initial states leading to a given attractor upon relaxation, hence making attractor dynamics suitable to implement robust associative memory. The initial network state is dictated by the stimulus, and relaxation to the attractor state implements the retrieval of the corresponding memorized prototypical pattern. In a previous work we demonstrated that a neuromorphic recurrent network of spiking neurons and suitably chosen, fixed synapses supports attractor dynamics. Here we focus on learning: activating on-chip synaptic plasticity and using a theory-driven strategy for choosing network parameters, we show that autonomous learning, following repeated presentation of simple visual stimuli, shapes a synaptic connectivity supporting stimulus-selective attractors. Associative memory develops on chip as the result of the coupled stimulus-driven neural activity and ensuing synaptic dynamics, with no artificial separation between learning and retrieval phases.

Cooperative learning neural network output feedback control of uncertain nonlinear multi-agent systems under directed topologies

NASA Astrophysics Data System (ADS)

Wang, W.; Wang, D.; Peng, Z. H.

2017-09-01

Without assuming that the communication topologies among the neural network (NN) weights are to be undirected and the states of each agent are measurable, the cooperative learning NN output feedback control is addressed for uncertain nonlinear multi-agent systems with identical structures in strict-feedback form. By establishing directed communication topologies among NN weights to share their learned knowledge, NNs with cooperative learning laws are employed to identify the uncertainties. By designing NN-based κ-filter observers to estimate the unmeasurable states, a new cooperative learning output feedback control scheme is proposed to guarantee that the system outputs can track nonidentical reference signals with bounded tracking errors. A simulation example is given to demonstrate the effectiveness of the theoretical results.

Deep Learning for Computer Vision: A Brief Review

PubMed Central

Doulamis, Nikolaos; Doulamis, Anastasios; Protopapadakis, Eftychios

2018-01-01

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

Deep Learning and Its Applications in Biomedicine.

PubMed

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

2018-02-01

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

Neuronal avalanches of a self-organized neural network with active-neuron-dominant structure.

PubMed

Li, Xiumin; Small, Michael

2012-06-01

Neuronal avalanche is a spontaneous neuronal activity which obeys a power-law distribution of population event sizes with an exponent of -3/2. It has been observed in the superficial layers of cortex both in vivo and in vitro. In this paper, we analyze the information transmission of a novel self-organized neural network with active-neuron-dominant structure. Neuronal avalanches can be observed in this network with appropriate input intensity. We find that the process of network learning via spike-timing dependent plasticity dramatically increases the complexity of network structure, which is finally self-organized to be active-neuron-dominant connectivity. Both the entropy of activity patterns and the complexity of their resulting post-synaptic inputs are maximized when the network dynamics are propagated as neuronal avalanches. This emergent topology is beneficial for information transmission with high efficiency and also could be responsible for the large information capacity of this network compared with alternative archetypal networks with different neural connectivity.

Structural reliability calculation method based on the dual neural network and direct integration method.

PubMed

Li, Haibin; He, Yun; Nie, Xiaobo

2018-01-01

Structural reliability analysis under uncertainty is paid wide attention by engineers and scholars due to reflecting the structural characteristics and the bearing actual situation. The direct integration method, started from the definition of reliability theory, is easy to be understood, but there are still mathematics difficulties in the calculation of multiple integrals. Therefore, a dual neural network method is proposed for calculating multiple integrals in this paper. Dual neural network consists of two neural networks. The neural network A is used to learn the integrand function, and the neural network B is used to simulate the original function. According to the derivative relationships between the network output and the network input, the neural network B is derived from the neural network A. On this basis, the performance function of normalization is employed in the proposed method to overcome the difficulty of multiple integrations and to improve the accuracy for reliability calculations. The comparisons between the proposed method and Monte Carlo simulation method, Hasofer-Lind method, the mean value first-order second moment method have demonstrated that the proposed method is an efficient and accurate reliability method for structural reliability problems.

Airport Flight Departure Delay Model on Improved BN Structure Learning

NASA Astrophysics Data System (ADS)

Cao, Weidong; Fang, Xiangnong

An high score prior genetic simulated annealing Bayesian network structure learning algorithm (HSPGSA) by combining genetic algorithm(GA) with simulated annealing algorithm(SAA) is developed. The new algorithm provides not only with strong global search capability of GA, but also with strong local hill climb search capability of SAA. The structure with the highest score is prior selected. In the mean time, structures with lower score are also could be choice. It can avoid efficiently prematurity problem by higher score individual wrong direct growing population. Algorithm is applied to flight departure delays analysis in a large hub airport. Based on the flight data a BN model is created. Experiments show that parameters learning can reflect departure delay.

Network formation: neighborhood structures, establishment costs, and distributed learning.

PubMed

Chasparis, Georgios C; Shamma, Jeff S

2013-12-01

We consider the problem of network formation in a distributed fashion. Network formation is modeled as a strategic-form game, where agents represent nodes that form and sever unidirectional links with other nodes and derive utilities from these links. Furthermore, agents can form links only with a limited set of neighbors. Agents trade off the benefit from links, which is determined by a distance-dependent reward function, and the cost of maintaining links. When each agent acts independently, trying to maximize its own utility function, we can characterize “stable” networks through the notion of Nash equilibrium. In fact, the introduced reward and cost functions lead to Nash equilibria (networks), which exhibit several desirable properties such as connectivity, bounded-hop diameter, and efficiency (i.e., minimum number of links). Since Nash networks may not necessarily be efficient, we also explore the possibility of “shaping” the set of Nash networks through the introduction of state-based utility functions. Such utility functions may represent dynamic phenomena such as establishment costs (either positive or negative). Finally, we show how Nash networks can be the outcome of a distributed learning process. In particular, we extend previous learning processes to so-called “state-based” weakly acyclic games, and we show that the proposed network formation games belong to this class of games.

Machine Learning and Network Analysis of Molecular Dynamics Trajectories Reveal Two Chains of Red/Ox-specific Residue Interactions in Human Protein Disulfide Isomerase.

PubMed

Karamzadeh, Razieh; Karimi-Jafari, Mohammad Hossein; Sharifi-Zarchi, Ali; Chitsaz, Hamidreza; Salekdeh, Ghasem Hosseini; Moosavi-Movahedi, Ali Akbar

2017-06-16

The human protein disulfide isomerase (hPDI), is an essential four-domain multifunctional enzyme. As a result of disulfide shuffling in its terminal domains, hPDI exists in two oxidation states with different conformational preferences which are important for substrate binding and functional activities. Here, we address the redox-dependent conformational dynamics of hPDI through molecular dynamics (MD) simulations. Collective domain motions are identified by the principal component analysis of MD trajectories and redox-dependent opening-closing structure variations are highlighted on projected free energy landscapes. Then, important structural features that exhibit considerable differences in dynamics of redox states are extracted by statistical machine learning methods. Mapping the structural variations to time series of residue interaction networks also provides a holistic representation of the dynamical redox differences. With emphasizing on persistent long-lasting interactions, an approach is proposed that compiled these time series networks to a single dynamic residue interaction network (DRIN). Differential comparison of DRIN in oxidized and reduced states reveals chains of residue interactions that represent potential allosteric paths between catalytic and ligand binding sites of hPDI.

Structure-based control of complex networks with nonlinear dynamics.

PubMed

Zañudo, Jorge Gomez Tejeda; Yang, Gang; Albert, Réka

2017-07-11

What can we learn about controlling a system solely from its underlying network structure? Here we adapt a recently developed framework for control of networks governed by a broad class of nonlinear dynamics that includes the major dynamic models of biological, technological, and social processes. This feedback-based framework provides realizable node overrides that steer a system toward any of its natural long-term dynamic behaviors, regardless of the specific functional forms and system parameters. We use this framework on several real networks, identify the topological characteristics that underlie the predicted node overrides, and compare its predictions to those of structural controllability in control theory. Finally, we demonstrate this framework's applicability in dynamic models of gene regulatory networks and identify nodes whose override is necessary for control in the general case but not in specific model instances.

Collaborative Internet Learning.

ERIC Educational Resources Information Center

Tate, Joanne

This paper describes pioneering in the area of telecommunications and the use of the Internet across the curriculum in Australian schools through the I*EARN (International Education and Resource Network). Topics discussed include: (1) changes to the traditional learning approach and school structure, including the role of the teacher and resource…

Network evolution induced by asynchronous stimuli through spike-timing-dependent plasticity.

PubMed

Yuan, Wu-Jie; Zhou, Jian-Fang; Zhou, Changsong

2013-01-01

In sensory neural system, external asynchronous stimuli play an important role in perceptual learning, associative memory and map development. However, the organization of structure and dynamics of neural networks induced by external asynchronous stimuli are not well understood. Spike-timing-dependent plasticity (STDP) is a typical synaptic plasticity that has been extensively found in the sensory systems and that has received much theoretical attention. This synaptic plasticity is highly sensitive to correlations between pre- and postsynaptic firings. Thus, STDP is expected to play an important role in response to external asynchronous stimuli, which can induce segregative pre- and postsynaptic firings. In this paper, we study the impact of external asynchronous stimuli on the organization of structure and dynamics of neural networks through STDP. We construct a two-dimensional spatial neural network model with local connectivity and sparseness, and use external currents to stimulate alternately on different spatial layers. The adopted external currents imposed alternately on spatial layers can be here regarded as external asynchronous stimuli. Through extensive numerical simulations, we focus on the effects of stimulus number and inter-stimulus timing on synaptic connecting weights and the property of propagation dynamics in the resulting network structure. Interestingly, the resulting feedforward structure induced by stimulus-dependent asynchronous firings and its propagation dynamics reflect both the underlying property of STDP. The results imply a possible important role of STDP in generating feedforward structure and collective propagation activity required for experience-dependent map plasticity in developing in vivo sensory pathways and cortices. The relevance of the results to cue-triggered recall of learned temporal sequences, an important cognitive function, is briefly discussed as well. Furthermore, this finding suggests a potential application for examining STDP by measuring neural population activity in a cultured neural network.

The application of the multi-alternative approach in active neural network models

NASA Astrophysics Data System (ADS)

Podvalny, S.; Vasiljev, E.

2017-02-01

The article refers to the construction of intelligent systems based artificial neuron networks are used. We discuss the basic properties of the non-compliance of artificial neuron networks and their biological prototypes. It is shown here that the main reason for these discrepancies is the structural immutability of the neuron network models in the learning process, that is, their passivity. Based on the modern understanding of the biological nervous system as a structured ensemble of nerve cells, it is proposed to abandon the attempts to simulate its work at the level of the elementary neurons functioning processes and proceed to the reproduction of the information structure of data storage and processing on the basis of the general enough evolutionary principles of multialternativity, i.e. the multi-level structural model, diversity and modularity. The implementation method of these principles is offered, using the faceted memory organization in the neuron network with the rearranging active structure. An example of the implementation of the active facet-type neuron network in the intellectual decision-making system in the conditions of critical events development in the electrical distribution system.

Neural network-based model reference adaptive control system.

PubMed

Patino, H D; Liu, D

2000-01-01

In this paper, an approach to model reference adaptive control based on neural networks is proposed and analyzed for a class of first-order continuous-time nonlinear dynamical systems. The controller structure can employ either a radial basis function network or a feedforward neural network to compensate adaptively the nonlinearities in the plant. A stable controller-parameter adjustment mechanism, which is determined using the Lyapunov theory, is constructed using a sigma-modification-type updating law. The evaluation of control error in terms of the neural network learning error is performed. That is, the control error converges asymptotically to a neighborhood of zero, whose size is evaluated and depends on the approximation error of the neural network. In the design and analysis of neural network-based control systems, it is important to take into account the neural network learning error and its influence on the control error of the plant. Simulation results showing the feasibility and performance of the proposed approach are given.

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

PubMed

Gharehbaghi, Arash; Linden, Maria

2017-10-12

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

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

PubMed

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

2013-01-01

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

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

PubMed Central

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

2013-01-01

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

Spatial-Temporal Dynamics of High-Resolution Animal Networks: What Can We Learn from Domestic Animals?

PubMed

Chen, Shi; Ilany, Amiyaal; White, Brad J; Sanderson, Michael W; Lanzas, Cristina

2015-01-01

Animal social network is the key to understand many ecological and epidemiological processes. We used real-time location system (RTLS) to accurately track cattle position, analyze their proximity networks, and tested the hypothesis of temporal stationarity and spatial homogeneity in these networks during different daily time periods and in different areas of the pen. The network structure was analyzed using global network characteristics (network density), subgroup clustering (modularity), triadic property (transitivity), and dyadic interactions (correlation coefficient from a quadratic assignment procedure) at hourly level. We demonstrated substantial spatial-temporal heterogeneity in these networks and potential link between indirect animal-environment contact and direct animal-animal contact. But such heterogeneity diminished if data were collected at lower spatial (aggregated at entire pen level) or temporal (aggregated at daily level) resolution. The network structure (described by the characteristics such as density, modularity, transitivity, etc.) also changed substantially at different time and locations. There were certain time (feeding) and location (hay) that the proximity network structures were more consistent based on the dyadic interaction analysis. These results reveal new insights for animal network structure and spatial-temporal dynamics, provide more accurate descriptions of animal social networks, and allow more accurate modeling of multiple (both direct and indirect) disease transmission pathways.

Centrality measures in temporal networks with time series analysis

NASA Astrophysics Data System (ADS)

Huang, Qiangjuan; Zhao, Chengli; Zhang, Xue; Wang, Xiaojie; Yi, Dongyun

2017-05-01

The study of identifying important nodes in networks has a wide application in different fields. However, the current researches are mostly based on static or aggregated networks. Recently, the increasing attention to networks with time-varying structure promotes the study of node centrality in temporal networks. In this paper, we define a supra-evolution matrix to depict the temporal network structure. With using of the time series analysis, the relationships between different time layers can be learned automatically. Based on the special form of the supra-evolution matrix, the eigenvector centrality calculating problem is turned into the calculation of eigenvectors of several low-dimensional matrices through iteration, which effectively reduces the computational complexity. Experiments are carried out on two real-world temporal networks, Enron email communication network and DBLP co-authorship network, the results of which show that our method is more efficient at discovering the important nodes than the common aggregating method.

Persistent homology of time-dependent functional networks constructed from coupled time series

NASA Astrophysics Data System (ADS)

Stolz, Bernadette J.; Harrington, Heather A.; Porter, Mason A.

2017-04-01

We use topological data analysis to study "functional networks" that we construct from time-series data from both experimental and synthetic sources. We use persistent homology with a weight rank clique filtration to gain insights into these functional networks, and we use persistence landscapes to interpret our results. Our first example uses time-series output from networks of coupled Kuramoto oscillators. Our second example consists of biological data in the form of functional magnetic resonance imaging data that were acquired from human subjects during a simple motor-learning task in which subjects were monitored for three days during a five-day period. With these examples, we demonstrate that (1) using persistent homology to study functional networks provides fascinating insights into their properties and (2) the position of the features in a filtration can sometimes play a more vital role than persistence in the interpretation of topological features, even though conventionally the latter is used to distinguish between signal and noise. We find that persistent homology can detect differences in synchronization patterns in our data sets over time, giving insight both on changes in community structure in the networks and on increased synchronization between brain regions that form loops in a functional network during motor learning. For the motor-learning data, persistence landscapes also reveal that on average the majority of changes in the network loops take place on the second of the three days of the learning process.

Dependency-based Siamese long short-term memory network for learning sentence representations

PubMed Central

Zhu, Wenhao; Ni, Jianyue; Wei, Baogang; Lu, Zhiguo

2018-01-01

Textual representations play an important role in the field of natural language processing (NLP). The efficiency of NLP tasks, such as text comprehension and information extraction, can be significantly improved with proper textual representations. As neural networks are gradually applied to learn the representation of words and phrases, fairly efficient models of learning short text representations have been developed, such as the continuous bag of words (CBOW) and skip-gram models, and they have been extensively employed in a variety of NLP tasks. Because of the complex structure generated by the longer text lengths, such as sentences, algorithms appropriate for learning short textual representations are not applicable for learning long textual representations. One method of learning long textual representations is the Long Short-Term Memory (LSTM) network, which is suitable for processing sequences. However, the standard LSTM does not adequately address the primary sentence structure (subject, predicate and object), which is an important factor for producing appropriate sentence representations. To resolve this issue, this paper proposes the dependency-based LSTM model (D-LSTM). The D-LSTM divides a sentence representation into two parts: a basic component and a supporting component. The D-LSTM uses a pre-trained dependency parser to obtain the primary sentence information and generate supporting components, and it also uses a standard LSTM model to generate the basic sentence components. A weight factor that can adjust the ratio of the basic and supporting components in a sentence is introduced to generate the sentence representation. Compared with the representation learned by the standard LSTM, the sentence representation learned by the D-LSTM contains a greater amount of useful information. The experimental results show that the D-LSTM is superior to the standard LSTM for sentences involving compositional knowledge (SICK) data. PMID:29513748

Exploring MEDLINE Space with Random Indexing and Pathfinder Networks

PubMed Central

Cohen, Trevor

2008-01-01

The integration of disparate research domains is a prerequisite for the success of the translational science initiative. MEDLINE abstracts contain content from a broad range of disciplines, presenting an opportunity for the development of methods able to integrate the knowledge they contain. Latent Semantic Analysis (LSA) and related methods learn human-like associations between terms from unannotated text. However, their computational and memory demands limits their ability to address a corpus of this size. Furthermore, visualization methods previously used in conjunction with LSA have limited ability to define the local structure of the associative networks LSA learns. This paper explores these issues by (1) processing the entire MEDLINE corpus using Random Indexing, a variant of LSA, and (2) exploring learned associations using Pathfinder Networks. Meaningful associations are inferred from MEDLINE, including a drug-disease association undetected by PUBMED search. PMID:18999236

Exploring MEDLINE space with random indexing and pathfinder networks.

PubMed

Cohen, Trevor

2008-11-06

The integration of disparate research domains is a prerequisite for the success of the translational science initiative. MEDLINE abstracts contain content from a broad range of disciplines, presenting an opportunity for the development of methods able to integrate the knowledge they contain. Latent Semantic Analysis (LSA) and related methods learn human-like associations between terms from unannotated text. However, their computational and memory demands limits their ability to address a corpus of this size. Furthermore, visualization methods previously used in conjunction with LSA have limited ability to define the local structure of the associative networks LSA learns. This paper explores these issues by (1) processing the entire MEDLINE corpus using Random Indexing, a variant of LSA, and (2) exploring learned associations using Pathfinder Networks. Meaningful associations are inferred from MEDLINE, including a drug-disease association undetected by PUBMED search.

Dynamic Information Networks: Geometry, Topology and Statistical Learning for the Articulation of Structure

DTIC Science & Technology

2015-06-23

T. Bates, S. Brocklebank, S. Pauls, and D.Rockmore, A spectral clustering approach to the structure of personality: contrasting the FFM and...A spectral clustering approach to the structure of personality: contrasting the FFM and HEXACO models, Journal of Research in Personality, Volume 57

A comparison of back propagation and Generalized Regression Neural Networks performance in neutron spectrometry.

PubMed

Martínez-Blanco, Ma Del Rosario; Ornelas-Vargas, Gerardo; Solís-Sánchez, Luis Octavio; Castañeda-Miranada, Rodrigo; Vega-Carrillo, Héctor René; Celaya-Padilla, José M; Garza-Veloz, Idalia; Martínez-Fierro, Margarita; Ortiz-Rodríguez, José Manuel

2016-11-01

The process of unfolding the neutron energy spectrum has been subject of research for many years. Monte Carlo, iterative methods, the bayesian theory, the principle of maximum entropy are some of the methods used. The drawbacks associated with traditional unfolding procedures have motivated the research of complementary approaches. Back Propagation Neural Networks (BPNN), have been applied with success in neutron spectrometry and dosimetry domains, however, the structure and learning parameters are factors that highly impact in the networks performance. In ANN domain, Generalized Regression Neural Network (GRNN) is one of the simplest neural networks in term of network architecture and learning algorithm. The learning is instantaneous, requiring no time for training. Opposite to BPNN, a GRNN would be formed instantly with just a 1-pass training on the development data. In the network development phase, the only hurdle is to optimize the hyper-parameter, which is known as sigma, governing the smoothness of the network. The aim of this work was to compare the performance of BPNN and GRNN in the solution of the neutron spectrometry problem. From results obtained it can be observed that despite the very similar results, GRNN performs better than BPNN. Copyright © 2016 Elsevier Ltd. All rights reserved.

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

PubMed

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

2015-04-01

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

Digging deeper on "deep" learning: A computational ecology approach.

PubMed

Buscema, Massimo; Sacco, Pier Luigi

2017-01-01

We propose an alternative approach to "deep" learning that is based on computational ecologies of structurally diverse artificial neural networks, and on dynamic associative memory responses to stimuli. Rather than focusing on massive computation of many different examples of a single situation, we opt for model-based learning and adaptive flexibility. Cross-fertilization of learning processes across multiple domains is the fundamental feature of human intelligence that must inform "new" artificial intelligence.

Use long short-term memory to enhance Internet of Things for combined sewer overflow monitoring

NASA Astrophysics Data System (ADS)

Zhang, Duo; Lindholm, Geir; Ratnaweera, Harsha

2018-01-01

Combined sewer overflow causes severe water pollution, urban flooding and reduced treatment plant efficiency. Understanding the behavior of CSO structures is vital for urban flooding prevention and overflow control. Neural networks have been extensively applied in water resource related fields. In this study, we collect data from an Internet of Things monitoring CSO structure and build different neural network models for simulating and predicting the water level of the CSO structure. Through a comparison of four different neural networks, namely multilayer perceptron (MLP), wavelet neural network (WNN), long short-term memory (LSTM) and gated recurrent unit (GRU), the LSTM and GRU present superior capabilities for multi-step-ahead time series prediction. Furthermore, GRU achieves prediction performances similar to LSTM with a quicker learning curve.

PatterNet: a system to learn compact physical design pattern representations for pattern-based analytics

NASA Astrophysics Data System (ADS)

Lutich, Andrey

2017-07-01

This research considers the problem of generating compact vector representations of physical design patterns for analytics purposes in semiconductor patterning domain. PatterNet uses a deep artificial neural network to learn mapping of physical design patterns to a compact Euclidean hyperspace. Distances among mapped patterns in this space correspond to dissimilarities among patterns defined at the time of the network training. Once the mapping network has been trained, PatterNet embeddings can be used as feature vectors with standard machine learning algorithms, and pattern search, comparison, and clustering become trivial problems. PatterNet is inspired by the concepts developed within the framework of generative adversarial networks as well as the FaceNet. Our method facilitates a deep neural network (DNN) to learn directly the compact representation by supplying it with pairs of design patterns and dissimilarity among these patterns defined by a user. In the simplest case, the dissimilarity is represented by an area of the XOR of two patterns. Important to realize that our PatterNet approach is very different to the methods developed for deep learning on image data. In contrast to "conventional" pictures, the patterns in the CAD world are the lists of polygon vertex coordinates. The method solely relies on the promise of deep learning to discover internal structure of the incoming data and learn its hierarchical representations. Artificial intelligence arising from the combination of PatterNet and clustering analysis very precisely follows intuition of patterning/optical proximity correction experts paving the way toward human-like and human-friendly engineering tools.

Direct Adaptive Aircraft Control Using Dynamic Cell Structure Neural Networks

NASA Technical Reports Server (NTRS)

Jorgensen, Charles C.

1997-01-01

A Dynamic Cell Structure (DCS) Neural Network was developed which learns topology representing networks (TRNS) of F-15 aircraft aerodynamic stability and control derivatives. The network is integrated into a direct adaptive tracking controller. The combination produces a robust adaptive architecture capable of handling multiple accident and off- nominal flight scenarios. This paper describes the DCS network and modifications to the parameter estimation procedure. The work represents one step towards an integrated real-time reconfiguration control architecture for rapid prototyping of new aircraft designs. Performance was evaluated using three off-line benchmarks and on-line nonlinear Virtual Reality simulation. Flight control was evaluated under scenarios including differential stabilator lock, soft sensor failure, control and stability derivative variations, and air turbulence.

eLoom and Flatland: specification, simulation and visualization engines for the study of arbitrary hierarchical neural architectures.

PubMed

Caudell, Thomas P; Xiao, Yunhai; Healy, Michael J

2003-01-01

eLoom is an open source graph simulation software tool, developed at the University of New Mexico (UNM), that enables users to specify and simulate neural network models. Its specification language and libraries enables users to construct and simulate arbitrary, potentially hierarchical network structures on serial and parallel processing systems. In addition, eLoom is integrated with UNM's Flatland, an open source virtual environments development tool to provide real-time visualizations of the network structure and activity. Visualization is a useful method for understanding both learning and computation in artificial neural networks. Through 3D animated pictorially representations of the state and flow of information in the network, a better understanding of network functionality is achieved. ART-1, LAPART-II, MLP, and SOM neural networks are presented to illustrate eLoom and Flatland's capabilities.

Automatic detection of anatomical regions in frontal x-ray images: comparing convolutional neural networks to random forest

NASA Astrophysics Data System (ADS)

Olory Agomma, R.; Vázquez, C.; Cresson, T.; De Guise, J.

2018-02-01

Most algorithms to detect and identify anatomical structures in medical images require either to be initialized close to the target structure, or to know that the structure is present in the image, or to be trained on a homogeneous database (e.g. all full body or all lower limbs). Detecting these structures when there is no guarantee that the structure is present in the image, or when the image database is heterogeneous (mixed configurations), is a challenge for automatic algorithms. In this work we compared two state-of-the-art machine learning techniques in order to determine which one is the most appropriate for predicting targets locations based on image patches. By knowing the position of thirteen landmarks points, labelled by an expert in EOS frontal radiography, we learn the displacement between salient points detected in the image and these thirteen landmarks. The learning step is carried out with a machine learning approach by exploring two methods: Convolutional Neural Network (CNN) and Random Forest (RF). The automatic detection of the thirteen landmarks points in a new image is then obtained by averaging the positions of each one of these thirteen landmarks estimated from all the salient points in the new image. We respectively obtain for CNN and RF, an average prediction error (both mean and standard deviation in mm) of 29 +/-18 and 30 +/- 21 for the thirteen landmarks points, indicating the approximate location of anatomical regions. On the other hand, the learning time is 9 days for CNN versus 80 minutes for RF. We provide a comparison of the results between the two machine learning approaches.

Characterization of emergent synaptic topologies in noisy neural networks

NASA Astrophysics Data System (ADS)

Miller, Aaron James

Learned behaviors are one of the key contributors to an animal's ultimate survival. It is widely believed that the brain's microcircuitry undergoes structural changes when a new behavior is learned. In particular, motor learning, during which an animal learns a sequence of muscular movements, often requires precisely-timed coordination between muscles and becomes very natural once ingrained. Experiments show that neurons in the motor cortex exhibit precisely-timed spike activity when performing a learned motor behavior, and constituent stereotypical elements of the behavior can last several hundred milliseconds. The subject of this manuscript concerns how organized synaptic structures that produce stereotypical spike sequences emerge from random, dynamical networks. After a brief introduction in Chapter 1, we begin Chapter 2 by introducing a spike-timing-dependent plasticity (STDP) rule that defines how the activity of the network drives changes in network topology. The rule is then applied to idealized networks of leaky integrate-and-fire neurons (LIF). These neurons are not subjected to the variability that typically characterize neurons in vivo. In noiseless networks, synapses develop closed loops of strong connectivity that reproduce stereotypical, precisely-timed spike patterns from an initially random network. We demonstrate the characteristics of the asymptotic synaptic configuration are dependent on the statistics of the initial random network. The spike timings of the neurons simulated in Chapter 2 are generated exactly by a computationally economical, nonlinear mapping which is extended to LIF neurons injected with fluctuating current in Chapter 3. Development of an economical mapping that incorporates noise provides a practical solution to the long simulation times required to produce asymptotic synaptic topologies in networks with STDP in the presence of realistic neuronal variability. The mapping relies on generating numerical solutions to the dynamics of a LIF neuron subjected to Gaussian white noise (GWN). The system reduces to the Ornstein-Uhlenbeck first passage time problem, the solution of which we build into the mapping method of Chapter 2. We demonstrate that simulations using the stochastic mapping have reduced computation time compared to traditional Runge-Kutta methods by more than a factor of 150. In Chapter 4, we use the stochastic mapping to study the dynamics of emerging synaptic topologies in noisy networks. With the addition of membrane noise, networks with dynamical synapses can admit states in which the distribution of the synaptic weights is static under spontaneous activity, but the random connectivity between neurons is dynamical. The widely cited problem of instabilities in networks with STDP is avoided with the implementation of a synaptic decay and an activation threshold on each synapse. When such networks are presented with stimulus modeled by a focused excitatory current, chain-like networks can emerge with the addition of an axon-remodeling plasticity rule, a topological constraint on the connectivity modeling the finite resources available to each neuron. The emergent topologies are the result of an iterative stochastic process. The dynamics of the growth process suggest a strong interplay between the network topology and the spike sequences they produce during development. Namely, the existence of an embedded spike sequence alters the distribution of synaptic weights through the entire network. The roles of model parameters that affect the interplay between network structure and activity are elucidated. Finally, we propose two mathematical growth models, which are complementary, that capture the essence of the growth dynamics observed in simulations. In Chapter 5, we present an extension of the stochastic mapping that allows the possibility of neuronal cooperation. We demonstrate that synaptic topologies admitting stereotypical sequences can emerge in yet higher, biologically realistic levels of membrane potential variability when neurons cooperate to innervate shared targets. The structure that is most robust to the variability is that of a synfire chain. The principles of growth dynamics detailed in Chapter 4 are the same that sculpt the emergent synfire topologies. We conclude by discussing avenues for extensions of these results.

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

Empirical Models of Social Learning in a Large, Evolving Network.

PubMed

Bener, Ayşe Başar; Çağlayan, Bora; Henry, Adam Douglas; Prałat, Paweł

2016-01-01

This paper advances theories of social learning through an empirical examination of how social networks change over time. Social networks are important for learning because they constrain individuals' access to information about the behaviors and cognitions of other people. Using data on a large social network of mobile device users over a one-month time period, we test three hypotheses: 1) attraction homophily causes individuals to form ties on the basis of attribute similarity, 2) aversion homophily causes individuals to delete existing ties on the basis of attribute dissimilarity, and 3) social influence causes individuals to adopt the attributes of others they share direct ties with. Statistical models offer varied degrees of support for all three hypotheses and show that these mechanisms are more complex than assumed in prior work. Although homophily is normally thought of as a process of attraction, people also avoid relationships with others who are different. These mechanisms have distinct effects on network structure. While social influence does help explain behavior, people tend to follow global trends more than they follow their friends.

Empirical Models of Social Learning in a Large, Evolving Network

PubMed Central

Bener, Ayşe Başar; Çağlayan, Bora; Henry, Adam Douglas; Prałat, Paweł

2016-01-01

This paper advances theories of social learning through an empirical examination of how social networks change over time. Social networks are important for learning because they constrain individuals’ access to information about the behaviors and cognitions of other people. Using data on a large social network of mobile device users over a one-month time period, we test three hypotheses: 1) attraction homophily causes individuals to form ties on the basis of attribute similarity, 2) aversion homophily causes individuals to delete existing ties on the basis of attribute dissimilarity, and 3) social influence causes individuals to adopt the attributes of others they share direct ties with. Statistical models offer varied degrees of support for all three hypotheses and show that these mechanisms are more complex than assumed in prior work. Although homophily is normally thought of as a process of attraction, people also avoid relationships with others who are different. These mechanisms have distinct effects on network structure. While social influence does help explain behavior, people tend to follow global trends more than they follow their friends. PMID:27701430

Active Semi-Supervised Community Detection Based on Must-Link and Cannot-Link Constraints

PubMed Central

Cheng, Jianjun; Leng, Mingwei; Li, Longjie; Zhou, Hanhai; Chen, Xiaoyun

2014-01-01

Community structure detection is of great importance because it can help in discovering the relationship between the function and the topology structure of a network. Many community detection algorithms have been proposed, but how to incorporate the prior knowledge in the detection process remains a challenging problem. In this paper, we propose a semi-supervised community detection algorithm, which makes full utilization of the must-link and cannot-link constraints to guide the process of community detection and thereby extracts high-quality community structures from networks. To acquire the high-quality must-link and cannot-link constraints, we also propose a semi-supervised component generation algorithm based on active learning, which actively selects nodes with maximum utility for the proposed semi-supervised community detection algorithm step by step, and then generates the must-link and cannot-link constraints by accessing a noiseless oracle. Extensive experiments were carried out, and the experimental results show that the introduction of active learning into the problem of community detection makes a success. Our proposed method can extract high-quality community structures from networks, and significantly outperforms other comparison methods. PMID:25329660

Searching for realism, structure and agency in Actor Network Theory.

PubMed

Elder-Vass, Dave

2008-09-01

Superficially, Actor Network Theory (ANT) and critical realism (CR) are radically opposed research traditions. Written from a realist perspective, this paper asks whether there might be a basis for finding common ground between these two traditions. It looks in turn at the questions of realism, structure, and agency, analysing the differences between the two perspectives and seeking to identify what each might learn from the other. Overall, the paper argues that there is a great deal that realists can learn from actor network theory; yet ANT remains stunted by its lack of a depth ontology. It fails to recognize the significance of mechanisms, and of their dependence on emergence, and thus lacks both dimensions of the depth that is characteristic of critical realism's ontology. This prevents ANT from recognizing the role and powers of social structure; but on the other hand, realists would do well to heed ANT's call for us to trace the connections through which structures are constantly made and remade. A lack of ontological depth also underpins ANT's practice of treating human and non-human actors symmetrically, yet this remains a valuable provocation to sociologists who neglect non-human entities entirely.

Community detection in complex networks using deep auto-encoded extreme learning machine

NASA Astrophysics Data System (ADS)

Wang, Feifan; Zhang, Baihai; Chai, Senchun; Xia, Yuanqing

2018-06-01

Community detection has long been a fascinating topic in complex networks since the community structure usually unveils valuable information of interest. The prevalence and evolution of deep learning and neural networks have been pushing forward the advancement in various research fields and also provide us numerous useful and off the shelf techniques. In this paper, we put the cascaded stacked autoencoders and the unsupervised extreme learning machine (ELM) together in a two-level embedding process and propose a novel community detection algorithm. Extensive comparison experiments in circumstances of both synthetic and real-world networks manifest the advantages of the proposed algorithm. On one hand, it outperforms the k-means clustering in terms of the accuracy and stability thus benefiting from the determinate dimensions of the ELM block and the integration of sparsity restrictions. On the other hand, it endures smaller complexity than the spectral clustering method on account of the shrinkage in time spent on the eigenvalue decomposition procedure.

Global adaptation in networks of selfish components: emergent associative memory at the system scale.

PubMed

Watson, Richard A; Mills, Rob; Buckley, C L

2011-01-01

In some circumstances complex adaptive systems composed of numerous self-interested agents can self-organize into structures that enhance global adaptation, efficiency, or function. However, the general conditions for such an outcome are poorly understood and present a fundamental open question for domains as varied as ecology, sociology, economics, organismic biology, and technological infrastructure design. In contrast, sufficient conditions for artificial neural networks to form structures that perform collective computational processes such as associative memory/recall, classification, generalization, and optimization are well understood. Such global functions within a single agent or organism are not wholly surprising, since the mechanisms (e.g., Hebbian learning) that create these neural organizations may be selected for this purpose; but agents in a multi-agent system have no obvious reason to adhere to such a structuring protocol or produce such global behaviors when acting from individual self-interest. However, Hebbian learning is actually a very simple and fully distributed habituation or positive feedback principle. Here we show that when self-interested agents can modify how they are affected by other agents (e.g., when they can influence which other agents they interact with), then, in adapting these inter-agent relationships to maximize their own utility, they will necessarily alter them in a manner homologous with Hebbian learning. Multi-agent systems with adaptable relationships will thereby exhibit the same system-level behaviors as neural networks under Hebbian learning. For example, improved global efficiency in multi-agent systems can be explained by the inherent ability of associative memory to generalize by idealizing stored patterns and/or creating new combinations of subpatterns. Thus distributed multi-agent systems can spontaneously exhibit adaptive global behaviors in the same sense, and by the same mechanism, as with the organizational principles familiar in connectionist models of organismic learning.

Honeycomb: Visual Analysis of Large Scale Social Networks

NASA Astrophysics Data System (ADS)

van Ham, Frank; Schulz, Hans-Jörg; Dimicco, Joan M.

The rise in the use of social network sites allows us to collect large amounts of user reported data on social structures and analysis of this data could provide useful insights for many of the social sciences. This analysis is typically the domain of Social Network Analysis, and visualization of these structures often proves invaluable in understanding them. However, currently available visual analysis tools are not very well suited to handle the massive scale of this network data, and often resolve to displaying small ego networks or heavily abstracted networks. In this paper, we present Honeycomb, a visualization tool that is able to deal with much larger scale data (with millions of connections), which we illustrate by using a large scale corporate social networking site as an example. Additionally, we introduce a new probability based network metric to guide users to potentially interesting or anomalous patterns and discuss lessons learned during design and implementation.

Conceptual Hierarchies in a Flat Attractor Network

PubMed Central

O’Connor, Christopher M.; Cree, George S.; McRae, Ken

2009-01-01

The structure of people’s conceptual knowledge of concrete nouns has traditionally been viewed as hierarchical (Collins & Quillian, 1969). For example, superordinate concepts (vegetable) are assumed to reside at a higher level than basic-level concepts (carrot). A feature-based attractor network with a single layer of semantic features developed representations of both basic-level and superordinate concepts. No hierarchical structure was built into the network. In Experiment and Simulation 1, the graded structure of categories (typicality ratings) is accounted for by the flat attractor-network. Experiment and Simulation 2 show that, as with basic-level concepts, such a network predicts feature verification latencies for superordinate concepts (vegetable ). In Experiment and Simulation 3, counterintuitive results regarding the temporal dynamics of similarity in semantic priming are explained by the model. By treating both types of concepts the same in terms of representation, learning, and computations, the model provides new insights into semantic memory. PMID:19543434

Crystal Structure Prediction via Deep Learning.

PubMed

Ryan, Kevin; Lengyel, Jeff; Shatruk, Michael

2018-06-06

We demonstrate the application of deep neural networks as a machine-learning tool for the analysis of a large collection of crystallographic data contained in the crystal structure repositories. Using input data in the form of multi-perspective atomic fingerprints, which describe coordination topology around unique crystallographic sites, we show that the neural-network model can be trained to effectively distinguish chemical elements based on the topology of their crystallographic environment. The model also identifies structurally similar atomic sites in the entire dataset of ~50000 crystal structures, essentially uncovering trends that reflect the periodic table of elements. The trained model was used to analyze templates derived from the known binary and ternary crystal structures in order to predict the likelihood to form new compounds that could be generated by placing elements into these structural templates in combinatorial fashion. Statistical analysis of predictive performance of the neural-network model, which was applied to a test set of structures never seen by the model during training, indicates its ability to predict known elemental compositions with a high likelihood of success. In ~30% of cases, the known compositions were found among top-10 most likely candidates proposed by the model. These results suggest that the approach developed in this work can be used to effectively guide the synthetic efforts in the discovery of new materials, especially in the case of systems composed of 3 or more chemical elements.

Simpler grammar, larger vocabulary: How population size affects language

PubMed Central

2018-01-01

Languages with many speakers tend to be structurally simple while small communities sometimes develop languages with great structural complexity. Paradoxically, the opposite pattern appears to be observed for non-structural properties of language such as vocabulary size. These apparently opposite patterns pose a challenge for theories of language change and evolution. We use computational simulations to show that this inverse pattern can depend on a single factor: ease of diffusion through the population. A population of interacting agents was arranged on a network, passing linguistic conventions to one another along network links. Agents can invent new conventions, or replicate conventions that they have previously generated themselves or learned from other agents. Linguistic conventions are either Easy or Hard to diffuse, depending on how many times an agent needs to encounter a convention to learn it. In large groups, only linguistic conventions that are easy to learn, such as words, tend to proliferate, whereas small groups where everyone talks to everyone else allow for more complex conventions, like grammatical regularities, to be maintained. Our simulations thus suggest that language, and possibly other aspects of culture, may become simpler at the structural level as our world becomes increasingly interconnected. PMID:29367397

The Intellectual Structure of Research on Educational Technology in Science Education (ETiSE): A Co-citation Network Analysis of Publications in Selected Journals (2008-2013)

NASA Astrophysics Data System (ADS)

Tang, Kai-Yu; Tsai, Chin-Chung

2016-01-01

The main purpose of this paper is to investigate the intellectual structure of the research on educational technology in science education (ETiSE) within the most recent years (2008-2013). Based on the criteria for educational technology research and the citation threshold for educational co-citation analysis, a total of 137 relevant ETiSE papers were identified from the International Journal of Science Education, the Journal of Research in Science Teaching, Science Education, and the Journal of Science Education and Technology. Then, a series of methodologies were performed to analyze all 137 source documents, including document co-citation analysis, social network analysis, and exploratory factor analysis. As a result, 454 co-citation ties were obtained and then graphically visualized with an undirected network, presenting a global structure of the current ETiSE research network. In addition, four major underlying intellectual subfields within the main component of the ETiSE network were extracted and named as: (1) technology-enhanced science inquiry, (2) simulation and visualization for understanding, (3) technology-enhanced chemistry learning, and (4) game-based science learning. The most influential co-citation pairs and cross-boundary phenomena were then analyzed and visualized in a co-citation network. This is the very first attempt to illuminate the core ideas underlying ETiSE research by integrating the co-citation method, factor analysis, and the networking visualization technique. The findings of this study provide a platform for scholarly discussion of the dissemination and research trends within the current ETiSE literature.

Bilingual Lexical Interactions in an Unsupervised Neural Network Model

ERIC Educational Resources Information Center

Zhao, Xiaowei; Li, Ping

2010-01-01

In this paper we present an unsupervised neural network model of bilingual lexical development and interaction. We focus on how the representational structures of the bilingual lexicons can emerge, develop, and interact with each other as a function of the learning history. The results show that: (1) distinct representations for the two lexicons…

Graphing in Groups: Learning about Lines in a Collaborative Classroom Network Environment

ERIC Educational Resources Information Center

White, Tobin; Wallace, Matthew; Lai, Kevin

2012-01-01

This article presents a design experiment in which we explore new structures for classroom collaboration supported by a classroom network of handheld graphing calculators. We describe a design for small group investigations of linear functions and present findings from its implementation in three high school algebra classrooms. Our coding of the…

Deep learning and the electronic structure problem

NASA Astrophysics Data System (ADS)

Mills, Kyle; Spanner, Michael; Tamblyn, Isaac

In the past decade, the fields of artificial intelligence and computer vision have progressed remarkably. Supported by the enthusiasm of large tech companies, as well as significant hardware advances and the utilization of graphical processing units to accelerate computations, deep neural networks (DNN) are gaining momentum as a robust choice for many diverse machine learning applications. We have demonstrated the ability of a DNN to solve a quantum mechanical eigenvalue equation directly, without the need to compute a wavefunction, and without knowledge of the underlying physics. We have trained a convolutional neural network to predict the total energy of an electron in a confining, 2-dimensional electrostatic potential. We numerically solved the one-electron Schrödinger equation for millions of electrostatic potentials, and used this as training data for our neural network. Four classes of potentials were assessed: the canonical cases of the harmonic oscillator and infinite well, and two types of randomly generated potentials for which no analytic solution is known. We compare the performance of the neural network and consider how these results could lead to future advances in electronic structure theory.

TopologyNet: Topology based deep convolutional and multi-task neural networks for biomolecular property predictions

PubMed Central

2017-01-01

Although deep learning approaches have had tremendous success in image, video and audio processing, computer vision, and speech recognition, their applications to three-dimensional (3D) biomolecular structural data sets have been hindered by the geometric and biological complexity. To address this problem we introduce the element-specific persistent homology (ESPH) method. ESPH represents 3D complex geometry by one-dimensional (1D) topological invariants and retains important biological information via a multichannel image-like representation. This representation reveals hidden structure-function relationships in biomolecules. We further integrate ESPH and deep convolutional neural networks to construct a multichannel topological neural network (TopologyNet) for the predictions of protein-ligand binding affinities and protein stability changes upon mutation. To overcome the deep learning limitations from small and noisy training sets, we propose a multi-task multichannel topological convolutional neural network (MM-TCNN). We demonstrate that TopologyNet outperforms the latest methods in the prediction of protein-ligand binding affinities, mutation induced globular protein folding free energy changes, and mutation induced membrane protein folding free energy changes. Availability: weilab.math.msu.edu/TDL/ PMID:28749969

Learning to Predict Social Influence in Complex Networks

DTIC Science & Technology

2012-03-29

03/2010 – 17/03/2012 Abstract: First, we addressed the problem of analyzing information diffusion process in a social network using two kinds...algorithm which avoids the inner loop optimization during the search. We tested the performance using the structures of four real world networks, and...result of information diffusion that starts from the node. 2 We use “infected” and “activated” interchangeably. Efficient Discovery of Influential

Data Acquisition and Preparation for Social Network Analysis Based on Email: Lessons Learned

DTIC Science & Technology

2009-06-01

Mrvar , A., and Batagelj , V. (2005), Exploratory Social Network Analysis with Pajek (Structural Analysis in the Social Sciences series). Cambridge, New...visualization of large networks. This program was developed by Vladimir Batagelj and Andrej Mrvar of the University of Ljubljana in Slovenia. Pajek evolved...theory, presumes Wasserman & Faust as foundation Amazon: 55% purchase rate among viewers 5. de Nooy, W., Mrvar , A., and Batagelj , V. (2005

Structure of NCI Cooperative Groups Program Prior to NCTN

Cancer.gov

Learn how the National Cancer Institute’s Cooperative Groups Program was structured prior to its being replaced by NCI’s National Clinical Trials Network (NCTN). The NCTN gives funds and other support to cancer research organizations to conduct cancer clinical trials.

Equilibrium point control of a monkey arm simulator by a fast learning tree structured artificial neural network.

PubMed

Dornay, M; Sanger, T D

1993-01-01

A planar 17 muscle model of the monkey's arm based on realistic biomechanical measurements was simulated on a Symbolics Lisp Machine. The simulator implements the equilibrium point hypothesis for the control of arm movements. Given initial and final desired positions, it generates a minimum-jerk desired trajectory of the hand and uses the backdriving algorithm to determine an appropriate sequence of motor commands to the muscles (Flash 1987; Mussa-Ivaldi et al. 1991; Dornay 1991b). These motor commands specify a temporal sequence of stable (attractive) equilibrium positions which lead to the desired hand movement. A strong disadvantage of the simulator is that it has no memory of previous computations. Determining the desired trajectory using the minimum-jerk model is instantaneous, but the laborious backdriving algorithm is slow, and can take up to one hour for some trajectories. The complexity of the required computations makes it a poor model for biological motor control. We propose a computationally simpler and more biologically plausible method for control which achieves the benefits of the backdriving algorithm. A fast learning, tree-structured network (Sanger 1991c) was trained to remember the knowledge obtained by the backdriving algorithm. The neural network learned the nonlinear mapping from a 2-dimensional cartesian planar hand position (x,y) to a 17-dimensional motor command space (u1, . . ., u17). Learning 20 training trajectories, each composed of 26 sample points [[x,y], [u1, . . ., u17] took only 20 min on a Sun-4 Sparc workstation. After the learning stage, new, untrained test trajectories as well as the original trajectories of the hand were given to the neural network as input. The network calculated the required motor commands for these movements. The resulting movements were close to the desired ones for both the training and test cases.

Real time unsupervised learning of visual stimuli in neuromorphic VLSI systems

PubMed Central

Giulioni, Massimiliano; Corradi, Federico; Dante, Vittorio; del Giudice, Paolo

2015-01-01

Neuromorphic chips embody computational principles operating in the nervous system, into microelectronic devices. In this domain it is important to identify computational primitives that theory and experiments suggest as generic and reusable cognitive elements. One such element is provided by attractor dynamics in recurrent networks. Point attractors are equilibrium states of the dynamics (up to fluctuations), determined by the synaptic structure of the network; a ‘basin’ of attraction comprises all initial states leading to a given attractor upon relaxation, hence making attractor dynamics suitable to implement robust associative memory. The initial network state is dictated by the stimulus, and relaxation to the attractor state implements the retrieval of the corresponding memorized prototypical pattern. In a previous work we demonstrated that a neuromorphic recurrent network of spiking neurons and suitably chosen, fixed synapses supports attractor dynamics. Here we focus on learning: activating on-chip synaptic plasticity and using a theory-driven strategy for choosing network parameters, we show that autonomous learning, following repeated presentation of simple visual stimuli, shapes a synaptic connectivity supporting stimulus-selective attractors. Associative memory develops on chip as the result of the coupled stimulus-driven neural activity and ensuing synaptic dynamics, with no artificial separation between learning and retrieval phases. PMID:26463272

Comparative Analysis of Soft Computing Models in Prediction of Bending Rigidity of Cotton Woven Fabrics

NASA Astrophysics Data System (ADS)

Guruprasad, R.; Behera, B. K.

2015-10-01

Quantitative prediction of fabric mechanical properties is an essential requirement for design engineering of textile and apparel products. In this work, the possibility of prediction of bending rigidity of cotton woven fabrics has been explored with the application of Artificial Neural Network (ANN) and two hybrid methodologies, namely Neuro-genetic modeling and Adaptive Neuro-Fuzzy Inference System (ANFIS) modeling. For this purpose, a set of cotton woven grey fabrics was desized, scoured and relaxed. The fabrics were then conditioned and tested for bending properties. With the database thus created, a neural network model was first developed using back propagation as the learning algorithm. The second model was developed by applying a hybrid learning strategy, in which genetic algorithm was first used as a learning algorithm to optimize the number of neurons and connection weights of the neural network. The Genetic algorithm optimized network structure was further allowed to learn using back propagation algorithm. In the third model, an ANFIS modeling approach was attempted to map the input-output data. The prediction performances of the models were compared and a sensitivity analysis was reported. The results show that the prediction by neuro-genetic and ANFIS models were better in comparison with that of back propagation neural network model.

Redistribution of neural phase coherence reflects establishment of feedforward map in speech motor adaptation

PubMed Central

Sengupta, Ranit

2015-01-01

Despite recent progress in our understanding of sensorimotor integration in speech learning, a comprehensive framework to investigate its neural basis is lacking at behaviorally relevant timescales. Structural and functional imaging studies in humans have helped us identify brain networks that support speech but fail to capture the precise spatiotemporal coordination within the networks that takes place during speech learning. Here we use neuronal oscillations to investigate interactions within speech motor networks in a paradigm of speech motor adaptation under altered feedback with continuous recording of EEG in which subjects adapted to the real-time auditory perturbation of a target vowel sound. As subjects adapted to the task, concurrent changes were observed in the theta-gamma phase coherence during speech planning at several distinct scalp regions that is consistent with the establishment of a feedforward map. In particular, there was an increase in coherence over the central region and a decrease over the fronto-temporal regions, revealing a redistribution of coherence over an interacting network of brain regions that could be a general feature of error-based motor learning in general. Our findings have implications for understanding the neural basis of speech motor learning and could elucidate how transient breakdown of neuronal communication within speech networks relates to speech disorders. PMID:25632078

A Mixtures-of-Trees Framework for Multi-Label Classification

PubMed Central

Hong, Charmgil; Batal, Iyad; Hauskrecht, Milos

2015-01-01

We propose a new probabilistic approach for multi-label classification that aims to represent the class posterior distribution P(Y|X). Our approach uses a mixture of tree-structured Bayesian networks, which can leverage the computational advantages of conditional tree-structured models and the abilities of mixtures to compensate for tree-structured restrictions. We develop algorithms for learning the model from data and for performing multi-label predictions using the learned model. Experiments on multiple datasets demonstrate that our approach outperforms several state-of-the-art multi-label classification methods. PMID:25927011

Bayesian network prior: network analysis of biological data using external knowledge

PubMed Central

Isci, Senol; Dogan, Haluk; Ozturk, Cengizhan; Otu, Hasan H.

2014-01-01

Motivation: Reverse engineering GI networks from experimental data is a challenging task due to the complex nature of the networks and the noise inherent in the data. One way to overcome these hurdles would be incorporating the vast amounts of external biological knowledge when building interaction networks. We propose a framework where GI networks are learned from experimental data using Bayesian networks (BNs) and the incorporation of external knowledge is also done via a BN that we call Bayesian Network Prior (BNP). BNP depicts the relation between various evidence types that contribute to the event ‘gene interaction’ and is used to calculate the probability of a candidate graph (G) in the structure learning process. Results: Our simulation results on synthetic, simulated and real biological data show that the proposed approach can identify the underlying interaction network with high accuracy even when the prior information is distorted and outperforms existing methods. Availability: Accompanying BNP software package is freely available for academic use at http://bioe.bilgi.edu.tr/BNP. Contact: hasan.otu@bilgi.edu.tr Supplementary Information: Supplementary data are available at Bioinformatics online. PMID:24215027

[GSH fermentation process modeling using entropy-criterion based RBF neural network model].

PubMed

Tan, Zuoping; Wang, Shitong; Deng, Zhaohong; Du, Guocheng

2008-05-01

The prediction accuracy and generalization of GSH fermentation process modeling are often deteriorated by noise existing in the corresponding experimental data. In order to avoid this problem, we present a novel RBF neural network modeling approach based on entropy criterion. It considers the whole distribution structure of the training data set in the parameter learning process compared with the traditional MSE-criterion based parameter learning, and thus effectively avoids the weak generalization and over-learning. Then the proposed approach is applied to the GSH fermentation process modeling. Our results demonstrate that this proposed method has better prediction accuracy, generalization and robustness such that it offers a potential application merit for the GSH fermentation process modeling.

Social learning within a community of practice: Investigating interactions about evaluation among zoo education professionals.

PubMed

Khalil, Kathayoon; Ardoin, Nicole M; Wojcik, Deborah

2017-04-01

The accessibility and ubiquity of zoos and aquariums-which reach over 700 million people worldwide annually-make them critical sites for science and environmental learning. Through educational offerings, these sites can generate excitement and curiosity about nature and motivate stewardship behavior, but only if their programs are high quality and meet the needs of their audiences. Evaluation is, therefore, critical: knowing what works, for whom, and under what conditions must be central to these organizations. Yet, many zoo and aquarium educators find evaluation to be daunting, and they are challenged to implement evaluations and/or use the findings iteratively in program development and improvement. This article examines how zoo education professionals engage with one another in a learning community related to evaluation. We use a communities of practice lens and social network analysis to understand the structure of this networked learning community, considering changes over time. Our findings suggest that individuals' roles in a networked learning community are influenced by factors such as communicative convenience and one's perceptions of others' evaluation expertise, which also contribute to forming and sustaining professional relationships. This study illuminates how project-based professional networks can become communities of practice. Copyright © 2016 Elsevier Ltd. All rights reserved.

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

PubMed

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

2016-11-01

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

Merging Social Networking Environments and Formal Learning Environments to Support and Facilitate Interprofessional Instruction

PubMed Central

King, Sharla; Greidanus, Elaine; Carbonaro, Michael; Drummond, Jane; Patterson, Steven

2009-01-01

This study describes the redesign of an interprofessional team development course for health science students. A theoretical model is hypothesized as a framework for the redesign process, consisting of two themes: 1) the increasing trend among post-secondary students to participate in social networking (e.g., Facebook, Second Life) and 2) the need for healthcare educators to provide interprofessional training that results in effective communities of practice and better patient care. The redesign focused on increasing the relevance of the course through the integration of custom-designed technology to facilitate social networking during their interprofessional education. Results suggest that students in an educationally structured social networking environment can be guided to join learning communities quickly and access course materials. More research and implementation work is required to effectively develop interprofessional health sciences communities in a combined face-to-face and on-line social networking context. PMID:20165519

Merging social networking environments and formal learning environments to support and facilitate interprofessional instruction.

PubMed

King, Sharla; Greidanus, Elaine; Carbonaro, Michael; Drummond, Jane; Patterson, Steven

2009-04-28

This study describes the redesign of an interprofessional team development course for health science students. A theoretical model is hypothesized as a framework for the redesign process, consisting of two themes: 1) the increasing trend among post-secondary students to participate in social networking (e.g., Facebook, Second Life) and 2) the need for healthcare educators to provide interprofessional training that results in effective communities of practice and better patient care. The redesign focused on increasing the relevance of the course through the integration of custom-designed technology to facilitate social networking during their interprofessional education. Results suggest that students in an educationally structured social networking environment can be guided to join learning communities quickly and access course materials. More research and implementation work is required to effectively develop interprofessional health sciences communities in a combined face-to-face and on-line social networking context.

Revealing networks from dynamics: an introduction

NASA Astrophysics Data System (ADS)

Timme, Marc; Casadiego, Jose

2014-08-01

What can we learn from the collective dynamics of a complex network about its interaction topology? Taking the perspective from nonlinear dynamics, we briefly review recent progress on how to infer structural connectivity (direct interactions) from accessing the dynamics of the units. Potential applications range from interaction networks in physics, to chemical and metabolic reactions, protein and gene regulatory networks as well as neural circuits in biology and electric power grids or wireless sensor networks in engineering. Moreover, we briefly mention some standard ways of inferring effective or functional connectivity.

Automated sub-cortical brain structure segmentation combining spatial and deep convolutional features.

PubMed

Kushibar, Kaisar; Valverde, Sergi; González-Villà, Sandra; Bernal, Jose; Cabezas, Mariano; Oliver, Arnau; Lladó, Xavier

2018-06-15

Sub-cortical brain structure segmentation in Magnetic Resonance Images (MRI) has attracted the interest of the research community for a long time as morphological changes in these structures are related to different neurodegenerative disorders. However, manual segmentation of these structures can be tedious and prone to variability, highlighting the need for robust automated segmentation methods. In this paper, we present a novel convolutional neural network based approach for accurate segmentation of the sub-cortical brain structures that combines both convolutional and prior spatial features for improving the segmentation accuracy. In order to increase the accuracy of the automated segmentation, we propose to train the network using a restricted sample selection to force the network to learn the most difficult parts of the structures. We evaluate the accuracy of the proposed method on the public MICCAI 2012 challenge and IBSR 18 datasets, comparing it with different traditional and deep learning state-of-the-art methods. On the MICCAI 2012 dataset, our method shows an excellent performance comparable to the best participant strategy on the challenge, while performing significantly better than state-of-the-art techniques such as FreeSurfer and FIRST. On the IBSR 18 dataset, our method also exhibits a significant increase in the performance with respect to not only FreeSurfer and FIRST, but also comparable or better results than other recent deep learning approaches. Moreover, our experiments show that both the addition of the spatial priors and the restricted sampling strategy have a significant effect on the accuracy of the proposed method. In order to encourage the reproducibility and the use of the proposed method, a public version of our approach is available to download for the neuroimaging community. Copyright © 2018 The Authors. Published by Elsevier B.V. All rights reserved.

Beam-column joint shear prediction using hybridized deep learning neural network with genetic algorithm

NASA Astrophysics Data System (ADS)

Mundher Yaseen, Zaher; Abdulmohsin Afan, Haitham; Tran, Minh-Tung

2018-04-01

Scientifically evidenced that beam-column joints are a critical point in the reinforced concrete (RC) structure under the fluctuation loads effects. In this novel hybrid data-intelligence model developed to predict the joint shear behavior of exterior beam-column structure frame. The hybrid data-intelligence model is called genetic algorithm integrated with deep learning neural network model (GA-DLNN). The genetic algorithm is used as prior modelling phase for the input approximation whereas the DLNN predictive model is used for the prediction phase. To demonstrate this structural problem, experimental data is collected from the literature that defined the dimensional and specimens’ properties. The attained findings evidenced the efficitveness of the hybrid GA-DLNN in modelling beam-column joint shear problem. In addition, the accurate prediction achived with less input variables owing to the feasibility of the evolutionary phase.

Application of Crack Identification Techniques for an Aging Concrete Bridge Inspection Using an Unmanned Aerial Vehicle.

PubMed

Kim, In-Ho; Jeon, Haemin; Baek, Seung-Chan; Hong, Won-Hwa; Jung, Hyung-Jo

2018-06-08

Bridge inspection using unmanned aerial vehicles (UAV) with high performance vision sensors has received considerable attention due to its safety and reliability. As bridges become obsolete, the number of bridges that need to be inspected increases, and they require much maintenance cost. Therefore, a bridge inspection method based on UAV with vision sensors is proposed as one of the promising strategies to maintain bridges. In this paper, a crack identification method by using a commercial UAV with a high resolution vision sensor is investigated in an aging concrete bridge. First, a point cloud-based background model is generated in the preliminary flight. Then, cracks on the structural surface are detected with the deep learning algorithm, and their thickness and length are calculated. In the deep learning method, region with convolutional neural networks (R-CNN)-based transfer learning is applied. As a result, a new network for the 384 collected crack images of 256 × 256 pixel resolution is generated from the pre-trained network. A field test is conducted to verify the proposed approach, and the experimental results proved that the UAV-based bridge inspection is effective at identifying and quantifying the cracks on the structures.

Social networks and expertise development for Australian breast radiologists.

PubMed

Taba, Seyedamir Tavakoli; Hossain, Liaquat; Willis, Karen; Lewis, Sarah

2017-02-11

In this study, we explore the nexus between social networks and expertise development of Australian breast radiologists. Background literature has shown that a lack of appropriate social networks and interaction among certain professional group(s) may be an obstacle for knowledge acquisition, information flow and expertise sharing. To date there have not been any systematic studies investigating how social networks and expertise development are interconnected and whether this leads to improved performance for breast radiologists. This study explores the value of social networks in building expertise alongside with other constructs of performance for the Australian radiology workforce using semi-structured in-depth interviews with 17 breast radiologists. The findings from this study emphasise the influences of knowledge transfer and learning through social networks and interactions as well as knowledge acquisition and development through experience and feedback. The results also show that accessibility to learning resources and a variety of timely feedback on performance through the information and communication technologies (ICT) is likely to facilitate improved performance and build social support. We argue that radiologists' and, in particular, breast radiologists' work performance, needs to be explored not only through individual numerical characteristics but also by analysing the social context and peer support networks in which they operate and we identify multidisciplinary care as a core entity of social learning.

Structural Organization of the Laryngeal Motor Cortical Network and Its Implication for Evolution of Speech Production.

PubMed

Kumar, Veena; Croxson, Paula L; Simonyan, Kristina

2016-04-13

The laryngeal motor cortex (LMC) is essential for the production of learned vocal behaviors because bilateral damage to this area renders humans unable to speak but has no apparent effect on innate vocalizations such as human laughing and crying or monkey calls. Several hypotheses have been put forward attempting to explain the evolutionary changes from monkeys to humans that potentially led to enhanced LMC functionality for finer motor control of speech production. These views, however, remain limited to the position of the larynx area within the motor cortex, as well as its connections with the phonatory brainstem regions responsible for the direct control of laryngeal muscles. Using probabilistic diffusion tractography in healthy humans and rhesus monkeys, we show that, whereas the LMC structural network is largely comparable in both species, the LMC establishes nearly 7-fold stronger connectivity with the somatosensory and inferior parietal cortices in humans than in macaques. These findings suggest that important "hard-wired" components of the human LMC network controlling the laryngeal component of speech motor output evolved from an already existing, similar network in nonhuman primates. However, the evolution of enhanced LMC-parietal connections likely allowed for more complex synchrony of higher-order sensorimotor coordination, proprioceptive and tactile feedback, and modulation of learned voice for speech production. The role of the primary motor cortex in the formation of a comprehensive network controlling speech and language has been long underestimated and poorly studied. Here, we provide comparative and quantitative evidence for the significance of this region in the control of a highly learned and uniquely human behavior: speech production. From the viewpoint of structural network organization, we discuss potential evolutionary advances of enhanced temporoparietal cortical connections with the laryngeal motor cortex in humans compared with nonhuman primates that may have contributed to the development of finer vocal motor control necessary for speech production. Copyright © 2016 the authors 0270-6474/16/364170-12$15.00/0.

Overlap and Differences in Brain Networks Underlying the Processing of Complex Sentence Structures in Second Language Users Compared with Native Speakers.

PubMed

Weber, Kirsten; Luther, Lisa; Indefrey, Peter; Hagoort, Peter

2016-05-01

When we learn a second language later in life, do we integrate it with the established neural networks in place for the first language or is at least a partially new network recruited? While there is evidence that simple grammatical structures in a second language share a system with the native language, the story becomes more multifaceted for complex sentence structures. In this study, we investigated the underlying brain networks in native speakers compared with proficient second language users while processing complex sentences. As hypothesized, complex structures were processed by the same large-scale inferior frontal and middle temporal language networks of the brain in the second language, as seen in native speakers. These effects were seen both in activations and task-related connectivity patterns. Furthermore, the second language users showed increased task-related connectivity from inferior frontal to inferior parietal regions of the brain, regions related to attention and cognitive control, suggesting less automatic processing for these structures in a second language.

Global Conceptualization of the Professional Learning Community Process: Transitioning from Country Perspectives to International Commonalities

ERIC Educational Resources Information Center

Huffman, Jane B.; Olivier, Dianne F.; Wang, Ting; Chen, Peiying; Hairon, Salleh; Pang, Nicholas

2016-01-01

The authors seek to find common PLC structures and actions among global educational systems to enhance understanding and practice. Six international researchers formed the Global Professional Learning Community Network (GloPLCNet), conducted literature reviews of each country's involvement with PLC actions, and noted similarities and common…

Social Capital and Learning Organisation: Is It Worth to Engage in Networking?

ERIC Educational Resources Information Center

Akhtar, Shoaib; Awan, Sajid H.; Ismail, Kamariah; Naveed, Shaheryar

2017-01-01

This paper attempts to examine the influence of social capital towards learning organisation in higher education institutions. The study adopted quantitative approach with survey questionnaire. The sample of the study was 227 academic staff members of 22 higher educational institutions. Social capital was measured using structural, relational and…

The Effect of Centralization and Cohesion on the Social Construction of Knowledge in Discussion Forums

ERIC Educational Resources Information Center

Tirado, Ramón; Hernando, Ángel; Aguaded, José Ignacio

2015-01-01

Interactive relationships in online learning communities can influence the process and quality of knowledge building. The aim of this study is to empirically investigate the relationships between network structures and social knowledge building in an asynchronous writing environment through discussion forums in a learning management system. The…

The Effect of Centralization and Cohesion on the Social Construction of Knowledge in Discussion Forums

ERIC Educational Resources Information Center

Tirado, Ramon; Hernando, Angel; Aguaded, Jose Ignacio

2012-01-01

Interactive relationships in online learning communities can influence the process and quality of knowledge building. The aim of this study is to empirically investigate the relationships between network structures and social knowledge building in an asynchronous writing environment through discussion forums in a learning management system. The…

Understanding Knowledge-Sharing Breakdowns: A Meeting of the Quantitative and Qualitative Minds

ERIC Educational Resources Information Center

Soller, Amy

2004-01-01

The rapid advance of distance learning and networking technology has enabled universities and corporations to reach out and educate students across time and space barriers. Although this technology enables structured collaborative learning activities, online groups often do not enjoy the same benefits as face-to-face learners, and their…

Knowledge Structures of Entering Computer Networking Students and Their Instructors

ERIC Educational Resources Information Center

DiCerbo, Kristen E.

2007-01-01

Students bring prior knowledge to their learning experiences. This prior knowledge is known to affect how students encode and later retrieve new information learned. Teachers and content developers can use information about students' prior knowledge to create more effective lessons and materials. In many content areas, particularly the sciences,…

Graph Representations of Flow and Transport in Fracture Networks using Machine Learning

NASA Astrophysics Data System (ADS)

Srinivasan, G.; Viswanathan, H. S.; Karra, S.; O'Malley, D.; Godinez, H. C.; Hagberg, A.; Osthus, D.; Mohd-Yusof, J.

2017-12-01

Flow and transport of fluids through fractured systems is governed by the properties and interactions at the micro-scale. Retaining information about the micro-structure such as fracture length, orientation, aperture and connectivity in mesh-based computational models results in solving for millions to billions of degrees of freedom and quickly renders the problem computationally intractable. Our approach depicts fracture networks graphically, by mapping fractures to nodes and intersections to edges, thereby greatly reducing computational burden. Additionally, we use machine learning techniques to build simulators on the graph representation, trained on data from the mesh-based high fidelity simulations to speed up computation by orders of magnitude. We demonstrate our methodology on ensembles of discrete fracture networks, dividing up the data into training and validation sets. Our machine learned graph-based solvers result in over 3 orders of magnitude speedup without any significant sacrifice in accuracy.

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.

Self-Control and Deviant Peer Network Structure

ERIC Educational Resources Information Center

McGloin, Jean Marie; Shermer, Lauren O'Neill

2009-01-01

From learning and opportunity perspectives, peer group structural dimensions shed light on social processes that can amplify or ameliorate the risk of having delinquent friends. Previous research has not accounted for a primary criminological variable, self-control, limiting theoretical clarity. The authors developed three hypotheses about…

DeepNAT: Deep convolutional neural network for segmenting neuroanatomy.

PubMed

Wachinger, Christian; Reuter, Martin; Klein, Tassilo

2018-04-15

We introduce DeepNAT, a 3D Deep convolutional neural network for the automatic segmentation of NeuroAnaTomy in T1-weighted magnetic resonance images. DeepNAT is an end-to-end learning-based approach to brain segmentation that jointly learns an abstract feature representation and a multi-class classification. We propose a 3D patch-based approach, where we do not only predict the center voxel of the patch but also neighbors, which is formulated as multi-task learning. To address a class imbalance problem, we arrange two networks hierarchically, where the first one separates foreground from background, and the second one identifies 25 brain structures on the foreground. Since patches lack spatial context, we augment them with coordinates. To this end, we introduce a novel intrinsic parameterization of the brain volume, formed by eigenfunctions of the Laplace-Beltrami operator. As network architecture, we use three convolutional layers with pooling, batch normalization, and non-linearities, followed by fully connected layers with dropout. The final segmentation is inferred from the probabilistic output of the network with a 3D fully connected conditional random field, which ensures label agreement between close voxels. The roughly 2.7million parameters in the network are learned with stochastic gradient descent. Our results show that DeepNAT compares favorably to state-of-the-art methods. Finally, the purely learning-based method may have a high potential for the adaptation to young, old, or diseased brains by fine-tuning the pre-trained network with a small training sample on the target application, where the availability of larger datasets with manual annotations may boost the overall segmentation accuracy in the future. Copyright © 2017 Elsevier Inc. All rights reserved.

Grounding statistical learning in context: The effects of learning and retrieval contexts on cross-situational word learning.

PubMed

Chen, Chi-Hsin; Yu, Chen

2017-06-01

Natural language environments usually provide structured contexts for learning. This study examined the effects of semantically themed contexts-in both learning and retrieval phases-on statistical word learning. Results from 2 experiments consistently showed that participants had higher performance in semantically themed learning contexts. In contrast, themed retrieval contexts did not affect performance. Our work suggests that word learners are sensitive to statistical regularities not just at the level of individual word-object co-occurrences but also at another level containing a whole network of associations among objects and their properties.

Similarities and differences between the brain networks underlying allocentric and egocentric spatial learning in rat revealed by cytochrome oxidase histochemistry.

PubMed

Rubio, S; Begega, A; Méndez, M; Méndez-López, M; Arias, J L

2012-10-25

The involvement of different brain regions in place- and response-learning was examined using a water cross-maze. Rats were trained to find the goal from the initial arm by turning left at the choice point (egocentric strategy) or by using environmental cues (allocentric strategy). Although different strategies were required, the same maze and learning conditions were used. Using cytochrome oxidase histochemistry as a marker of cellular activity, the function of the 13 diverse cortical and subcortical regions was assessed in rats performing these two tasks. Our results show that allocentric learning depends on the recruitment of a large functional network, which includes the hippocampal CA3, dentate gyrus, medial mammillary nucleus and supramammillary nucleus. Along with the striatum, these last three structures are also related to egocentric spatial learning. The present study provides evidence for the contribution of these regions to spatial navigation and supports a possible functional interaction between the two memory systems, as their structural convergence may facilitate functional cooperation in the behaviours guided by more than one strategy. In summary, it can be argued that spatial learning is based on dynamic functional systems in which the interaction of brain regions is modulated by task requirements. Copyright © 2012 IBRO. Published by Elsevier Ltd. All rights reserved.

Intelligent-based Structural Damage Detection Model

NASA Astrophysics Data System (ADS)

Lee, Eric Wai Ming; Yu, Kin Fung

2010-05-01

This paper presents the application of a novel Artificial Neural Network (ANN) model for the diagnosis of structural damage. The ANN model, denoted as the GRNNFA, is a hybrid model combining the General Regression Neural Network Model (GRNN) and the Fuzzy ART (FA) model. It not only retains the important features of the GRNN and FA models (i.e. fast and stable network training and incremental growth of network structure) but also facilitates the removal of the noise embedded in the training samples. Structural damage alters the stiffness distribution of the structure and so as to change the natural frequencies and mode shapes of the system. The measured modal parameter changes due to a particular damage are treated as patterns for that damage. The proposed GRNNFA model was trained to learn those patterns in order to detect the possible damage location of the structure. Simulated data is employed to verify and illustrate the procedures of the proposed ANN-based damage diagnosis methodology. The results of this study have demonstrated the feasibility of applying the GRNNFA model to structural damage diagnosis even when the training samples were noise contaminated.

Predicting backbone Cα angles and dihedrals from protein sequences by stacked sparse auto-encoder deep neural network.

PubMed

Lyons, James; Dehzangi, Abdollah; Heffernan, Rhys; Sharma, Alok; Paliwal, Kuldip; Sattar, Abdul; Zhou, Yaoqi; Yang, Yuedong

2014-10-30

Because a nearly constant distance between two neighbouring Cα atoms, local backbone structure of proteins can be represented accurately by the angle between C(αi-1)-C(αi)-C(αi+1) (θ) and a dihedral angle rotated about the C(αi)-C(αi+1) bond (τ). θ and τ angles, as the representative of structural properties of three to four amino-acid residues, offer a description of backbone conformations that is complementary to φ and ψ angles (single residue) and secondary structures (>3 residues). Here, we report the first machine-learning technique for sequence-based prediction of θ and τ angles. Predicted angles based on an independent test have a mean absolute error of 9° for θ and 34° for τ with a distribution on the θ-τ plane close to that of native values. The average root-mean-square distance of 10-residue fragment structures constructed from predicted θ and τ angles is only 1.9Å from their corresponding native structures. Predicted θ and τ angles are expected to be complementary to predicted ϕ and ψ angles and secondary structures for using in model validation and template-based as well as template-free structure prediction. The deep neural network learning technique is available as an on-line server called Structural Property prediction with Integrated DEep neuRal network (SPIDER) at http://sparks-lab.org. Copyright © 2014 Wiley Periodicals, Inc.

Sequence-specific bias correction for RNA-seq data using recurrent neural networks.

PubMed

Zhang, Yao-Zhong; Yamaguchi, Rui; Imoto, Seiya; Miyano, Satoru

2017-01-25

The recent success of deep learning techniques in machine learning and artificial intelligence has stimulated a great deal of interest among bioinformaticians, who now wish to bring the power of deep learning to bare on a host of bioinformatical problems. Deep learning is ideally suited for biological problems that require automatic or hierarchical feature representation for biological data when prior knowledge is limited. In this work, we address the sequence-specific bias correction problem for RNA-seq data redusing Recurrent Neural Networks (RNNs) to model nucleotide sequences without pre-determining sequence structures. The sequence-specific bias of a read is then calculated based on the sequence probabilities estimated by RNNs, and used in the estimation of gene abundance. We explore the application of two popular RNN recurrent units for this task and demonstrate that RNN-based approaches provide a flexible way to model nucleotide sequences without knowledge of predetermined sequence structures. Our experiments show that training a RNN-based nucleotide sequence model is efficient and RNN-based bias correction methods compare well with the-state-of-the-art sequence-specific bias correction method on the commonly used MAQC-III data set. RNNs provides an alternative and flexible way to calculate sequence-specific bias without explicitly pre-determining sequence structures.

Examining Neuronal Connectivity and Its Role in Learning and Memory

NASA Astrophysics Data System (ADS)

Gala, Rohan

Learning and long-term memory formation are accompanied with changes in the patterns and weights of synaptic connections in the underlying neuronal network. However, the fundamental rules that drive connectivity changes, and the precise structure-function relationships within neuronal networks remain elusive. Technological improvements over the last few decades have enabled the observation of large but specific subsets of neurons and their connections in unprecedented detail. Devising robust and automated computational methods is critical to distill information from ever-increasing volumes of raw experimental data. Moreover, statistical models and theoretical frameworks are required to interpret the data and assemble evidence into understanding of brain function. In this thesis, I first describe computational methods to reconstruct connectivity based on light microscopy imaging experiments. Next, I use these methods to quantify structural changes in connectivity based on in vivo time-lapse imaging experiments. Finally, I present a theoretical model of associative learning that can explain many stereotypical features of experimentally observed connectivity.

An examination of the structure and nomological network of trainee reactions: a closer look at "smile sheets".

PubMed

Brown, Kenneth G

2005-09-01

Although D. L. Kirkpatrick (1959, 1996) popularized the concept of trainee reactions over 40 years ago, few studies have critically examined trainees' reactions to learning events. In this article, research on mood and emotion is used to develop a theoretical framework for research on trainee reactions. Two studies examine the factor structure of reactions and their nomological network. In Study 1, 178 undergraduate and 101 graduate students listened to a computer-delivered multimedia lecture. Results suggest that (a) reactions can be conceptualized as hierarchical, with overall satisfaction explaining associations among distinct reaction facets (enjoyment, relevance, and technology satisfaction), and (b) reactions are predicted by trainee characteristics. In Study 2, 97 undergraduates experienced the same lecture in 1 of 3 randomly assigned delivery technologies. Reactions were influenced by technology and were related to learning process (engagement) and outcomes (intentions regarding delivery technology, content, and learning). Both studies support the theoretical framework proposed. Copyright 2005 APA, all rights reserved.

Extraction of business relationships in supply networks using statistical learning theory.

PubMed

Zuo, Yi; Kajikawa, Yuya; Mori, Junichiro

2016-06-01

Supply chain management represents one of the most important scientific streams of operations research. The supply of energy, materials, products, and services involves millions of transactions conducted among national and local business enterprises. To deliver efficient and effective support for supply chain design and management, structural analyses and predictive models of customer-supplier relationships are expected to clarify current enterprise business conditions and to help enterprises identify innovative business partners for future success. This article presents the outcomes of a recent structural investigation concerning a supply network in the central area of Japan. We investigated the effectiveness of statistical learning theory to express the individual differences of a supply chain of enterprises within a certain business community using social network analysis. In the experiments, we employ support vector machine to train a customer-supplier relationship model on one of the main communities extracted from a supply network in the central area of Japan. The prediction results reveal an F-value of approximately 70% when the model is built by using network-based features, and an F-value of approximately 77% when the model is built by using attribute-based features. When we build the model based on both, F-values are improved to approximately 82%. The results of this research can help to dispel the implicit design space concerning customer-supplier relationships, which can be explored and refined from detailed topological information provided by network structures rather than from traditional and attribute-related enterprise profiles. We also investigate and discuss differences in the predictive accuracy of the model for different sizes of enterprises and types of business communities.

Tractography-Based Score for Learning Effective Connectivity From Multimodal Imaging Data Using Dynamic Bayesian Networks.

PubMed

Dang, Shilpa; Chaudhury, Santanu; Lall, Brejesh; Roy, Prasun K

2018-05-01

Effective connectivity (EC) is the methodology for determining functional-integration among the functionally active segregated regions of the brain. By definition EC is "the causal influence exerted by one neuronal group on another" which is constrained by anatomical connectivity (AC) (axonal connections). AC is necessary for EC but does not fully determine it, because synaptic communication occurs dynamically in a context-dependent fashion. Although there is a vast emerging evidence of structure-function relationship using multimodal imaging studies, till date only a few studies have done joint modeling of the two modalities: functional MRI (fMRI) and diffusion tensor imaging (DTI). We aim to propose a unified probabilistic framework that combines information from both sources to learn EC using dynamic Bayesian networks (DBNs). DBNs are probabilistic graphical temporal models that learn EC in an exploratory fashion. Specifically, we propose a novel anatomically informed (AI) score that evaluates fitness of a given connectivity structure to both DTI and fMRI data simultaneously. The AI score is employed in structure learning of DBN given the data. Experiments with synthetic-data demonstrate the face validity of structure learning with our AI score over anatomically uninformed counterpart. Moreover, real-data results are cross-validated by performing classification-experiments. EC inferred on real fMRI-DTI datasets is found to be consistent with previous literature and show promising results in light of the AC present as compared to other classically used techniques such as Granger-causality. Multimodal analyses provide a more reliable basis for differentiating brain under abnormal/diseased conditions than the single modality analysis.

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.

Influence of Students' Affective and Conative Factors on Laboratory Learning: Moderating Effect of Online Social Network Attention

ERIC Educational Resources Information Center

Hwang, Wu-Yuin; Kongcharoen, Chaknarin; Ghinea, Gheorghita

2017-01-01

According to aptitude theory, the measures of aptitude include not only cognitive factors but also affective factors (i.e., emotions) and conative factors (i.e., motivation) that can influence students' learning achievement (LA). Therefore, this study employed structural equation modelling from experimental data of 96 college students to…

The Development of the Network Examination for Student Socialization (NEXSS) Observational Instrument

ERIC Educational Resources Information Center

Rhoades, Jesse Lee; Hastmann, Tanis Joy

2014-01-01

The complexity of learning has plagued the educational establishment for decades. Recently, ideas of complexity theory and complex adaptive systems have made headway in how we think of institutions of learning. This study developed and tested an instrument for the modeling of underlying social structures, as an element of complexity, within the…

Integration of Online Parameter Identification and Neural Network for In-Flight Adaptive Control

NASA Technical Reports Server (NTRS)

Hageman, Jacob J.; Smith, Mark S.; Stachowiak, Susan

2003-01-01

An indirect adaptive system has been constructed for robust control of an aircraft with uncertain aerodynamic characteristics. This system consists of a multilayer perceptron pre-trained neural network, online stability and control derivative identification, a dynamic cell structure online learning neural network, and a model following control system based on the stochastic optimal feedforward and feedback technique. The pre-trained neural network and model following control system have been flight-tested, but the online parameter identification and online learning neural network are new additions used for in-flight adaptation of the control system model. A description of the modification and integration of these two stand-alone software packages into the complete system in preparation for initial flight tests is presented. Open-loop results using both simulation and flight data, as well as closed-loop performance of the complete system in a nonlinear, six-degree-of-freedom, flight validated simulation, are analyzed. Results show that this online learning system, in contrast to the nonlearning system, has the ability to adapt to changes in aerodynamic characteristics in a real-time, closed-loop, piloted simulation, resulting in improved flying qualities.

Deep Visual Attention Prediction

NASA Astrophysics Data System (ADS)

Wang, Wenguan; Shen, Jianbing

2018-05-01

In this work, we aim to predict human eye fixation with view-free scenes based on an end-to-end deep learning architecture. Although Convolutional Neural Networks (CNNs) have made substantial improvement on human attention prediction, it is still needed to improve CNN based attention models by efficiently leveraging multi-scale features. Our visual attention network is proposed to capture hierarchical saliency information from deep, coarse layers with global saliency information to shallow, fine layers with local saliency response. Our model is based on a skip-layer network structure, which predicts human attention from multiple convolutional layers with various reception fields. Final saliency prediction is achieved via the cooperation of those global and local predictions. Our model is learned in a deep supervision manner, where supervision is directly fed into multi-level layers, instead of previous approaches of providing supervision only at the output layer and propagating this supervision back to earlier layers. Our model thus incorporates multi-level saliency predictions within a single network, which significantly decreases the redundancy of previous approaches of learning multiple network streams with different input scales. Extensive experimental analysis on various challenging benchmark datasets demonstrate our method yields state-of-the-art performance with competitive inference time.

Experimental Machine Learning of Quantum States

NASA Astrophysics Data System (ADS)

Gao, Jun; Qiao, Lu-Feng; Jiao, Zhi-Qiang; Ma, Yue-Chi; Hu, Cheng-Qiu; Ren, Ruo-Jing; Yang, Ai-Lin; Tang, Hao; Yung, Man-Hong; Jin, Xian-Min

2018-06-01

Quantum information technologies provide promising applications in communication and computation, while machine learning has become a powerful technique for extracting meaningful structures in "big data." A crossover between quantum information and machine learning represents a new interdisciplinary area stimulating progress in both fields. Traditionally, a quantum state is characterized by quantum-state tomography, which is a resource-consuming process when scaled up. Here we experimentally demonstrate a machine-learning approach to construct a quantum-state classifier for identifying the separability of quantum states. We show that it is possible to experimentally train an artificial neural network to efficiently learn and classify quantum states, without the need of obtaining the full information of the states. We also show how adding a hidden layer of neurons to the neural network can significantly boost the performance of the state classifier. These results shed new light on how classification of quantum states can be achieved with limited resources, and represent a step towards machine-learning-based applications in quantum information processing.

Metric learning with spectral graph convolutions on brain connectivity networks.

PubMed

Ktena, Sofia Ira; Parisot, Sarah; Ferrante, Enzo; Rajchl, Martin; Lee, Matthew; Glocker, Ben; Rueckert, Daniel

2018-04-01

Graph representations are often used to model structured data at an individual or population level and have numerous applications in pattern recognition problems. In the field of neuroscience, where such representations are commonly used to model structural or functional connectivity between a set of brain regions, graphs have proven to be of great importance. This is mainly due to the capability of revealing patterns related to brain development and disease, which were previously unknown. Evaluating similarity between these brain connectivity networks in a manner that accounts for the graph structure and is tailored for a particular application is, however, non-trivial. Most existing methods fail to accommodate the graph structure, discarding information that could be beneficial for further classification or regression analyses based on these similarities. We propose to learn a graph similarity metric using a siamese graph convolutional neural network (s-GCN) in a supervised setting. The proposed framework takes into consideration the graph structure for the evaluation of similarity between a pair of graphs, by employing spectral graph convolutions that allow the generalisation of traditional convolutions to irregular graphs and operates in the graph spectral domain. We apply the proposed model on two datasets: the challenging ABIDE database, which comprises functional MRI data of 403 patients with autism spectrum disorder (ASD) and 468 healthy controls aggregated from multiple acquisition sites, and a set of 2500 subjects from UK Biobank. We demonstrate the performance of the method for the tasks of classification between matching and non-matching graphs, as well as individual subject classification and manifold learning, showing that it leads to significantly improved results compared to traditional methods. Copyright © 2017 Elsevier Inc. All rights reserved.

Patient-tailored prioritization for a pediatric care decision support system through machine learning.

PubMed

Klann, Jeffrey G; Anand, Vibha; Downs, Stephen M

2013-12-01

Over 8 years, we have developed an innovative computer decision support system that improves appropriate delivery of pediatric screening and care. This system employs a guidelines evaluation engine using data from the electronic health record (EHR) and input from patients and caregivers. Because guideline recommendations typically exceed the scope of one visit, the engine uses a static prioritization scheme to select recommendations. Here we extend an earlier idea to create patient-tailored prioritization. We used Bayesian structure learning to build networks of association among previously collected data from our decision support system. Using area under the receiver-operating characteristic curve (AUC) as a measure of discriminability (a sine qua non for expected value calculations needed for prioritization), we performed a structural analysis of variables with high AUC on a test set. Our source data included 177 variables for 29 402 patients. The method produced a network model containing 78 screening questions and anticipatory guidance (107 variables total). Average AUC was 0.65, which is sufficient for prioritization depending on factors such as population prevalence. Structure analysis of seven highly predictive variables reveals both face-validity (related nodes are connected) and non-intuitive relationships. We demonstrate the ability of a Bayesian structure learning method to 'phenotype the population' seen in our primary care pediatric clinics. The resulting network can be used to produce patient-tailored posterior probabilities that can be used to prioritize content based on the patient's current circumstances. This study demonstrates the feasibility of EHR-driven population phenotyping for patient-tailored prioritization of pediatric preventive care services.

Selected Flight Test Results for Online Learning Neural Network-Based Flight Control System

NASA Technical Reports Server (NTRS)

Williams-Hayes, Peggy S.

2004-01-01

The NASA F-15 Intelligent Flight Control System project team developed a series of flight control concepts designed to demonstrate neural network-based adaptive controller benefits, with the objective to develop and flight-test control systems using neural network technology to optimize aircraft performance under nominal conditions and stabilize the aircraft under failure conditions. This report presents flight-test results for an adaptive controller using stability and control derivative values from an online learning neural network. A dynamic cell structure neural network is used in conjunction with a real-time parameter identification algorithm to estimate aerodynamic stability and control derivative increments to baseline aerodynamic derivatives in flight. This open-loop flight test set was performed in preparation for a future phase in which the learning neural network and parameter identification algorithm output would provide the flight controller with aerodynamic stability and control derivative updates in near real time. Two flight maneuvers are analyzed - pitch frequency sweep and automated flight-test maneuver designed to optimally excite the parameter identification algorithm in all axes. Frequency responses generated from flight data are compared to those obtained from nonlinear simulation runs. Flight data examination shows that addition of flight-identified aerodynamic derivative increments into the simulation improved aircraft pitch handling qualities.

A neural learning classifier system with self-adaptive constructivism for mobile robot control.

PubMed

Hurst, Jacob; Bull, Larry

2006-01-01

For artificial entities to achieve true autonomy and display complex lifelike behavior, they will need to exploit appropriate adaptable learning algorithms. In this context adaptability implies flexibility guided by the environment at any given time and an open-ended ability to learn appropriate behaviors. This article examines the use of constructivism-inspired mechanisms within a neural learning classifier system architecture that exploits parameter self-adaptation as an approach to realize such behavior. The system uses a rule structure in which each rule is represented by an artificial neural network. It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the learner and that the structure indicates underlying features of the task. Results are presented in simulated mazes before moving to a mobile robot platform.

Connecticut permanent long-term bridge monitoring network, volume 7 : lessons learned for specifications to guide design of structural health monitoring systems.

DOT National Transportation Integrated Search

2014-08-01

This report proposes a set of specifications for bridge structural health monitoring that has resulted from the : experiences gained during the installation and monitoring of six permanent long-term bridge monitoring systems in : Connecticut. As expe...

Understanding Classrooms through Social Network Analysis: A Primer for Social Network Analysis in Education Research

PubMed Central

Wiggins, Benjamin L.; Goodreau, Steven M.

2014-01-01

Social interactions between students are a major and underexplored part of undergraduate education. Understanding how learning relationships form in undergraduate classrooms, as well as the impacts these relationships have on learning outcomes, can inform educators in unique ways and improve educational reform. Social network analysis (SNA) provides the necessary tool kit for investigating questions involving relational data. We introduce basic concepts in SNA, along with methods for data collection, data processing, and data analysis, using a previously collected example study on an undergraduate biology classroom as a tutorial. We conduct descriptive analyses of the structure of the network of costudying relationships. We explore generative processes that create observed study networks between students and also test for an association between network position and success on exams. We also cover practical issues, such as the unique aspects of human subjects review for network studies. Our aims are to convince readers that using SNA in classroom environments allows rich and informative analyses to take place and to provide some initial tools for doing so, in the process inspiring future educational studies incorporating relational data. PMID:26086650

KNT-artificial neural network model for flux prediction of ultrafiltration membrane producing drinking water.

PubMed

Oh, H K; Yu, M J; Gwon, E M; Koo, J Y; Kim, S G; Koizumi, A

2004-01-01

This paper describes the prediction of flux behavior in an ultrafiltration (UF) membrane system using a Kalman neuro training (KNT) network model. The experimental data was obtained from operating a pilot plant of hollow fiber UF membrane with groundwater for 7 months. The network was trained using operating conditions such as inlet pressure, filtration duration, and feed water quality parameters including turbidity, temperature and UV254. Pre-processing of raw data allowed the normalized input data to be used in sigmoid activation functions. A neural network architecture was structured by modifying the number of hidden layers, neurons and learning iterations. The structure of KNT-neural network with 3 layers and 5 neurons allowed a good prediction of permeate flux by 0.997 of correlation coefficient during the learning phase. Also the validity of the designed model was evaluated with other experimental data not used during the training phase and nonlinear flux behavior was accurately estimated with 0.999 of correlation coefficient and a lower error of prediction in the testing phase. This good flux prediction can provide preliminary criteria in membrane design and set up the proper cleaning cycle in membrane operation. The KNT-artificial neural network is also expected to predict the variation of transmembrane pressure during filtration cycles and can be applied to automation and control of full scale treatment plants.

Structure constrained by metadata in networks of chess players.

PubMed

Almeira, Nahuel; Schaigorodsky, Ana L; Perotti, Juan I; Billoni, Orlando V

2017-11-09

Chess is an emblematic sport that stands out because of its age, popularity and complexity. It has served to study human behavior from the perspective of a wide number of disciplines, from cognitive skills such as memory and learning, to aspects like innovation and decision-making. Given that an extensive documentation of chess games played throughout history is available, it is possible to perform detailed and statistically significant studies about this sport. Here we use one of the most extensive chess databases in the world to construct two networks of chess players. One of the networks includes games that were played over-the-board and the other contains games played on the Internet. We study the main topological characteristics of the networks, such as degree distribution and correlations, transitivity and community structure. We complement the structural analysis by incorporating players' level of play as node metadata. Although both networks are topologically different, we show that in both cases players gather in communities according to their expertise and that an emergent rich-club structure, composed by the top-rated players, is also present.

Self-organization in multilayer network with adaptation mechanisms based on competition

NASA Astrophysics Data System (ADS)

Pitsik, Elena N.; Makarov, Vladimir V.; Nedaivozov, Vladimir O.; Kirsanov, Daniil V.; Goremyko, Mikhail V.

2018-04-01

The paper considers the phenomena of competition in multiplex network whose structure evolves corresponding to dynamics of it's elements, forming closed loop of self-learning with the aim to reach the optimal topology. Numerical analysis of proposed model shows that it is possible to obtain scale-invariant structures for corresponding parameters as well as the structures with homogeneous distribution of connections in the layers. Revealed phenomena emerges as the consequence of the self-organization processes related to structure-dynamical selflearning based on homeostasis and homophily, as well as the result of the competition between the network's layers for optimal topology. It was shown that in the mode of partial and cluster synchronization the network reaches scale-free topology of complex nature that is different from layer to layer. However, in the mode of global synchronization the homogeneous topologies on all layer of the network are observed. This phenomenon is tightly connected with the competitive processes that represent themselves as the natural mechanism of reaching the optimal topology of the links in variety of real-world systems.

Structure-based control of complex networks with nonlinear dynamics

NASA Astrophysics Data System (ADS)

Zanudo, Jorge G. T.; Yang, Gang; Albert, Reka

What can we learn about controlling a system solely from its underlying network structure? Here we use a framework for control of networks governed by a broad class of nonlinear dynamics that includes the major dynamic models of biological, technological, and social processes. This feedback-based framework provides realizable node overrides that steer a system towards any of its natural long term dynamic behaviors, regardless of the dynamic details and system parameters. We use this framework on several real networks, identify the topological characteristics that underlie the predicted node overrides, and compare its predictions to those of classical structural control theory. Finally, we demonstrate this framework's applicability in dynamic models of gene regulatory networks and identify nodes whose override is necessary for control in the general case, but not in specific model instances. This work was supported by NSF Grants PHY 1205840 and IIS 1160995. JGTZ is a recipient of a Stand Up To Cancer - The V Foundation Convergence Scholar Award.

Functional networks inference from rule-based machine learning models.

PubMed

Lazzarini, Nicola; Widera, Paweł; Williamson, Stuart; Heer, Rakesh; Krasnogor, Natalio; Bacardit, Jaume

2016-01-01

Functional networks play an important role in the analysis of biological processes and systems. The inference of these networks from high-throughput (-omics) data is an area of intense research. So far, the similarity-based inference paradigm (e.g. gene co-expression) has been the most popular approach. It assumes a functional relationship between genes which are expressed at similar levels across different samples. An alternative to this paradigm is the inference of relationships from the structure of machine learning models. These models are able to capture complex relationships between variables, that often are different/complementary to the similarity-based methods. We propose a protocol to infer functional networks from machine learning models, called FuNeL. It assumes, that genes used together within a rule-based machine learning model to classify the samples, might also be functionally related at a biological level. The protocol is first tested on synthetic datasets and then evaluated on a test suite of 8 real-world datasets related to human cancer. The networks inferred from the real-world data are compared against gene co-expression networks of equal size, generated with 3 different methods. The comparison is performed from two different points of view. We analyse the enriched biological terms in the set of network nodes and the relationships between known disease-associated genes in a context of the network topology. The comparison confirms both the biological relevance and the complementary character of the knowledge captured by the FuNeL networks in relation to similarity-based methods and demonstrates its potential to identify known disease associations as core elements of the network. Finally, using a prostate cancer dataset as a case study, we confirm that the biological knowledge captured by our method is relevant to the disease and consistent with the specialised literature and with an independent dataset not used in the inference process. The implementation of our network inference protocol is available at: http://ico2s.org/software/funel.html.

Facebook for Supervision? Research Education Shaped by the Structural Properties of a Social Media Space

ERIC Educational Resources Information Center

Pimmer, Christoph; Chipps, Jennifer; Brysiewicz, Petra; Walters, Fiona; Linxen, Sebastian; Gröhbiel, Urs

2017-01-01

This study analyses the use of a group space on the social networking site Facebook as a way to facilitate research supervision for teams of learners. Borrowing Lee's framework for research supervision, the goal was to understand how supervision and learning was achieved in, and shaped by, the properties of a social networking space. For this…

Exploring the Potential of Social Network Sites in Relation to Intercultural Communication

ERIC Educational Resources Information Center

Lang, Anouk

2012-01-01

This article reports on the results of a project which used a social network site to support students on a year abroad and foster informal learning, particularly in the area of intercultural communication. The project employed a peer-mentoring structure to solve the problem of role conflict, in which users of these sites may feel some tension as…

Learning multivariate distributions by competitive assembly of marginals.

PubMed

Sánchez-Vega, Francisco; Younes, Laurent; Geman, Donald

2013-02-01

We present a new framework for learning high-dimensional multivariate probability distributions from estimated marginals. The approach is motivated by compositional models and Bayesian networks, and designed to adapt to small sample sizes. We start with a large, overlapping set of elementary statistical building blocks, or "primitives," which are low-dimensional marginal distributions learned from data. Each variable may appear in many primitives. Subsets of primitives are combined in a Lego-like fashion to construct a probabilistic graphical model; only a small fraction of the primitives will participate in any valid construction. Since primitives can be precomputed, parameter estimation and structure search are separated. Model complexity is controlled by strong biases; we adapt the primitives to the amount of training data and impose rules which restrict the merging of them into allowable compositions. The likelihood of the data decomposes into a sum of local gains, one for each primitive in the final structure. We focus on a specific subclass of networks which are binary forests. Structure optimization corresponds to an integer linear program and the maximizing composition can be computed for reasonably large numbers of variables. Performance is evaluated using both synthetic data and real datasets from natural language processing and computational biology.

Social media for lifelong learning.

PubMed

Kind, Terry; Evans, Yolanda

2015-04-01

Learning is ongoing, and can be considered a social activity. In this paper we aim to provide a review of the use of social media for lifelong learning. We start by defining lifelong learning, drawing upon principles of continuous professional development and adult learning theory. We searched Embase and MEDLINE from 2004-2014 for search terms relevant to social media and learning. We describe examples of lifelong learners using social media in medical education and healthcare that have been reported in the peer-reviewed literature. Medical or other health professions students may have qualities consistent with being a lifelong learner, yet once individuals move beyond structured learning environments they will need to recognize their own gaps in knowledge and skills over time and be motivated to fill them, thereby incorporating lifelong learning principles into their day-to-day practice. Engagement with social media can parallel engagement in the learning process over time, to the extent that online social networking fosters feedback and collaboration. The use of social media and online networking platforms are a key way to continuously learn in today's information sharing society. Additional research is needed, particularly rigorous studies that extend beyond learner satisfaction to knowledge, behaviour change, and outcomes.

Culture and biology in the origins of linguistic structure.

PubMed

Kirby, Simon

2017-02-01

Language is systematically structured at all levels of description, arguably setting it apart from all other instances of communication in nature. In this article, I survey work over the last 20 years that emphasises the contributions of individual learning, cultural transmission, and biological evolution to explaining the structural design features of language. These 3 complex adaptive systems exist in a network of interactions: individual learning biases shape the dynamics of cultural evolution; universal features of linguistic structure arise from this cultural process and form the ultimate linguistic phenotype; the nature of this phenotype affects the fitness landscape for the biological evolution of the language faculty; and in turn this determines individuals' learning bias. Using a combination of computational simulation, laboratory experiments, and comparison with real-world cases of language emergence, I show that linguistic structure emerges as a natural outcome of cultural evolution once certain minimal biological requirements are in place.

A new neural net approach to robot 3D perception and visuo-motor coordination

NASA Technical Reports Server (NTRS)

Lee, Sukhan

1992-01-01

A novel neural network approach to robot hand-eye coordination is presented. The approach provides a true sense of visual error servoing, redundant arm configuration control for collision avoidance, and invariant visuo-motor learning under gazing control. A 3-D perception network is introduced to represent the robot internal 3-D metric space in which visual error servoing and arm configuration control are performed. The arm kinematic network performs the bidirectional association between 3-D space arm configurations and joint angles, and enforces the legitimate arm configurations. The arm kinematic net is structured by a radial-based competitive and cooperative network with hierarchical self-organizing learning. The main goal of the present work is to demonstrate that the neural net representation of the robot 3-D perception net serves as an important intermediate functional block connecting robot eyes and arms.

Discover mouse gene coexpression landscapes using dictionary learning and sparse coding.

PubMed

Li, Yujie; Chen, Hanbo; Jiang, Xi; Li, Xiang; Lv, Jinglei; Peng, Hanchuan; Tsien, Joe Z; Liu, Tianming

2017-12-01

Gene coexpression patterns carry rich information regarding enormously complex brain structures and functions. Characterization of these patterns in an unbiased, integrated, and anatomically comprehensive manner will illuminate the higher-order transcriptome organization and offer genetic foundations of functional circuitry. Here using dictionary learning and sparse coding, we derived coexpression networks from the space-resolved anatomical comprehensive in situ hybridization data from Allen Mouse Brain Atlas dataset. The key idea is that if two genes use the same dictionary to represent their original signals, then their gene expressions must share similar patterns, thereby considering them as "coexpressed." For each network, we have simultaneous knowledge of spatial distributions, the genes in the network and the extent a particular gene conforms to the coexpression pattern. Gene ontologies and the comparisons with published gene lists reveal biologically identified coexpression networks, some of which correspond to major cell types, biological pathways, and/or anatomical regions.

Deep Artificial Neural Networks and Neuromorphic Chips for Big Data Analysis: Pharmaceutical and Bioinformatics Applications.

PubMed

Pastur-Romay, Lucas Antón; Cedrón, Francisco; Pazos, Alejandro; Porto-Pazos, Ana Belén

2016-08-11

Over the past decade, Deep Artificial Neural Networks (DNNs) have become the state-of-the-art algorithms in Machine Learning (ML), speech recognition, computer vision, natural language processing and many other tasks. This was made possible by the advancement in Big Data, Deep Learning (DL) and drastically increased chip processing abilities, especially general-purpose graphical processing units (GPGPUs). All this has created a growing interest in making the most of the potential offered by DNNs in almost every field. An overview of the main architectures of DNNs, and their usefulness in Pharmacology and Bioinformatics are presented in this work. The featured applications are: drug design, virtual screening (VS), Quantitative Structure-Activity Relationship (QSAR) research, protein structure prediction and genomics (and other omics) data mining. The future need of neuromorphic hardware for DNNs is also discussed, and the two most advanced chips are reviewed: IBM TrueNorth and SpiNNaker. In addition, this review points out the importance of considering not only neurons, as DNNs and neuromorphic chips should also include glial cells, given the proven importance of astrocytes, a type of glial cell which contributes to information processing in the brain. The Deep Artificial Neuron-Astrocyte Networks (DANAN) could overcome the difficulties in architecture design, learning process and scalability of the current ML methods.

Self organising hypothesis networks: a new approach for representing and structuring SAR knowledge

PubMed Central

2014-01-01

Background Combining different sources of knowledge to build improved structure activity relationship models is not easy owing to the variety of knowledge formats and the absence of a common framework to interoperate between learning techniques. Most of the current approaches address this problem by using consensus models that operate at the prediction level. We explore the possibility to directly combine these sources at the knowledge level, with the aim to harvest potentially increased synergy at an earlier stage. Our goal is to design a general methodology to facilitate knowledge discovery and produce accurate and interpretable models. Results To combine models at the knowledge level, we propose to decouple the learning phase from the knowledge application phase using a pivot representation (lingua franca) based on the concept of hypothesis. A hypothesis is a simple and interpretable knowledge unit. Regardless of its origin, knowledge is broken down into a collection of hypotheses. These hypotheses are subsequently organised into hierarchical network. This unification permits to combine different sources of knowledge into a common formalised framework. The approach allows us to create a synergistic system between different forms of knowledge and new algorithms can be applied to leverage this unified model. This first article focuses on the general principle of the Self Organising Hypothesis Network (SOHN) approach in the context of binary classification problems along with an illustrative application to the prediction of mutagenicity. Conclusion It is possible to represent knowledge in the unified form of a hypothesis network allowing interpretable predictions with performances comparable to mainstream machine learning techniques. This new approach offers the potential to combine knowledge from different sources into a common framework in which high level reasoning and meta-learning can be applied; these latter perspectives will be explored in future work. PMID:24959206

Understanding the Convolutional Neural Networks with Gradient Descent and Backpropagation

NASA Astrophysics Data System (ADS)

Zhou, XueFei

2018-04-01

With the development of computer technology, the applications of machine learning are more and more extensive. And machine learning is providing endless opportunities to develop new applications. One of those applications is image recognition by using Convolutional Neural Networks (CNNs). CNN is one of the most common algorithms in image recognition. It is significant to understand its theory and structure for every scholar who is interested in this field. CNN is mainly used in computer identification, especially in voice, text recognition and other aspects of the application. It utilizes hierarchical structure with different layers to accelerate computing speed. In addition, the greatest features of CNNs are the weight sharing and dimension reduction. And all of these consolidate the high effectiveness and efficiency of CNNs with idea computing speed and error rate. With the help of other learning altruisms, CNNs could be used in several scenarios for machine learning, especially for deep learning. Based on the general introduction to the background and the core solution CNN, this paper is going to focus on summarizing how Gradient Descent and Backpropagation work, and how they contribute to the high performances of CNNs. Also, some practical applications will be discussed in the following parts. The last section exhibits the conclusion and some perspectives of future work.

High resolution depth reconstruction from monocular images and sparse point clouds using deep convolutional neural network

NASA Astrophysics Data System (ADS)

Dimitrievski, Martin; Goossens, Bart; Veelaert, Peter; Philips, Wilfried

2017-09-01

Understanding the 3D structure of the environment is advantageous for many tasks in the field of robotics and autonomous vehicles. From the robot's point of view, 3D perception is often formulated as a depth image reconstruction problem. In the literature, dense depth images are often recovered deterministically from stereo image disparities. Other systems use an expensive LiDAR sensor to produce accurate, but semi-sparse depth images. With the advent of deep learning there have also been attempts to estimate depth by only using monocular images. In this paper we combine the best of the two worlds, focusing on a combination of monocular images and low cost LiDAR point clouds. We explore the idea that very sparse depth information accurately captures the global scene structure while variations in image patches can be used to reconstruct local depth to a high resolution. The main contribution of this paper is a supervised learning depth reconstruction system based on a deep convolutional neural network. The network is trained on RGB image patches reinforced with sparse depth information and the output is a depth estimate for each pixel. Using image and point cloud data from the KITTI vision dataset we are able to learn a correspondence between local RGB information and local depth, while at the same time preserving the global scene structure. Our results are evaluated on sequences from the KITTI dataset and our own recordings using a low cost camera and LiDAR setup.

A Collaborative Learning Network Approach to Improvement: The CUSP Learning Network.

PubMed

Weaver, Sallie J; Lofthus, Jennifer; Sawyer, Melinda; Greer, Lee; Opett, Kristin; Reynolds, Catherine; Wyskiel, Rhonda; Peditto, Stephanie; Pronovost, Peter J

2015-04-01

Collaborative improvement networks draw on the science of collaborative organizational learning and communities of practice to facilitate peer-to-peer learning, coaching, and local adaption. Although significant improvements in patient safety and quality have been achieved through collaborative methods, insight regarding how collaborative networks are used by members is needed. Improvement Strategy: The Comprehensive Unit-based Safety Program (CUSP) Learning Network is a multi-institutional collaborative network that is designed to facilitate peer-to-peer learning and coaching specifically related to CUSP. Member organizations implement all or part of the CUSP methodology to improve organizational safety culture, patient safety, and care quality. Qualitative case studies developed by participating members examine the impact of network participation across three levels of analysis (unit, hospital, health system). In addition, results of a satisfaction survey designed to evaluate member experiences were collected to inform network development. Common themes across case studies suggest that members found value in collaborative learning and sharing strategies across organizational boundaries related to a specific improvement strategy. The CUSP Learning Network is an example of network-based collaborative learning in action. Although this learning network focuses on a particular improvement methodology-CUSP-there is clear potential for member-driven learning networks to grow around other methods or topic areas. Such collaborative learning networks may offer a way to develop an infrastructure for longer-term support of improvement efforts and to more quickly diffuse creative sustainment strategies.

Neural networks for learning and prediction with applications to remote sensing and speech perception

NASA Astrophysics Data System (ADS)

Gjaja, Marin N.

1997-11-01

Neural networks for supervised and unsupervised learning are developed and applied to problems in remote sensing, continuous map learning, and speech perception. Adaptive Resonance Theory (ART) models are real-time neural networks for category learning, pattern recognition, and prediction. Unsupervised fuzzy ART networks synthesize fuzzy logic and neural networks, and supervised ARTMAP networks incorporate ART modules for prediction and classification. New ART and ARTMAP methods resulting from analyses of data structure, parameter specification, and category selection are developed. Architectural modifications providing flexibility for a variety of applications are also introduced and explored. A new methodology for automatic mapping from Landsat Thematic Mapper (TM) and terrain data, based on fuzzy ARTMAP, is developed. System capabilities are tested on a challenging remote sensing problem, prediction of vegetation classes in the Cleveland National Forest from spectral and terrain features. After training at the pixel level, performance is tested at the stand level, using sites not seen during training. Results are compared to those of maximum likelihood classifiers, back propagation neural networks, and K-nearest neighbor algorithms. Best performance is obtained using a hybrid system based on a convex combination of fuzzy ARTMAP and maximum likelihood predictions. This work forms the foundation for additional studies exploring fuzzy ARTMAP's capability to estimate class mixture composition for non-homogeneous sites. Exploratory simulations apply ARTMAP to the problem of learning continuous multidimensional mappings. A novel system architecture retains basic ARTMAP properties of incremental and fast learning in an on-line setting while adding components to solve this class of problems. The perceptual magnet effect is a language-specific phenomenon arising early in infant speech development that is characterized by a warping of speech sound perception. An unsupervised neural network model is proposed that embodies two principal hypotheses supported by experimental data--that sensory experience guides language-specific development of an auditory neural map and that a population vector can predict psychological phenomena based on map cell activities. Model simulations show how a nonuniform distribution of map cell firing preferences can develop from language-specific input and give rise to the magnet effect.

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

The Effect of Interactive, Three Dimensional, High Speed Simulations on High School Science Students' Conceptions of the Molecular Structure of Water.

ERIC Educational Resources Information Center

Hakerem, Gita; And Others

The Water and Molecular Networks (WAMNet) Project uses graduate student written Reduced Instruction Set Computing (RISC) computer simulations of the molecular structure of water to assist high school students learn about the nature of water. This study examined: (1) preconceptions concerning the molecular structure of water common among high…

Pattern classification and recognition of invertebrate functional groups using self-organizing neural networks.

PubMed

Zhang, WenJun

2007-07-01

Self-organizing neural networks can be used to mimic non-linear systems. The main objective of this study is to make pattern classification and recognition on sampling information using two self-organizing neural network models. Invertebrate functional groups sampled in the irrigated rice field were classified and recognized using one-dimensional self-organizing map and self-organizing competitive learning neural networks. Comparisons between neural network models, distance (similarity) measures, and number of neurons were conducted. The results showed that self-organizing map and self-organizing competitive learning neural network models were effective in pattern classification and recognition of sampling information. Overall the performance of one-dimensional self-organizing map neural network was better than self-organizing competitive learning neural network. The number of neurons could determine the number of classes in the classification. Different neural network models with various distance (similarity) measures yielded similar classifications. Some differences, dependent upon the specific network structure, would be found. The pattern of an unrecognized functional group was recognized with the self-organizing neural network. A relative consistent classification indicated that the following invertebrate functional groups, terrestrial blood sucker; terrestrial flyer; tourist (nonpredatory species with no known functional role other than as prey in ecosystem); gall former; collector (gather, deposit feeder); predator and parasitoid; leaf miner; idiobiont (acarine ectoparasitoid), were classified into the same group, and the following invertebrate functional groups, external plant feeder; terrestrial crawler, walker, jumper or hunter; neustonic (water surface) swimmer (semi-aquatic), were classified into another group. It was concluded that reliable conclusions could be drawn from comparisons of different neural network models that use different distance (similarity) measures. Results with the larger consistency will be more reliable.

Quantum-chemical insights from deep tensor neural networks

PubMed Central

Schütt, Kristof T.; Arbabzadah, Farhad; Chmiela, Stefan; Müller, Klaus R.; Tkatchenko, Alexandre

2017-01-01

Learning from data has led to paradigm shifts in a multitude of disciplines, including web, text and image search, speech recognition, as well as bioinformatics. Can machine learning enable similar breakthroughs in understanding quantum many-body systems? Here we develop an efficient deep learning approach that enables spatially and chemically resolved insights into quantum-mechanical observables of molecular systems. We unify concepts from many-body Hamiltonians with purpose-designed deep tensor neural networks, which leads to size-extensive and uniformly accurate (1 kcal mol−1) predictions in compositional and configurational chemical space for molecules of intermediate size. As an example of chemical relevance, the model reveals a classification of aromatic rings with respect to their stability. Further applications of our model for predicting atomic energies and local chemical potentials in molecules, reliable isomer energies, and molecules with peculiar electronic structure demonstrate the potential of machine learning for revealing insights into complex quantum-chemical systems. PMID:28067221

Quantum-chemical insights from deep tensor neural networks.

PubMed

Schütt, Kristof T; Arbabzadah, Farhad; Chmiela, Stefan; Müller, Klaus R; Tkatchenko, Alexandre

2017-01-09

Learning from data has led to paradigm shifts in a multitude of disciplines, including web, text and image search, speech recognition, as well as bioinformatics. Can machine learning enable similar breakthroughs in understanding quantum many-body systems? Here we develop an efficient deep learning approach that enables spatially and chemically resolved insights into quantum-mechanical observables of molecular systems. We unify concepts from many-body Hamiltonians with purpose-designed deep tensor neural networks, which leads to size-extensive and uniformly accurate (1 kcal mol -1 ) predictions in compositional and configurational chemical space for molecules of intermediate size. As an example of chemical relevance, the model reveals a classification of aromatic rings with respect to their stability. Further applications of our model for predicting atomic energies and local chemical potentials in molecules, reliable isomer energies, and molecules with peculiar electronic structure demonstrate the potential of machine learning for revealing insights into complex quantum-chemical systems.

Quantum-chemical insights from deep tensor neural networks

NASA Astrophysics Data System (ADS)

Schütt, Kristof T.; Arbabzadah, Farhad; Chmiela, Stefan; Müller, Klaus R.; Tkatchenko, Alexandre

2017-01-01

Learning from data has led to paradigm shifts in a multitude of disciplines, including web, text and image search, speech recognition, as well as bioinformatics. Can machine learning enable similar breakthroughs in understanding quantum many-body systems? Here we develop an efficient deep learning approach that enables spatially and chemically resolved insights into quantum-mechanical observables of molecular systems. We unify concepts from many-body Hamiltonians with purpose-designed deep tensor neural networks, which leads to size-extensive and uniformly accurate (1 kcal mol-1) predictions in compositional and configurational chemical space for molecules of intermediate size. As an example of chemical relevance, the model reveals a classification of aromatic rings with respect to their stability. Further applications of our model for predicting atomic energies and local chemical potentials in molecules, reliable isomer energies, and molecules with peculiar electronic structure demonstrate the potential of machine learning for revealing insights into complex quantum-chemical systems.

Building machines that learn and think like people.

PubMed

Lake, Brenden M; Ullman, Tomer D; Tenenbaum, Joshua B; Gershman, Samuel J

2017-01-01

Recent progress in artificial intelligence has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats that of humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn and how they learn it. Specifically, we argue that these machines should (1) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (2) ground learning in intuitive theories of physics and psychology to support and enrich the knowledge that is learned; and (3) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes toward these goals that can combine the strengths of recent neural network advances with more structured cognitive models.

SVM-based tree-type neural networks as a critic in adaptive critic designs for control.

PubMed

Deb, Alok Kanti; Jayadeva; Gopal, Madan; Chandra, Suresh

2007-07-01

In this paper, we use the approach of adaptive critic design (ACD) for control, specifically, the action-dependent heuristic dynamic programming (ADHDP) method. A least squares support vector machine (SVM) regressor has been used for generating the control actions, while an SVM-based tree-type neural network (NN) is used as the critic. After a failure occurs, the critic and action are retrained in tandem using the failure data. Failure data is binary classification data, where the number of failure states are very few as compared to the number of no-failure states. The difficulty of conventional multilayer feedforward NNs in learning this type of classification data has been overcome by using the SVM-based tree-type NN, which due to its feature to add neurons to learn misclassified data, has the capability to learn any binary classification data without a priori choice of the number of neurons or the structure of the network. The capability of the trained controller to handle unforeseen situations is demonstrated.

Machine-Learning Classifier for Patients with Major Depressive Disorder: Multifeature Approach Based on a High-Order Minimum Spanning Tree Functional Brain Network.

PubMed

Guo, Hao; Qin, Mengna; Chen, Junjie; Xu, Yong; Xiang, Jie

2017-01-01

High-order functional connectivity networks are rich in time information that can reflect dynamic changes in functional connectivity between brain regions. Accordingly, such networks are widely used to classify brain diseases. However, traditional methods for processing high-order functional connectivity networks generally include the clustering method, which reduces data dimensionality. As a result, such networks cannot be effectively interpreted in the context of neurology. Additionally, due to the large scale of high-order functional connectivity networks, it can be computationally very expensive to use complex network or graph theory to calculate certain topological properties. Here, we propose a novel method of generating a high-order minimum spanning tree functional connectivity network. This method increases the neurological significance of the high-order functional connectivity network, reduces network computing consumption, and produces a network scale that is conducive to subsequent network analysis. To ensure the quality of the topological information in the network structure, we used frequent subgraph mining technology to capture the discriminative subnetworks as features and combined this with quantifiable local network features. Then we applied a multikernel learning technique to the corresponding selected features to obtain the final classification results. We evaluated our proposed method using a data set containing 38 patients with major depressive disorder and 28 healthy controls. The experimental results showed a classification accuracy of up to 97.54%.

Machine-Learning Classifier for Patients with Major Depressive Disorder: Multifeature Approach Based on a High-Order Minimum Spanning Tree Functional Brain Network

PubMed Central

Qin, Mengna; Chen, Junjie; Xu, Yong; Xiang, Jie

2017-01-01

High-order functional connectivity networks are rich in time information that can reflect dynamic changes in functional connectivity between brain regions. Accordingly, such networks are widely used to classify brain diseases. However, traditional methods for processing high-order functional connectivity networks generally include the clustering method, which reduces data dimensionality. As a result, such networks cannot be effectively interpreted in the context of neurology. Additionally, due to the large scale of high-order functional connectivity networks, it can be computationally very expensive to use complex network or graph theory to calculate certain topological properties. Here, we propose a novel method of generating a high-order minimum spanning tree functional connectivity network. This method increases the neurological significance of the high-order functional connectivity network, reduces network computing consumption, and produces a network scale that is conducive to subsequent network analysis. To ensure the quality of the topological information in the network structure, we used frequent subgraph mining technology to capture the discriminative subnetworks as features and combined this with quantifiable local network features. Then we applied a multikernel learning technique to the corresponding selected features to obtain the final classification results. We evaluated our proposed method using a data set containing 38 patients with major depressive disorder and 28 healthy controls. The experimental results showed a classification accuracy of up to 97.54%. PMID:29387141

Optimized Structure of the Traffic Flow Forecasting Model With a Deep Learning Approach.

PubMed

Yang, Hao-Fan; Dillon, Tharam S; Chen, Yi-Ping Phoebe

2017-10-01

Forecasting accuracy is an important issue for successful intelligent traffic management, especially in the domain of traffic efficiency and congestion reduction. The dawning of the big data era brings opportunities to greatly improve prediction accuracy. In this paper, we propose a novel model, stacked autoencoder Levenberg-Marquardt model, which is a type of deep architecture of neural network approach aiming to improve forecasting accuracy. The proposed model is designed using the Taguchi method to develop an optimized structure and to learn traffic flow features through layer-by-layer feature granulation with a greedy layerwise unsupervised learning algorithm. It is applied to real-world data collected from the M6 freeway in the U.K. and is compared with three existing traffic predictors. To the best of our knowledge, this is the first time that an optimized structure of the traffic flow forecasting model with a deep learning approach is presented. The evaluation results demonstrate that the proposed model with an optimized structure has superior performance in traffic flow forecasting.

Network integration and limits to social inheritance in vervet monkeys.

PubMed

Jarrett, Jonathan D; Bonnell, Tyler R; Young, Christopher; Barrett, Louise; Henzi, S Peter

2018-04-11

Social networks can be adaptive for members and a recent model (Ilany and Akçay 2016 Nat. Comm. 7 , 12084 (doi:10.1038/ncomms12084)) has demonstrated that network structure can be maintained by a simple process of social inheritance. Here, we ask how juvenile vervet monkeys integrate into their adult grooming networks, using the model to test whether observed grooming patterns replicate network structure. Female juveniles, who are philopatric, increased their grooming effort towards adults more than males, although this was not reciprocated by the adults themselves. While more consistent maternal grooming networks, together with maternal network strength, predicted increasing similarity in the patterning of mother-daughter grooming allocations, daughters' grooming networks generally did not match closely those of their mothers. However, maternal networks themselves were not very consistent across time, thus presenting youngsters with a moving target that may be difficult to match. Observed patterns of juvenile female grooming did not replicate the adult network, for which increased association with adults not groomed by their mothers would be necessary. These results suggest that network flexibility, not stability, characterizes our groups and that juveniles are exposed to, and must learn to cope with, temporal shifts in network structure. We hypothesize that this may lead to individual variation in behavioural flexibility, which in turn may help explain why and how variation in sociability influences fitness. © 2018 The Author(s).

A Dialogic Action Perspective on Open Collective Inquiry in Online Forums

ERIC Educational Resources Information Center

Jung, Yusun

2012-01-01

In today's networked environment, online forums emerge as a popular form of social structures that have greater opportunities for learning in various organizational contexts. A plethora of studies have investigated the phenomenon to identify antecedent of its success, such as individual characteristics and organizational structure. However,…

Sunspot drawings handwritten character recognition method based on deep learning

NASA Astrophysics Data System (ADS)

Zheng, Sheng; Zeng, Xiangyun; Lin, Ganghua; Zhao, Cui; Feng, Yongli; Tao, Jinping; Zhu, Daoyuan; Xiong, Li

2016-05-01

High accuracy scanned sunspot drawings handwritten characters recognition is an issue of critical importance to analyze sunspots movement and store them in the database. This paper presents a robust deep learning method for scanned sunspot drawings handwritten characters recognition. The convolution neural network (CNN) is one algorithm of deep learning which is truly successful in training of multi-layer network structure. CNN is used to train recognition model of handwritten character images which are extracted from the original sunspot drawings. We demonstrate the advantages of the proposed method on sunspot drawings provided by Chinese Academy Yunnan Observatory and obtain the daily full-disc sunspot numbers and sunspot areas from the sunspot drawings. The experimental results show that the proposed method achieves a high recognition accurate rate.

Machine-learning approach for local classification of crystalline structures in multiphase systems

NASA Astrophysics Data System (ADS)

Dietz, C.; Kretz, T.; Thoma, M. H.

2017-07-01

Machine learning is one of the most popular fields in computer science and has a vast number of applications. In this work we will propose a method that will use a neural network to locally identify crystal structures in a mixed phase Yukawa system consisting of fcc, hcp, and bcc clusters and disordered particles similar to plasma crystals. We compare our approach to already used methods and show that the quality of identification increases significantly. The technique works very well for highly disturbed lattices and shows a flexible and robust way to classify crystalline structures that can be used by only providing particle positions. This leads to insights into highly disturbed crystalline structures.

Using an Instructional LAN to Teach a Statistics Course.

ERIC Educational Resources Information Center

Barnes, J. Wesley; And Others

1988-01-01

Discusses a computer assisted learning system for engineering statistics based on personalized system of instruction methods. Describes the system's network, development, course structure, programing, and security. Lists the benefits of the system. (MVL)

Korean immigrants don't buy health insurance: The influences of culture on self-employed Korean immigrants focusing on structure and functions of social networks.

PubMed

Oh, Hyunsung; Jeong, Chung Hyeon

2017-10-01

Culture has been pinpointed as a culprit of disparities in health insurance coverage between Korean immigrants and other ethnic groups. This study explored specific mechanisms by which culture influences a decision to buy health insurance among self-employed Korean immigrants living in ethnic enclaves by focusing on the structure and functions of social networks. Between March and June 2015, we recruited 24 Korean immigrant adults (aged 18 or older) who identified as self-employed and being uninsured for substantial periods before 2014 in Southern California. Interviews were conducted in Korean, and Korean transcripts were translated into English by two bilingual interpreters. Using constant comparative analysis, we explored why participants didn't purchase health insurance after migrating to the United States and how their social networks influenced their decisions whether to purchase health insurance. Results indicate Korean immigrants sought health information from dense and homogeneous social networks whose members are mostly Korean immigrants embedded in similar social contexts. Social learning was frequently observed when people sought health care while uninsured. However, respondents often noted social ties do not provide helpful information about benefits, costs, and ways to use health insurance. "Koreans don't buy health insurance" was a dominant social norm reported by most respondents. Findings indicate that social learning and normative influence occur inside social networks and these mechanisms seemingly prevent purchasing of health insurance. In addition to the individual mandate in the Patient Protection and Affordable Care Act, more targeted approaches that consider the structure and functions of social networks could improve the public health of Korean immigrants. Copyright © 2017 Elsevier Ltd. All rights reserved.

Performance of Deep and Shallow Neural Networks, the Universal Approximation Theorem, Activity Cliffs, and QSAR.

PubMed

Winkler, David A; Le, Tu C

2017-01-01

Neural networks have generated valuable Quantitative Structure-Activity/Property Relationships (QSAR/QSPR) models for a wide variety of small molecules and materials properties. They have grown in sophistication and many of their initial problems have been overcome by modern mathematical techniques. QSAR studies have almost always used so-called "shallow" neural networks in which there is a single hidden layer between the input and output layers. Recently, a new and potentially paradigm-shifting type of neural network based on Deep Learning has appeared. Deep learning methods have generated impressive improvements in image and voice recognition, and are now being applied to QSAR and QSAR modelling. This paper describes the differences in approach between deep and shallow neural networks, compares their abilities to predict the properties of test sets for 15 large drug data sets (the kaggle set), discusses the results in terms of the Universal Approximation theorem for neural networks, and describes how DNN may ameliorate or remove troublesome "activity cliffs" in QSAR data sets. © 2017 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim.

Echo state networks with filter neurons and a delay&sum readout.

PubMed

Holzmann, Georg; Hauser, Helmut

2010-03-01

Echo state networks (ESNs) are a novel approach to recurrent neural network training with the advantage of a very simple and linear learning algorithm. It has been demonstrated that ESNs outperform other methods on a number of benchmark tasks. Although the approach is appealing, there are still some inherent limitations in the original formulation. Here we suggest two enhancements of this network model. First, the previously proposed idea of filters in neurons is extended to arbitrary infinite impulse response (IIR) filter neurons. This enables such networks to learn multiple attractors and signals at different timescales, which is especially important for modeling real-world time series. Second, a delay&sum readout is introduced, which adds trainable delays in the synaptic connections of output neurons and therefore vastly improves the memory capacity of echo state networks. It is shown in commonly used benchmark tasks and real-world examples, that this new structure is able to significantly outperform standard ESNs and other state-of-the-art models for nonlinear dynamical system modeling. Copyright 2009 Elsevier Ltd. All rights reserved.

Detecting trends in academic research from a citation network using network representation learning

PubMed Central

Mori, Junichiro; Ochi, Masanao; Sakata, Ichiro

2018-01-01

Several network features and information retrieval methods have been proposed to elucidate the structure of citation networks and to detect important nodes. However, it is difficult to retrieve information related to trends in an academic field and to detect cutting-edge areas from the citation network. In this paper, we propose a novel framework that detects the trend as the growth direction of a citation network using network representation learning(NRL). We presume that the linear growth of citation network in latent space obtained by NRL is the result of the iterative edge additional process of a citation network. On APS datasets and papers of some domains of the Web of Science, we confirm the existence of trends by observing that an academic field grows in a specific direction linearly in latent space. Next, we calculate each node’s degree of trend-following as an indicator called the intrinsic publication year (IPY). As a result, there is a correlation between the indicator and the number of future citations. Furthermore, a word frequently used in the abstracts of cutting-edge papers (high-IPY paper) is likely to be used often in future publications. These results confirm the validity of the detected trend for predicting citation network growth. PMID:29782521

A model for evolution of overlapping community networks

NASA Astrophysics Data System (ADS)

Karan, Rituraj; Biswal, Bibhu

2017-05-01

A model is proposed for the evolution of network topology in social networks with overlapping community structure. Starting from an initial community structure that is defined in terms of group affiliations, the model postulates that the subsequent growth and loss of connections is similar to the Hebbian learning and unlearning in the brain and is governed by two dominant factors: the strength and frequency of interaction between the members, and the degree of overlap between different communities. The temporal evolution from an initial community structure to the current network topology can be described based on these two parameters. It is possible to quantify the growth occurred so far and predict the final stationary state to which the network is likely to evolve. Applications in epidemiology or the spread of email virus in a computer network as well as finding specific target nodes to control it are envisaged. While facing the challenge of collecting and analyzing large-scale time-resolved data on social groups and communities one faces the most basic questions: how do communities evolve in time? This work aims to address this issue by developing a mathematical model for the evolution of community networks and studying it through computer simulation.

Deep learning for medical image segmentation - using the IBM TrueNorth neurosynaptic system

NASA Astrophysics Data System (ADS)

Moran, Steven; Gaonkar, Bilwaj; Whitehead, William; Wolk, Aidan; Macyszyn, Luke; Iyer, Subramanian S.

2018-03-01

Deep convolutional neural networks have found success in semantic image segmentation tasks in computer vision and medical imaging. These algorithms are executed on conventional von Neumann processor architectures or GPUs. This is suboptimal. Neuromorphic processors that replicate the structure of the brain are better-suited to train and execute deep learning models for image segmentation by relying on massively-parallel processing. However, given that they closely emulate the human brain, on-chip hardware and digital memory limitations also constrain them. Adapting deep learning models to execute image segmentation tasks on such chips, requires specialized training and validation. In this work, we demonstrate for the first-time, spinal image segmentation performed using a deep learning network implemented on neuromorphic hardware of the IBM TrueNorth Neurosynaptic System and validate the performance of our network by comparing it to human-generated segmentations of spinal vertebrae and disks. To achieve this on neuromorphic hardware, the training model constrains the coefficients of individual neurons to {-1,0,1} using the Energy Efficient Deep Neuromorphic (EEDN)1 networks training algorithm. Given the 1 million neurons and 256 million synapses, the scale and size of the neural network implemented by the IBM TrueNorth allows us to execute the requisite mapping between segmented images and non-uniform intensity MR images >20 times faster than on a GPU-accelerated network and using <0.1 W. This speed and efficiency implies that a trained neuromorphic chip can be deployed in intra-operative environments where real-time medical image segmentation is necessary.

Robust recognition of handwritten numerals based on dual cooperative network

NASA Technical Reports Server (NTRS)

Lee, Sukhan; Choi, Yeongwoo

1992-01-01

An approach to robust recognition of handwritten numerals using two operating parallel networks is presented. The first network uses inputs in Cartesian coordinates, and the second network uses the same inputs transformed into polar coordinates. How the proposed approach realizes the robustness to local and global variations of input numerals by handling inputs both in Cartesian coordinates and in its transformed Polar coordinates is described. The required network structures and its learning scheme are discussed. Experimental results show that by tracking only a small number of distinctive features for each teaching numeral in each coordinate, the proposed system can provide robust recognition of handwritten numerals.

Information flow through threespine stickleback networks without social transmission

PubMed Central

Atton, N.; Hoppitt, W.; Webster, M. M.; Galef, B. G.; Laland, K. N.

2012-01-01

Social networks can result in directed social transmission of learned information, thus influencing how innovations spread through populations. Here we presented shoals of threespine sticklebacks (Gasterosteous aculeatus) with two identical foraging tasks and applied network-based diffusion analysis (NBDA) to determine whether the order in which individuals in a social group contacted and solved the tasks was affected by the group's network structure. We found strong evidence for a social effect on discovery of the foraging tasks with individuals tending to discover a task sooner when others in their group had previously done so, and with the spread of discovery of the foraging tasks influenced by groups' social networks. However, the same patterns of association did not reliably predict spread of solution to the tasks, suggesting that social interactions affected the time at which the tasks were discovered, but not the latency to its solution following discovery. The present analysis, one of the first applications of NBDA to a natural animal system, illustrates how NBDA can lead to insight into the mechanisms supporting behaviour acquisition that more conventional statistical approaches might miss. Importantly, we provide the first compelling evidence that the spread of novel behaviours can result from social learning in the absence of social transmission, a phenomenon that we refer to as an untransmitted social effect on learning. PMID:22896644

Application of Deep Learning of Multi-Temporal SENTINEL-1 Images for the Classification of Coastal Vegetation Zone of the Danube Delta

NASA Astrophysics Data System (ADS)

Niculescu, S.; Ienco, D.; Hanganu, J.

2018-04-01

Land cover is a fundamental variable for regional planning, as well as for the study and understanding of the environment. This work propose a multi-temporal approach relying on a fusion of radar multi-sensor data and information collected by the latest sensor (Sentinel-1) with a view to obtaining better results than traditional image processing techniques. The Danube Delta is the site for this work. The spatial approach relies on new spatial analysis technologies and methodologies: Deep Learning of multi-temporal Sentinel-1. We propose a deep learning network for image classification which exploits the multi-temporal characteristic of Sentinel-1 data. The model we employ is a Gated Recurrent Unit (GRU) Network, a recurrent neural network that explicitly takes into account the time dimension via a gated mechanism to perform the final prediction. The main quality of the GRU network is its ability to consider only the important part of the information coming from the temporal data discarding the irrelevant information via a forgetting mechanism. We propose to use such network structure to classify a series of images Sentinel-1 (20 Sentinel-1 images acquired between 9.10.2014 and 01.04.2016). The results are compared with results of the classification of Random Forest.

Inter-synaptic learning of combination rules in a cortical network model

PubMed Central

Lavigne, Frédéric; Avnaïm, Francis; Dumercy, Laurent

2014-01-01

Selecting responses in working memory while processing combinations of stimuli depends strongly on their relations stored in long-term memory. However, the learning of XOR-like combinations of stimuli and responses according to complex rules raises the issue of the non-linear separability of the responses within the space of stimuli. One proposed solution is to add neurons that perform a stage of non-linear processing between the stimuli and responses, at the cost of increasing the network size. Based on the non-linear integration of synaptic inputs within dendritic compartments, we propose here an inter-synaptic (IS) learning algorithm that determines the probability of potentiating/depressing each synapse as a function of the co-activity of the other synapses within the same dendrite. The IS learning is effective with random connectivity and without either a priori wiring or additional neurons. Our results show that IS learning generates efficacy values that are sufficient for the processing of XOR-like combinations, on the basis of the sole correlational structure of the stimuli and responses. We analyze the types of dendrites involved in terms of the number of synapses from pre-synaptic neurons coding for the stimuli and responses. The synaptic efficacy values obtained show that different dendrites specialize in the detection of different combinations of stimuli. The resulting behavior of the cortical network model is analyzed as a function of inter-synaptic vs. Hebbian learning. Combinatorial priming effects show that the retrospective activity of neurons coding for the stimuli trigger XOR-like combination-selective prospective activity of neurons coding for the expected response. The synergistic effects of inter-synaptic learning and of mixed-coding neurons are simulated. The results show that, although each mechanism is sufficient by itself, their combined effects improve the performance of the network. PMID:25221529

Active vision and image/video understanding with decision structures based on the network-symbolic models

NASA Astrophysics Data System (ADS)

Kuvich, Gary

2003-08-01

Vision is a part of a larger information system that converts visual information into knowledge structures. These structures drive vision process, resolve ambiguity and uncertainty via feedback projections, and provide image understanding that is an interpretation of visual information in terms of such knowledge models. The ability of human brain to emulate knowledge structures in the form of networks-symbolic models is found. And that means an important shift of paradigm in our knowledge about brain from neural networks to "cortical software". Symbols, predicates and grammars naturally emerge in such active multilevel hierarchical networks, and logic is simply a way of restructuring such models. Brain analyzes an image as a graph-type decision structure created via multilevel hierarchical compression of visual information. Mid-level vision processes like clustering, perceptual grouping, separation of figure from ground, are special kinds of graph/network transformations. They convert low-level image structure into the set of more abstract ones, which represent objects and visual scene, making them easy for analysis by higher-level knowledge structures. Higher-level vision phenomena are results of such analysis. Composition of network-symbolic models works similar to frames and agents, combines learning, classification, analogy together with higher-level model-based reasoning into a single framework. Such models do not require supercomputers. Based on such principles, and using methods of Computational intelligence, an Image Understanding system can convert images into the network-symbolic knowledge models, and effectively resolve uncertainty and ambiguity, providing unifying representation for perception and cognition. That allows creating new intelligent computer vision systems for robotic and defense industries.

Pattern Storage, Bifurcations, and Groupwise Correlation Structure of an Exactly Solvable Asymmetric Neural Network Model.

PubMed

Fasoli, Diego; Cattani, Anna; Panzeri, Stefano

2018-05-01

Despite their biological plausibility, neural network models with asymmetric weights are rarely solved analytically, and closed-form solutions are available only in some limiting cases or in some mean-field approximations. We found exact analytical solutions of an asymmetric spin model of neural networks with arbitrary size without resorting to any approximation, and we comprehensively studied its dynamical and statistical properties. The network had discrete time evolution equations and binary firing rates, and it could be driven by noise with any distribution. We found analytical expressions of the conditional and stationary joint probability distributions of the membrane potentials and the firing rates. By manipulating the conditional probability distribution of the firing rates, we extend to stochastic networks the associating learning rule previously introduced by Personnaz and coworkers. The new learning rule allowed the safe storage, under the presence of noise, of point and cyclic attractors, with useful implications for content-addressable memories. Furthermore, we studied the bifurcation structure of the network dynamics in the zero-noise limit. We analytically derived examples of the codimension 1 and codimension 2 bifurcation diagrams of the network, which describe how the neuronal dynamics changes with the external stimuli. This showed that the network may undergo transitions among multistable regimes, oscillatory behavior elicited by asymmetric synaptic connections, and various forms of spontaneous symmetry breaking. We also calculated analytically groupwise correlations of neural activity in the network in the stationary regime. This revealed neuronal regimes where, statistically, the membrane potentials and the firing rates are either synchronous or asynchronous. Our results are valid for networks with any number of neurons, although our equations can be realistically solved only for small networks. For completeness, we also derived the network equations in the thermodynamic limit of infinite network size and we analytically studied their local bifurcations. All the analytical results were extensively validated by numerical simulations.

Learning Analytics for Networked Learning Models

ERIC Educational Resources Information Center

Joksimovic, Srecko; Hatala, Marek; Gaševic, Dragan

2014-01-01

Teaching and learning in networked settings has attracted significant attention recently. The central topic of networked learning research is human-human and human-information interactions occurring within a networked learning environment. The nature of these interactions is highly complex and usually requires a multi-dimensional approach to…

Complexity and non-commutativity of learning operations on graphs.

PubMed

Atmanspacher, Harald; Filk, Thomas

2006-07-01

We present results from numerical studies of supervised learning operations in small recurrent networks considered as graphs, leading from a given set of input conditions to predetermined outputs. Graphs that have optimized their output for particular inputs with respect to predetermined outputs are asymptotically stable and can be characterized by attractors, which form a representation space for an associative multiplicative structure of input operations. As the mapping from a series of inputs onto a series of such attractors generally depends on the sequence of inputs, this structure is generally non-commutative. Moreover, the size of the set of attractors, indicating the complexity of learning, is found to behave non-monotonically as learning proceeds. A tentative relation between this complexity and the notion of pragmatic information is indicated.

Motor-Skill Learning in an Insect Inspired Neuro-Computational Control System

PubMed Central

Arena, Eleonora; Arena, Paolo; Strauss, Roland; Patané, Luca

2017-01-01

In nature, insects show impressive adaptation and learning capabilities. The proposed computational model takes inspiration from specific structures of the insect brain: after proposing key hypotheses on the direct involvement of the mushroom bodies (MBs) and on their neural organization, we developed a new architecture for motor learning to be applied in insect-like walking robots. The proposed model is a nonlinear control system based on spiking neurons. MBs are modeled as a nonlinear recurrent spiking neural network (SNN) with novel characteristics, able to memorize time evolutions of key parameters of the neural motor controller, so that existing motor primitives can be improved. The adopted control scheme enables the structure to efficiently cope with goal-oriented behavioral motor tasks. Here, a six-legged structure, showing a steady-state exponentially stable locomotion pattern, is exposed to the need of learning new motor skills: moving through the environment, the structure is able to modulate motor commands and implements an obstacle climbing procedure. Experimental results on a simulated hexapod robot are reported; they are obtained in a dynamic simulation environment and the robot mimicks the structures of Drosophila melanogaster. PMID:28337138

Learning about learning: Mining human brain sub-network biomarkers from fMRI data

PubMed Central

Dereli, Nazli; Dang, Xuan-Hong; Bassett, Danielle S.; Wymbs, Nicholas F.; Grafton, Scott T.; Singh, Ambuj K.

2017-01-01

Modeling the brain as a functional network can reveal the relationship between distributed neurophysiological processes and functional interactions between brain structures. Existing literature on functional brain networks focuses mainly on a battery of network properties in “resting state” employing, for example, modularity, clustering, or path length among regions. In contrast, we seek to uncover functionally connected subnetworks that predict or correlate with cohort differences and are conserved within the subjects within a cohort. We focus on differences in both the rate of learning as well as overall performance in a sensorimotor task across subjects and develop a principled approach for the discovery of discriminative subgraphs of functional connectivity based on imaging acquired during practice. We discover two statistically significant subgraph regions: one involving multiple regions in the visual cortex and another involving the parietal operculum and planum temporale. High functional coherence in the former characterizes sessions in which subjects take longer to perform the task, while high coherence in the latter is associated with high learning rate (performance improvement across trials). Our proposed methodology is general, in that it can be applied to other cognitive tasks, to study learning or to differentiate between healthy patients and patients with neurological disorders, by revealing the salient interactions among brain regions associated with the observed global state. The discovery of such significant discriminative subgraphs promises a better data-driven understanding of the dynamic brain processes associated with high-level cognitive functions. PMID:29016686

Learning about learning: Mining human brain sub-network biomarkers from fMRI data.

PubMed

Bogdanov, Petko; Dereli, Nazli; Dang, Xuan-Hong; Bassett, Danielle S; Wymbs, Nicholas F; Grafton, Scott T; Singh, Ambuj K

2017-01-01

Modeling the brain as a functional network can reveal the relationship between distributed neurophysiological processes and functional interactions between brain structures. Existing literature on functional brain networks focuses mainly on a battery of network properties in "resting state" employing, for example, modularity, clustering, or path length among regions. In contrast, we seek to uncover functionally connected subnetworks that predict or correlate with cohort differences and are conserved within the subjects within a cohort. We focus on differences in both the rate of learning as well as overall performance in a sensorimotor task across subjects and develop a principled approach for the discovery of discriminative subgraphs of functional connectivity based on imaging acquired during practice. We discover two statistically significant subgraph regions: one involving multiple regions in the visual cortex and another involving the parietal operculum and planum temporale. High functional coherence in the former characterizes sessions in which subjects take longer to perform the task, while high coherence in the latter is associated with high learning rate (performance improvement across trials). Our proposed methodology is general, in that it can be applied to other cognitive tasks, to study learning or to differentiate between healthy patients and patients with neurological disorders, by revealing the salient interactions among brain regions associated with the observed global state. The discovery of such significant discriminative subgraphs promises a better data-driven understanding of the dynamic brain processes associated with high-level cognitive functions.

Multilayer Networks of Self-Interested Adaptive Units.

DTIC Science & Technology

1987-07-01

T. J. Sejnowski. A learning algorithm for Boltzmann machines. Cognitive Science, 9:147-169, 1985. 121 S. Amarel. Problems of Representation in...Barto and C. W. Anderson. Structural learning in connectionist sys- tems. In Proceedings of the Seventh Annual Conference of the Cognitive Science...E. Hinton and T. J. Sejnowski. Analyzing cooperative computation. In Proceedings of the Fifth Annual Conference of the Cognitive Science Society

Humans and Autonomy: Implications of Shared Decision Making for Military Operations

DTIC Science & Technology

2017-01-01

and machine learning transparency are identified as future research opportunities. 15. SUBJECT TERMS autonomy, human factors, intelligent agents...network as either the mission changes or an agent becomes disabled (DSB 2012). Fig. 2 Control structures for human agent teams. Robots without tools... learning (ML) algorithms monitor progress. However, operators have final executive authority; they are able to tweak the plan or choose an option

Modeling Temporal Variation in Social Network: An Evolutionary Web Graph Approach

NASA Astrophysics Data System (ADS)

Mitra, Susanta; Bagchi, Aditya

A social network is a social structure between actors (individuals, organization or other social entities) and indicates the ways in which they are connected through various social relationships like friendships, kinships, professional, academic etc. Usually, a social network represents a social community, like a club and its members or a city and its citizens etc. or a research group communicating over Internet. In seventies Leinhardt [1] first proposed the idea of representing a social community by a digraph. Later, this idea became popular among other research workers like, network designers, web-service application developers and e-learning modelers. It gave rise to a rapid proliferation of research work in the area of social network analysis. Some of the notable structural properties of a social network are connectedness between actors, reachability between a source and a target actor, reciprocity or pair-wise connection between actors with bi-directional links, centrality of actors or the important actors having high degree or more connections and finally the division of actors into sub-structures or cliques or strongly-connected components. The cycles present in a social network may even be nested [2, 3]. The formal definition of these structural properties will be provided in Sect. 8.2.1. The division of actors into cliques or sub-groups can be a very important factor for understanding a social structure, particularly the degree of cohesiveness in a community. The number, size, and connections among the sub-groups in a network are useful in understanding how the network, as a whole, is likely to behave.

The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction.

PubMed

Casey, M

1996-08-15

Recurrent neural networks (RNNs) can learn to perform finite state computations. It is shown that an RNN performing a finite state computation must organize its state space to mimic the states in the minimal deterministic finite state machine that can perform that computation, and a precise description of the attractor structure of such systems is given. This knowledge effectively predicts activation space dynamics, which allows one to understand RNN computation dynamics in spite of complexity in activation dynamics. This theory provides a theoretical framework for understanding finite state machine (FSM) extraction techniques and can be used to improve training methods for RNNs performing FSM computations. This provides an example of a successful approach to understanding a general class of complex systems that has not been explicitly designed, e.g., systems that have evolved or learned their internal structure.

Evolving neural networks through augmenting topologies.

PubMed

Stanley, Kenneth O; Miikkulainen, Risto

2002-01-01

An important question in neuroevolution is how to gain an advantage from evolving neural network topologies along with weights. We present a method, NeuroEvolution of Augmenting Topologies (NEAT), which outperforms the best fixed-topology method on a challenging benchmark reinforcement learning task. We claim that the increased efficiency is due to (1) employing a principled method of crossover of different topologies, (2) protecting structural innovation using speciation, and (3) incrementally growing from minimal structure. We test this claim through a series of ablation studies that demonstrate that each component is necessary to the system as a whole and to each other. What results is significantly faster learning. NEAT is also an important contribution to GAs because it shows how it is possible for evolution to both optimize and complexify solutions simultaneously, offering the possibility of evolving increasingly complex solutions over generations, and strengthening the analogy with biological evolution.

Deep learning for low-dose CT

NASA Astrophysics Data System (ADS)

Chen, Hu; Zhang, Yi; Zhou, Jiliu; Wang, Ge

2017-09-01

Given the potential risk of X-ray radiation to the patient, low-dose CT has attracted a considerable interest in the medical imaging field. Currently, the main stream low-dose CT methods include vendor-specific sinogram domain filtration and iterative reconstruction algorithms, but they need to access raw data whose formats are not transparent to most users. Due to the difficulty of modeling the statistical characteristics in the image domain, the existing methods for directly processing reconstructed images cannot eliminate image noise very well while keeping structural details. Inspired by the idea of deep learning, here we combine the autoencoder, deconvolution network, and shortcut connections into the residual encoder-decoder convolutional neural network (RED-CNN) for low-dose CT imaging. After patch-based training, the proposed RED-CNN achieves a competitive performance relative to the-state-of-art methods. Especially, our method has been favorably evaluated in terms of noise suppression and structural preservation.

Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties

NASA Astrophysics Data System (ADS)

Xie, Tian; Grossman, Jeffrey C.

2018-04-01

The use of machine learning methods for accelerating the design of crystalline materials usually requires manually constructed feature vectors or complex transformation of atom coordinates to input the crystal structure, which either constrains the model to certain crystal types or makes it difficult to provide chemical insights. Here, we develop a crystal graph convolutional neural networks framework to directly learn material properties from the connection of atoms in the crystal, providing a universal and interpretable representation of crystalline materials. Our method provides a highly accurate prediction of density functional theory calculated properties for eight different properties of crystals with various structure types and compositions after being trained with 1 04 data points. Further, our framework is interpretable because one can extract the contributions from local chemical environments to global properties. Using an example of perovskites, we show how this information can be utilized to discover empirical rules for materials design.

Multiple brain networks underpinning word learning from fluent speech revealed by independent component analysis.

PubMed

López-Barroso, Diana; Ripollés, Pablo; Marco-Pallarés, Josep; Mohammadi, Bahram; Münte, Thomas F; Bachoud-Lévi, Anne-Catherine; Rodriguez-Fornells, Antoni; de Diego-Balaguer, Ruth

2015-04-15

Although neuroimaging studies using standard subtraction-based analysis from functional magnetic resonance imaging (fMRI) have suggested that frontal and temporal regions are involved in word learning from fluent speech, the possible contribution of different brain networks during this type of learning is still largely unknown. Indeed, univariate fMRI analyses cannot identify the full extent of distributed networks that are engaged by a complex task such as word learning. Here we used Independent Component Analysis (ICA) to characterize the different brain networks subserving word learning from an artificial language speech stream. Results were replicated in a second cohort of participants with a different linguistic background. Four spatially independent networks were associated with the task in both cohorts: (i) a dorsal Auditory-Premotor network; (ii) a dorsal Sensory-Motor network; (iii) a dorsal Fronto-Parietal network; and (iv) a ventral Fronto-Temporal network. The level of engagement of these networks varied through the learning period with only the dorsal Auditory-Premotor network being engaged across all blocks. In addition, the connectivity strength of this network in the second block of the learning phase correlated with the individual variability in word learning performance. These findings suggest that: (i) word learning relies on segregated connectivity patterns involving dorsal and ventral networks; and (ii) specifically, the dorsal auditory-premotor network connectivity strength is directly correlated with word learning performance. Copyright © 2015 Elsevier Inc. All rights reserved.

Distinct hippocampal versus frontoparietal-network contributions to retrieval and memory-guided exploration

PubMed Central

Bridge, Donna J.; Cohen, Neal J.; Voss, Joel L.

2017-01-01

Memory can profoundly influence new learning, presumably because memory optimizes exploration of to-be-learned material. Although hippocampus and frontoparietal networks have been implicated in memory-guided exploration, their specific and interactive roles have not been identified. We examined eye movements during fMRI scanning to identify neural correlates of the influences of memory retrieval on exploration and learning. Following retrieval of one object in a multi-object array, viewing was strategically directed away from the retrieved object toward non-retrieved objects, such that exploration was directed towards to-be-learned content. Retrieved objects later served as optimal reminder cues, indicating that exploration caused memory to become structured around the retrieved content. Hippocampal activity was associated with memory retrieval whereas frontoparietal activity varied with strategic viewing patterns deployed following retrieval, thus providing spatiotemporal dissociation of memory retrieval from memory-guided learning strategies. Time-lagged fMRI connectivity analyses indicated that hippocampal activity predicted frontoparietal activity to a greater extent for a condition in which retrieval guided exploration than for a passive control condition in which exploration was not influenced by retrieval. This demonstrates network-level interaction effects specific to influences of memory on strategic exploration. These findings show how memory guides behavior during learning and demonstrate distinct yet interactive hippocampal-frontoparietal roles in implementing strategic exploration behaviors that determine the fate of evolving memory representations. PMID:28471729

Distinct Hippocampal versus Frontoparietal Network Contributions to Retrieval and Memory-guided Exploration.

PubMed

Bridge, Donna J; Cohen, Neal J; Voss, Joel L

2017-08-01

Memory can profoundly influence new learning, presumably because memory optimizes exploration of to-be-learned material. Although hippocampus and frontoparietal networks have been implicated in memory-guided exploration, their specific and interactive roles have not been identified. We examined eye movements during fMRI scanning to identify neural correlates of the influences of memory retrieval on exploration and learning. After retrieval of one object in a multiobject array, viewing was strategically directed away from the retrieved object toward nonretrieved objects, such that exploration was directed toward to-be-learned content. Retrieved objects later served as optimal reminder cues, indicating that exploration caused memory to become structured around the retrieved content. Hippocampal activity was associated with memory retrieval, whereas frontoparietal activity varied with strategic viewing patterns deployed after retrieval, thus providing spatiotemporal dissociation of memory retrieval from memory-guided learning strategies. Time-lagged fMRI connectivity analyses indicated that hippocampal activity predicted frontoparietal activity to a greater extent for a condition in which retrieval guided exploration occurred than for a passive control condition in which exploration was not influenced by retrieval. This demonstrates network-level interaction effects specific to influences of memory on strategic exploration. These findings show how memory guides behavior during learning and demonstrate distinct yet interactive hippocampal-frontoparietal roles in implementing strategic exploration behaviors that determine the fate of evolving memory representations.

Precise Network Modeling of Systems Genetics Data Using the Bayesian Network Webserver.

PubMed

Ziebarth, Jesse D; Cui, Yan

2017-01-01

The Bayesian Network Webserver (BNW, http://compbio.uthsc.edu/BNW ) is an integrated platform for Bayesian network modeling of biological datasets. It provides a web-based network modeling environment that seamlessly integrates advanced algorithms for probabilistic causal modeling and reasoning with Bayesian networks. BNW is designed for precise modeling of relatively small networks that contain less than 20 nodes. The structure learning algorithms used by BNW guarantee the discovery of the best (most probable) network structure given the data. To facilitate network modeling across multiple biological levels, BNW provides a very flexible interface that allows users to assign network nodes into different tiers and define the relationships between and within the tiers. This function is particularly useful for modeling systems genetics datasets that often consist of multiscalar heterogeneous genotype-to-phenotype data. BNW enables users to, within seconds or minutes, go from having a simply formatted input file containing a dataset to using a network model to make predictions about the interactions between variables and the potential effects of experimental interventions. In this chapter, we will introduce the functions of BNW and show how to model systems genetics datasets with BNW.

Self-Learning Power Control in Wireless Sensor Networks.

PubMed

Chincoli, Michele; Liotta, Antonio

2018-01-27

Current trends in interconnecting myriad smart objects to monetize on Internet of Things applications have led to high-density communications in wireless sensor networks. This aggravates the already over-congested unlicensed radio bands, calling for new mechanisms to improve spectrum management and energy efficiency, such as transmission power control. Existing protocols are based on simplistic heuristics that often approach interference problems (i.e., packet loss, delay and energy waste) by increasing power, leading to detrimental results. The scope of this work is to investigate how machine learning may be used to bring wireless nodes to the lowest possible transmission power level and, in turn, to respect the quality requirements of the overall network. Lowering transmission power has benefits in terms of both energy consumption and interference. We propose a protocol of transmission power control through a reinforcement learning process that we have set in a multi-agent system. The agents are independent learners using the same exploration strategy and reward structure, leading to an overall cooperative network. The simulation results show that the system converges to an equilibrium where each node transmits at the minimum power while respecting high packet reception ratio constraints. Consequently, the system benefits from low energy consumption and packet delay.

Spatial Learning and Action Planning in a Prefrontal Cortical Network Model

PubMed Central

Martinet, Louis-Emmanuel; Sheynikhovich, Denis; Benchenane, Karim; Arleo, Angelo

2011-01-01

The interplay between hippocampus and prefrontal cortex (PFC) is fundamental to spatial cognition. Complementing hippocampal place coding, prefrontal representations provide more abstract and hierarchically organized memories suitable for decision making. We model a prefrontal network mediating distributed information processing for spatial learning and action planning. Specific connectivity and synaptic adaptation principles shape the recurrent dynamics of the network arranged in cortical minicolumns. We show how the PFC columnar organization is suitable for learning sparse topological-metrical representations from redundant hippocampal inputs. The recurrent nature of the network supports multilevel spatial processing, allowing structural features of the environment to be encoded. An activation diffusion mechanism spreads the neural activity through the column population leading to trajectory planning. The model provides a functional framework for interpreting the activity of PFC neurons recorded during navigation tasks. We illustrate the link from single unit activity to behavioral responses. The results suggest plausible neural mechanisms subserving the cognitive “insight” capability originally attributed to rodents by Tolman & Honzik. Our time course analysis of neural responses shows how the interaction between hippocampus and PFC can yield the encoding of manifold information pertinent to spatial planning, including prospective coding and distance-to-goal correlates. PMID:21625569

Self-Learning Power Control in Wireless Sensor Networks

PubMed Central

Liotta, Antonio

2018-01-01

Current trends in interconnecting myriad smart objects to monetize on Internet of Things applications have led to high-density communications in wireless sensor networks. This aggravates the already over-congested unlicensed radio bands, calling for new mechanisms to improve spectrum management and energy efficiency, such as transmission power control. Existing protocols are based on simplistic heuristics that often approach interference problems (i.e., packet loss, delay and energy waste) by increasing power, leading to detrimental results. The scope of this work is to investigate how machine learning may be used to bring wireless nodes to the lowest possible transmission power level and, in turn, to respect the quality requirements of the overall network. Lowering transmission power has benefits in terms of both energy consumption and interference. We propose a protocol of transmission power control through a reinforcement learning process that we have set in a multi-agent system. The agents are independent learners using the same exploration strategy and reward structure, leading to an overall cooperative network. The simulation results show that the system converges to an equilibrium where each node transmits at the minimum power while respecting high packet reception ratio constraints. Consequently, the system benefits from low energy consumption and packet delay. PMID:29382072

A new optimized GA-RBF neural network algorithm.

PubMed

Jia, Weikuan; Zhao, Dean; Shen, Tian; Su, Chunyang; Hu, Chanli; Zhao, Yuyan

2014-01-01

When confronting the complex problems, radial basis function (RBF) neural network has the advantages of adaptive and self-learning ability, but it is difficult to determine the number of hidden layer neurons, and the weights learning ability from hidden layer to the output layer is low; these deficiencies easily lead to decreasing learning ability and recognition precision. Aiming at this problem, we propose a new optimized RBF neural network algorithm based on genetic algorithm (GA-RBF algorithm), which uses genetic algorithm to optimize the weights and structure of RBF neural network; it chooses new ways of hybrid encoding and optimizing simultaneously. Using the binary encoding encodes the number of the hidden layer's neurons and using real encoding encodes the connection weights. Hidden layer neurons number and connection weights are optimized simultaneously in the new algorithm. However, the connection weights optimization is not complete; we need to use least mean square (LMS) algorithm for further leaning, and finally get a new algorithm model. Using two UCI standard data sets to test the new algorithm, the results show that the new algorithm improves the operating efficiency in dealing with complex problems and also improves the recognition precision, which proves that the new algorithm is valid.

Human intelligence and brain networks

PubMed Central

Colom, Roberto; Karama, Sherif; Jung, Rex E.; Haier, Richard J.

2010-01-01

Intelligence can be defined as a general mental ability for reasoning, problem solving, and learning. Because of its general nature, intelligence integrates cognitive functions such as perception, attention, memory, language, or planning. On the basis of this definition, intelligence can be reliably measured by standardized tests with obtained scores predicting several broad social outcomes such as educational achievement, job performance, health, and longevity. A detailed understanding of the brain mechanisms underlying this general mental ability could provide significant individual and societal benefits. Structural and functional neuroimaging studies have generally supported a frontoparietal network relevant for intelligence. This same network has also been found to underlie cognitive functions related to perception, short-term memory storage, and language. The distributed nature of this network and its involvement in a wide range of cognitive functions fits well with the integrative nature of intelligence. A new key phase of research is beginning to investigate how functional networks relate to structural networks, with emphasis on how distributed brain areas communicate with each other. PMID:21319494

Neural net target-tracking system using structured laser patterns

NASA Astrophysics Data System (ADS)

Cho, Jae-Wan; Lee, Yong-Bum; Lee, Nam-Ho; Park, Soon-Yong; Lee, Jongmin; Choi, Gapchu; Baek, Sunghyun; Park, Dong-Sun

1996-06-01

In this paper, we describe a robot endeffector tracking system using sensory information from recently-announced structured pattern laser diodes, which can generate images with several different types of structured pattern. The neural network approach is employed to recognize the robot endeffector covering the situation of three types of motion: translation, scaling and rotation. Features for the neural network to detect the position of the endeffector are extracted from the preprocessed images. Artificial neural networks are used to store models and to match with unknown input features recognizing the position of the robot endeffector. Since a minimal number of samples are used for different directions of the robot endeffector in the system, an artificial neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network with the generalization capability can be utilized for unknown input features. A feedforward neural network trained with the back propagation learning is used to detect the position of the robot endeffector. Another feedforward neural network module is used to estimate the motion from a sequence of images and to control movements of the robot endeffector. COmbining the tow neural networks for recognizing the robot endeffector and estimating the motion with the preprocessing stage, the whole system keeps tracking of the robot endeffector effectively.

Learning representation hierarchies by sharing visual features: a computational investigation of Persian character recognition with unsupervised deep learning.

PubMed

Sadeghi, Zahra; Testolin, Alberto

2017-08-01

In humans, efficient recognition of written symbols is thought to rely on a hierarchical processing system, where simple features are progressively combined into more abstract, high-level representations. Here, we present a computational model of Persian character recognition based on deep belief networks, where increasingly more complex visual features emerge in a completely unsupervised manner by fitting a hierarchical generative model to the sensory data. Crucially, high-level internal representations emerging from unsupervised deep learning can be easily read out by a linear classifier, achieving state-of-the-art recognition accuracy. Furthermore, we tested the hypothesis that handwritten digits and letters share many common visual features: A generative model that captures the statistical structure of the letters distribution should therefore also support the recognition of written digits. To this aim, deep networks trained on Persian letters were used to build high-level representations of Persian digits, which were indeed read out with high accuracy. Our simulations show that complex visual features, such as those mediating the identification of Persian symbols, can emerge from unsupervised learning in multilayered neural networks and can support knowledge transfer across related domains.

Cultured Cortical Neurons Can Perform Blind Source Separation According to the Free-Energy Principle

PubMed Central

Isomura, Takuya; Kotani, Kiyoshi; Jimbo, Yasuhiko

2015-01-01

Blind source separation is the computation underlying the cocktail party effect––a partygoer can distinguish a particular talker’s voice from the ambient noise. Early studies indicated that the brain might use blind source separation as a signal processing strategy for sensory perception and numerous mathematical models have been proposed; however, it remains unclear how the neural networks extract particular sources from a complex mixture of inputs. We discovered that neurons in cultures of dissociated rat cortical cells could learn to represent particular sources while filtering out other signals. Specifically, the distinct classes of neurons in the culture learned to respond to the distinct sources after repeating training stimulation. Moreover, the neural network structures changed to reduce free energy, as predicted by the free-energy principle, a candidate unified theory of learning and memory, and by Jaynes’ principle of maximum entropy. This implicit learning can only be explained by some form of Hebbian plasticity. These results are the first in vitro (as opposed to in silico) demonstration of neural networks performing blind source separation, and the first formal demonstration of neuronal self-organization under the free energy principle. PMID:26690814

The Impacts of Network Centrality and Self-Regulation on an E-Learning Environment with the Support of Social Network Awareness

ERIC Educational Resources Information Center

Lin, Jian-Wei; Huang, Hsieh-Hong; Chuang, Yuh-Shy

2015-01-01

An e-learning environment that supports social network awareness (SNA) is a highly effective means of increasing peer interaction and assisting student learning by raising awareness of social and learning contexts of peers. Network centrality profoundly impacts student learning in an SNA-related e-learning environment. Additionally,…

Generative model selection using a scalable and size-independent complex network classifier

NASA Astrophysics Data System (ADS)

Motallebi, Sadegh; Aliakbary, Sadegh; Habibi, Jafar

2013-12-01

Real networks exhibit nontrivial topological features, such as heavy-tailed degree distribution, high clustering, and small-worldness. Researchers have developed several generative models for synthesizing artificial networks that are structurally similar to real networks. An important research problem is to identify the generative model that best fits to a target network. In this paper, we investigate this problem and our goal is to select the model that is able to generate graphs similar to a given network instance. By the means of generating synthetic networks with seven outstanding generative models, we have utilized machine learning methods to develop a decision tree for model selection. Our proposed method, which is named "Generative Model Selection for Complex Networks," outperforms existing methods with respect to accuracy, scalability, and size-independence.

Improvement Science and NetworkED Improvement Communities: An Interview with Dr. Anthony Bryk. An ExpandED Schools Resource Guide

ERIC Educational Resources Information Center

ExpandED Schools, 2016

2016-01-01

During the summer, we interviewed Tony Bryk, Author of Learning to Improve: How America's Schools Can Get Better at Getting Better and head of the Carnegie Foundation for the Advancement of Teaching. His work was seminal in the creation of the Framework for Great Schools, which has spurred New York City schools to rethink the structures and…

The discovery of structural form

PubMed Central

Kemp, Charles; Tenenbaum, Joshua B.

2008-01-01

Algorithms for finding structure in data have become increasingly important both as tools for scientific data analysis and as models of human learning, yet they suffer from a critical limitation. Scientists discover qualitatively new forms of structure in observed data: For instance, Linnaeus recognized the hierarchical organization of biological species, and Mendeleev recognized the periodic structure of the chemical elements. Analogous insights play a pivotal role in cognitive development: Children discover that object category labels can be organized into hierarchies, friendship networks are organized into cliques, and comparative relations (e.g., “bigger than” or “better than”) respect a transitive order. Standard algorithms, however, can only learn structures of a single form that must be specified in advance: For instance, algorithms for hierarchical clustering create tree structures, whereas algorithms for dimensionality-reduction create low-dimensional spaces. Here, we present a computational model that learns structures of many different forms and that discovers which form is best for a given dataset. The model makes probabilistic inferences over a space of graph grammars representing trees, linear orders, multidimensional spaces, rings, dominance hierarchies, cliques, and other forms and successfully discovers the underlying structure of a variety of physical, biological, and social domains. Our approach brings structure learning methods closer to human abilities and may lead to a deeper computational understanding of cognitive development. PMID:18669663

Disrupted topological organization of structural networks revealed by probabilistic diffusion tractography in Tourette syndrome children.

PubMed

Wen, Hongwei; Liu, Yue; Rekik, Islem; Wang, Shengpei; Zhang, Jishui; Zhang, Yue; Peng, Yun; He, Huiguang

2017-08-01

Tourette syndrome (TS) is a childhood-onset neurobehavioral disorder. Although previous TS studies revealed structural abnormalities in distinct corticobasal ganglia circuits, the topological alterations of the whole-brain white matter (WM) structural networks remain poorly understood. Here, we used diffusion MRI probabilistic tractography and graph theoretical analysis to investigate the topological organization of WM networks in 44 drug-naive TS children and 41 age- and gender-matched healthy children. The WM networks were constructed by estimating inter-regional connectivity probability and the topological properties were characterized using graph theory. We found that both TS and control groups showed an efficient small-world organization in WM networks. However, compared to controls, TS children exhibited decreased global and local efficiency, increased shortest path length and small worldness, indicating a disrupted balance between local specialization and global integration in structural networks. Although both TS and control groups showed highly similar hub distributions, TS children exhibited significant decreased nodal efficiency, mainly distributed in the default mode, language, visual, and sensorimotor systems. Furthermore, two separate networks showing significantly decreased connectivity in TS group were identified using network-based statistical (NBS) analysis, primarily composed of the parieto-occipital cortex, precuneus, and paracentral lobule. Importantly, we combined support vector machine and multiple kernel learning frameworks to fuse multiple levels of network topological features for classification of individuals, achieving high accuracy of 86.47%. Together, our study revealed the disrupted topological organization of structural networks related to pathophysiology of TS, and the discriminative topological features for classification are potential quantitative neuroimaging biomarkers for clinical TS diagnosis. Hum Brain Mapp 38:3988-4008, 2017. © 2017 Wiley Periodicals, Inc. © 2017 Wiley Periodicals, Inc.

Cognitive control over learning: Creating, clustering and generalizing task-set structure

PubMed Central

Collins, Anne G.E.; Frank, Michael J.

2013-01-01

Executive functions and learning share common neural substrates essential for their expression, notably in prefrontal cortex and basal ganglia. Understanding how they interact requires studying how cognitive control facilitates learning, but also how learning provides the (potentially hidden) structure, such as abstract rules or task-sets, needed for cognitive control. We investigate this question from three complementary angles. First, we develop a new computational “C-TS” (context-task-set) model inspired by non-parametric Bayesian methods, specifying how the learner might infer hidden structure and decide whether to re-use that structure in new situations, or to create new structure. Second, we develop a neurobiologically explicit model to assess potential mechanisms of such interactive structured learning in multiple circuits linking frontal cortex and basal ganglia. We systematically explore the link betweens these levels of modeling across multiple task demands. We find that the network provides an approximate implementation of high level C-TS computations, where manipulations of specific neural mechanisms are well captured by variations in distinct C-TS parameters. Third, this synergism across models yields strong predictions about the nature of human optimal and suboptimal choices and response times during learning. In particular, the models suggest that participants spontaneously build task-set structure into a learning problem when not cued to do so, which predicts positive and negative transfer in subsequent generalization tests. We provide evidence for these predictions in two experiments and show that the C-TS model provides a good quantitative fit to human sequences of choices in this task. These findings implicate a strong tendency to interactively engage cognitive control and learning, resulting in structured abstract representations that afford generalization opportunities, and thus potentially long-term rather than short-term optimality. PMID:23356780

Teachers' Motives for Learning in Networks: Costs, Rewards and Community Interest

ERIC Educational Resources Information Center

van den Beemt, Antoine; Ketelaar, Evelien; Diepstraten, Isabelle; de Laat, Maarten

2018-01-01

Background: This paper discusses teachers' perspectives on learning networks and their motives for participating in these networks. Although it is widely held that teachers' learning may be developed through learning networks, not all teachers participate in such networks. Purpose: The theme of reciprocity, central to studies in the area of…

Up the ANTe: Understanding Entrepreneurial Leadership Learning through Actor-Network Theory

ERIC Educational Resources Information Center

Smith, Sue; Kempster, Steve; Barnes, Stewart

2017-01-01

This article explores the role of educators in supporting the development of entrepreneurial leadership learning by creating peer learning networks of owner-managers of small businesses. Using actor-network theory, the authors think through the process of constructing and maintaining a peer learning network (conceived of as an actor-network) and…

Neural network based load and price forecasting and confidence interval estimation in deregulated power markets

NASA Astrophysics Data System (ADS)

Zhang, Li

With the deregulation of the electric power market in New England, an independent system operator (ISO) has been separated from the New England Power Pool (NEPOOL). The ISO provides a regional spot market, with bids on various electricity-related products and services submitted by utilities and independent power producers. A utility can bid on the spot market and buy or sell electricity via bilateral transactions. Good estimation of market clearing prices (MCP) will help utilities and independent power producers determine bidding and transaction strategies with low risks, and this is crucial for utilities to compete in the deregulated environment. MCP prediction, however, is difficult since bidding strategies used by participants are complicated and MCP is a non-stationary process. The main objective of this research is to provide efficient short-term load and MCP forecasting and corresponding confidence interval estimation methodologies. In this research, the complexity of load and MCP with other factors is investigated, and neural networks are used to model the complex relationship between input and output. With improved learning algorithm and on-line update features for load forecasting, a neural network based load forecaster was developed, and has been in daily industry use since summer 1998 with good performance. MCP is volatile because of the complexity of market behaviors. In practice, neural network based MCP predictors usually have a cascaded structure, as several key input factors need to be estimated first. In this research, the uncertainties involved in a cascaded neural network structure for MCP prediction are analyzed, and prediction distribution under the Bayesian framework is developed. A fast algorithm to evaluate the confidence intervals by using the memoryless Quasi-Newton method is also developed. The traditional back-propagation algorithm for neural network learning needs to be improved since MCP is a non-stationary process. The extended Kalman filter (EKF) can be used as an integrated adaptive learning and confidence interval estimation algorithm for neural networks, with fast convergence and small confidence intervals. However, EKF learning is computationally expensive because it involves high dimensional matrix manipulations. A modified U-D factorization within the decoupled EKF (DEKF-UD) framework is developed in this research. The computational efficiency and numerical stability are significantly improved.

Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks

PubMed Central

Zhao, Rui; Yan, Ruqiang; Wang, Jinjiang; Mao, Kezhi

2017-01-01

In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression models directly. Therefore, previous work focuses on feature extraction/fusion methods requiring expensive human labor and high quality expert knowledge. With the development of deep learning methods in the last few years, which redefine representation learning from raw data, a deep neural network structure named Convolutional Bi-directional Long Short-Term Memory networks (CBLSTM) has been designed here to address raw sensory data. CBLSTM firstly uses CNN to extract local features that are robust and informative from the sequential input. Then, bi-directional LSTM is introduced to encode temporal information. Long Short-Term Memory networks (LSTMs) are able to capture long-term dependencies and model sequential data, and the bi-directional structure enables the capture of past and future contexts. Stacked, fully-connected layers and the linear regression layer are built on top of bi-directional LSTMs to predict the target value. Here, a real-life tool wear test is introduced, and our proposed CBLSTM is able to predict the actual tool wear based on raw sensory data. The experimental results have shown that our model is able to outperform several state-of-the-art baseline methods. PMID:28146106

Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks.

PubMed

Zhao, Rui; Yan, Ruqiang; Wang, Jinjiang; Mao, Kezhi

2017-01-30

In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression models directly. Therefore, previous work focuses on feature extraction/fusion methods requiring expensive human labor and high quality expert knowledge. With the development of deep learning methods in the last few years, which redefine representation learning from raw data, a deep neural network structure named Convolutional Bi-directional Long Short-Term Memory networks (CBLSTM) has been designed here to address raw sensory data. CBLSTM firstly uses CNN to extract local features that are robust and informative from the sequential input. Then, bi-directional LSTM is introduced to encode temporal information. Long Short-Term Memory networks(LSTMs) are able to capture long-term dependencies and model sequential data, and the bi-directional structure enables the capture of past and future contexts. Stacked, fully-connected layers and the linear regression layer are built on top of bi-directional LSTMs to predict the target value. Here, a real-life tool wear test is introduced, and our proposed CBLSTM is able to predict the actual tool wear based on raw sensory data. The experimental results have shown that our model is able to outperform several state-of-the-art baseline methods.

Associative memory through rigid origami

NASA Astrophysics Data System (ADS)

Murugan, Arvind; Brenner, Michael

2015-03-01

Mechanisms such as Miura Ori have proven useful in diverse contexts since they have only one degree of freedom that is easily controlled. We combine the theory of rigid origami and associative memory in frustrated neural networks to create structures that can ``learn'' multiple generic folding mechanisms and yet can be robustly controlled. We show that such rigid origami structures can ``recall'' a specific learned mechanism when induced by a physical impulse that only need resemble the desired mechanism (i.e. robust recall through association). Such associative memory in matter, seen before in self-assembly, arises due to a balance between local promiscuity (i.e., many local degrees of freedom) and global frustration which minimizes interference between different learned behaviors. Origami with associative memory can lead to a new class of deployable structures and kinetic architectures with multiple context-dependent behaviors.

Learning by stimulation avoidance: A principle to control spiking neural networks dynamics

PubMed Central

Sinapayen, Lana; Ikegami, Takashi

2017-01-01

Learning based on networks of real neurons, and learning based on biologically inspired models of neural networks, have yet to find general learning rules leading to widespread applications. In this paper, we argue for the existence of a principle allowing to steer the dynamics of a biologically inspired neural network. Using carefully timed external stimulation, the network can be driven towards a desired dynamical state. We term this principle “Learning by Stimulation Avoidance” (LSA). We demonstrate through simulation that the minimal sufficient conditions leading to LSA in artificial networks are also sufficient to reproduce learning results similar to those obtained in biological neurons by Shahaf and Marom, and in addition explains synaptic pruning. We examined the underlying mechanism by simulating a small network of 3 neurons, then scaled it up to a hundred neurons. We show that LSA has a higher explanatory power than existing hypotheses about the response of biological neural networks to external simulation, and can be used as a learning rule for an embodied application: learning of wall avoidance by a simulated robot. In other works, reinforcement learning with spiking networks can be obtained through global reward signals akin simulating the dopamine system; we believe that this is the first project demonstrating sensory-motor learning with random spiking networks through Hebbian learning relying on environmental conditions without a separate reward system. PMID:28158309

Learning by stimulation avoidance: A principle to control spiking neural networks dynamics.

PubMed

Sinapayen, Lana; Masumori, Atsushi; Ikegami, Takashi

2017-01-01

Learning based on networks of real neurons, and learning based on biologically inspired models of neural networks, have yet to find general learning rules leading to widespread applications. In this paper, we argue for the existence of a principle allowing to steer the dynamics of a biologically inspired neural network. Using carefully timed external stimulation, the network can be driven towards a desired dynamical state. We term this principle "Learning by Stimulation Avoidance" (LSA). We demonstrate through simulation that the minimal sufficient conditions leading to LSA in artificial networks are also sufficient to reproduce learning results similar to those obtained in biological neurons by Shahaf and Marom, and in addition explains synaptic pruning. We examined the underlying mechanism by simulating a small network of 3 neurons, then scaled it up to a hundred neurons. We show that LSA has a higher explanatory power than existing hypotheses about the response of biological neural networks to external simulation, and can be used as a learning rule for an embodied application: learning of wall avoidance by a simulated robot. In other works, reinforcement learning with spiking networks can be obtained through global reward signals akin simulating the dopamine system; we believe that this is the first project demonstrating sensory-motor learning with random spiking networks through Hebbian learning relying on environmental conditions without a separate reward system.

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

PubMed

Baldi, Pierre; Sadowski, Peter

2016-11-01

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

Multi-threshold white matter structural networks fusion for accurate diagnosis of Tourette syndrome children

NASA Astrophysics Data System (ADS)

Wen, Hongwei; Liu, Yue; Wang, Shengpei; Li, Zuoyong; Zhang, Jishui; Peng, Yun; He, Huiguang

2017-03-01

Tourette syndrome (TS) is a childhood-onset neurobehavioral disorder. To date, TS is still misdiagnosed due to its varied presentation and lacking of obvious clinical symptoms. Therefore, studies of objective imaging biomarkers are of great importance for early TS diagnosis. As tic generation has been linked to disturbed structural networks, and many efforts have been made recently to investigate brain functional or structural networks using machine learning methods, for the purpose of disease diagnosis. However, few studies were related to TS and some drawbacks still existed in them. Therefore, we propose a novel classification framework integrating a multi-threshold strategy and a network fusion scheme to address the preexisting drawbacks. Here we used diffusion MRI probabilistic tractography to construct the structural networks of 44 TS children and 48 healthy children. We ameliorated the similarity network fusion algorithm specially to fuse the multi-threshold structural networks. Graph theoretical analysis was then implemented, and nodal degree, nodal efficiency and nodal betweenness centrality were selected as features. Finally, support vector machine recursive feature extraction (SVM-RFE) algorithm was used for feature selection, and then optimal features are fed into SVM to automatically discriminate TS children from controls. We achieved a high accuracy of 89.13% evaluated by a nested cross validation, demonstrated the superior performance of our framework over other comparison methods. The involved discriminative regions for classification primarily located in the basal ganglia and frontal cortico-cortical networks, all highly related to the pathology of TS. Together, our study may provide potential neuroimaging biomarkers for early-stage TS diagnosis.

Architecture and biological applications of artificial neural networks: a tuberculosis perspective.

PubMed

Darsey, Jerry A; Griffin, William O; Joginipelli, Sravanthi; Melapu, Venkata Kiran

2015-01-01

Advancement of science and technology has prompted researchers to develop new intelligent systems that can solve a variety of problems such as pattern recognition, prediction, and optimization. The ability of the human brain to learn in a fashion that tolerates noise and error has attracted many researchers and provided the starting point for the development of artificial neural networks: the intelligent systems. Intelligent systems can acclimatize to the environment or data and can maximize the chances of success or improve the efficiency of a search. Due to massive parallelism with large numbers of interconnected processers and their ability to learn from the data, neural networks can solve a variety of challenging computational problems. Neural networks have the ability to derive meaning from complicated and imprecise data; they are used in detecting patterns, and trends that are too complex for humans, or other computer systems. Solutions to the toughest problems will not be found through one narrow specialization; therefore we need to combine interdisciplinary approaches to discover the solutions to a variety of problems. Many researchers in different disciplines such as medicine, bioinformatics, molecular biology, and pharmacology have successfully applied artificial neural networks. This chapter helps the reader in understanding the basics of artificial neural networks, their applications, and methodology; it also outlines the network learning process and architecture. We present a brief outline of the application of neural networks to medical diagnosis, drug discovery, gene identification, and protein structure prediction. We conclude with a summary of the results from our study on tuberculosis data using neural networks, in diagnosing active tuberculosis, and predicting chronic vs. infiltrative forms of tuberculosis.

Managing clinical failure: a complex adaptive system perspective.

PubMed

Matthews, Jean I; Thomas, Paul T

2007-01-01

The purpose of this article is to explore the knowledge capture process at the clinical level. It aims to identify factors that enable or constrain learning. The study applies complex adaptive system thinking principles to reconcile learning within the NHS. The paper uses a qualitative exploratory study with an interpretative methodological stance set in a secondary care NHS Trust. Semi-structured interviews were conducted with healthcare practitioners and managers involved at both strategic and operational risk management processes. A network structure is revealed that exhibits the communication and interdependent working practices to support knowledge capture and adaptive learning. Collaborative multidisciplinary communities, whose values reflect local priorities and promote open dialogue and reflection, are featured. The main concern is that the characteristics of bureaucracy; rational-legal authority, a rule-based culture, hierarchical lines of communication and a centralised governance focus, are hindering clinical learning by generating barriers. Locally emergent collaborative processes are a key strategic resource to capture knowledge, potentially fostering an environment that could learn from failure and translate lessons between contexts. What must be addressed is that reporting mechanisms serve not only the governance objectives, but also supplement learning by highlighting the potential lessons in context. Managers must nurture a collaborative infrastructure using networks in a co-evolutionary manner. Their role is not to direct and design processes but to influence, support and create effective knowledge capture. Although the study only investigated one site the findings and conclusions may well translate to other trusts--such as the risk of not enabling a learning environment at clinical levels.

Core reactivity estimation in space reactors using recurrent dynamic networks

NASA Technical Reports Server (NTRS)

Parlos, Alexander G.; Tsai, Wei K.

1991-01-01

A recurrent multilayer perceptron network topology is used in the identification of nonlinear dynamic systems from only the input/output measurements. The identification is performed in the discrete time domain, with the learning algorithm being a modified form of the back propagation (BP) rule. The recurrent dynamic network (RDN) developed is applied for the total core reactivity prediction of a spacecraft reactor from only neutronic power level measurements. Results indicate that the RDN can reproduce the nonlinear response of the reactor while keeping the number of nodes roughly equal to the relative order of the system. As accuracy requirements are increased, the number of required nodes also increases, however, the order of the RDN necessary to obtain such results is still in the same order of magnitude as the order of the mathematical model of the system. It is believed that use of the recurrent MLP structure with a variety of different learning algorithms may prove useful in utilizing artificial neural networks for recognition, classification, and prediction of dynamic systems.

Design of fuzzy systems using neurofuzzy networks.

PubMed

Figueiredo, M; Gomide, F

1999-01-01

This paper introduces a systematic approach for fuzzy system design based on a class of neural fuzzy networks built upon a general neuron model. The network structure is such that it encodes the knowledge learned in the form of if-then fuzzy rules and processes data following fuzzy reasoning principles. The technique provides a mechanism to obtain rules covering the whole input/output space as well as the membership functions (including their shapes) for each input variable. Such characteristics are of utmost importance in fuzzy systems design and application. In addition, after learning, it is very simple to extract fuzzy rules in the linguistic form. The network has universal approximation capability, a property very useful in, e.g., modeling and control applications. Here we focus on function approximation problems as a vehicle to illustrate its usefulness and to evaluate its performance. Comparisons with alternative approaches are also included. Both, nonnoisy and noisy data have been studied and considered in the computational experiments. The neural fuzzy network developed here and, consequently, the underlying approach, has shown to provide good results from the accuracy, complexity, and system design points of view.

Sensory grammars for sensor networks

PubMed Central

Aloimonos, Yiannis

2009-01-01

One of the major goals of Ambient Intelligence and Smart Environments is to interpret human activity sensed by a variety of sensors. In order to develop useful technologies and a subsequent industry around smart environments, we need to proceed in a principled manner. This paper suggests that human activity can be expressed in a language. This is a special language with its own phonemes, its own morphemes (words) and its own syntax and it can be learned using machine learning techniques applied to gargantuan amounts of data collected by sensor networks. Developing such languages will create bridges between Ambient Intelligence and other disciplines. It will also provide a hierarchical structure that can lead to a successful industry. PMID:21897837

Personalized E- learning System Based on Intelligent Agent

NASA Astrophysics Data System (ADS)

Duo, Sun; Ying, Zhou Cai

Lack of personalized learning is the key shortcoming of traditional e-Learning system. This paper analyzes the personal characters in e-Learning activity. In order to meet the personalized e-learning, a personalized e-learning system based on intelligent agent was proposed and realized in the paper. The structure of system, work process, the design of intelligent agent and the realization of intelligent agent were introduced in the paper. After the test use of the system by certain network school, we found that the system could improve the learner's initiative participation, which can provide learners with personalized knowledge service. Thus, we thought it might be a practical solution to realize self- learning and self-promotion in the lifelong education age.

Mixed-method Exploration of Social Network Links to Participation

PubMed Central

Kreider, Consuelo M.; Bendixen, Roxanna M.; Mann, William C.; Young, Mary Ellen; McCarty, Christopher

2015-01-01

The people who regularly interact with an adolescent form that youth's social network, which may impact participation. We investigated the relationship of social networks to participation using personal network analysis and individual interviews. The sample included 36 youth, age 11 – 16 years. Nineteen had diagnoses of learning disability, attention disorder, or high-functioning autism and 17 were typically developing. Network analysis yielded 10 network variables, of which 8 measured network composition and 2 measured network structure, with significant links to at least one measure of participation using the Children's Assessment of Participation and Enjoyment (CAPE). Interviews from youth in the clinical group yielded description of strategies used to negotiate social interactions, as well as processes and reasoning used to remain engaged within social networks. Findings contribute to understanding the ways social networks are linked to youth participation and suggest the potential of social network factors for predicting rehabilitation outcomes. PMID:26594737

Blending Formal and Informal Learning Networks for Online Learning

ERIC Educational Resources Information Center

Czerkawski, Betül C.

2016-01-01

With the emergence of social software and the advance of web-based technologies, online learning networks provide invaluable opportunities for learning, whether formal or informal. Unlike top-down, instructor-centered, and carefully planned formal learning settings, informal learning networks offer more bottom-up, student-centered participatory…

Image/video understanding systems based on network-symbolic models

NASA Astrophysics Data System (ADS)

Kuvich, Gary

2004-03-01

Vision is a part of a larger information system that converts visual information into knowledge structures. These structures drive vision process, resolve ambiguity and uncertainty via feedback projections, and provide image understanding that is an interpretation of visual information in terms of such knowledge models. Computer simulation models are built on the basis of graphs/networks. The ability of human brain to emulate similar graph/network models is found. Symbols, predicates and grammars naturally emerge in such networks, and logic is simply a way of restructuring such models. Brain analyzes an image as a graph-type relational structure created via multilevel hierarchical compression of visual information. Primary areas provide active fusion of image features on a spatial grid-like structure, where nodes are cortical columns. Spatial logic and topology naturally present in such structures. Mid-level vision processes like perceptual grouping, separation of figure from ground, are special kinds of network transformations. They convert primary image structure into the set of more abstract ones, which represent objects and visual scene, making them easy for analysis by higher-level knowledge structures. Higher-level vision phenomena are results of such analysis. Composition of network-symbolic models combines learning, classification, and analogy together with higher-level model-based reasoning into a single framework, and it works similar to frames and agents. Computational intelligence methods transform images into model-based knowledge representation. Based on such principles, an Image/Video Understanding system can convert images into the knowledge models, and resolve uncertainty and ambiguity. This allows creating intelligent computer vision systems for design and manufacturing.

Neural networks and logical reasoning systems: a translation table.

PubMed

Martins, J; Mendes, R V

2001-04-01

A correspondence is established between the basic elements of logic reasoning systems (knowledge bases, rules, inference and queries) and the structure and dynamical evolution laws of neural networks. The correspondence is pictured as a translation dictionary which might allow to go back and forth between symbolic and network formulations, a desirable step in learning-oriented systems and multicomputer networks. In the framework of Horn clause logics, it is found that atomic propositions with n arguments correspond to nodes with nth order synapses, rules to synaptic intensity constraints, forward chaining to synaptic dynamics and queries either to simple node activation or to a query tensor dynamics.

From Actions to Habits

PubMed Central

Yin, Henry H.

2008-01-01

Recent work on the role of overlapping cerebral networks in action selection and habit formation has important implications for alcohol addiction research. As reviewed below, (1) these networks, which all involve a group of deep-brain structures called the basal ganglia, are associated with distinct behavioral control processes, such as reward-guided Pavlovian conditional responses, goal-directed instrumental actions, and stimulus-driven habits; (2) different stages of action learning are associated with different networks, which have the ability to change (i.e., plasticity); and (3) exposure to alcohol and other addictive drugs can have profound effects on these networks by influencing the mechanisms underlying neural plasticity. PMID:23584008

Learning-based traffic signal control algorithms with neighborhood information sharing: An application for sustainable mobility

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

Aziz, H. M. Abdul; Zhu, Feng; Ukkusuri, Satish V.

Here, this research applies R-Markov Average Reward Technique based reinforcement learning (RL) algorithm, namely RMART, for vehicular signal control problem leveraging information sharing among signal controllers in connected vehicle environment. We implemented the algorithm in a network of 18 signalized intersections and compare the performance of RMART with fixed, adaptive, and variants of the RL schemes. Results show significant improvement in system performance for RMART algorithm with information sharing over both traditional fixed signal timing plans and real time adaptive control schemes. Additionally, the comparison with reinforcement learning algorithms including Q learning and SARSA indicate that RMART performs better atmore » higher congestion levels. Further, a multi-reward structure is proposed that dynamically adjusts the reward function with varying congestion states at the intersection. Finally, the results from test networks show significant reduction in emissions (CO, CO 2, NO x, VOC, PM 10) when RL algorithms are implemented compared to fixed signal timings and adaptive schemes.« less

Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network.

PubMed

Prasoon, Adhish; Petersen, Kersten; Igel, Christian; Lauze, François; Dam, Erik; Nielsen, Mads

2013-01-01

Segmentation of anatomical structures in medical images is often based on a voxel/pixel classification approach. Deep learning systems, such as convolutional neural networks (CNNs), can infer a hierarchical representation of images that fosters categorization. We propose a novel system for voxel classification integrating three 2D CNNs, which have a one-to-one association with the xy, yz and zx planes of 3D image, respectively. We applied our method to the segmentation of tibial cartilage in low field knee MRI scans and tested it on 114 unseen scans. Although our method uses only 2D features at a single scale, it performs better than a state-of-the-art method using 3D multi-scale features. In the latter approach, the features and the classifier have been carefully adapted to the problem at hand. That we were able to get better results by a deep learning architecture that autonomously learns the features from the images is the main insight of this study.

Statistical learning and the challenge of syntax: Beyond finite state automata

NASA Astrophysics Data System (ADS)

Elman, Jeff

2003-10-01

Over the past decade, it has been clear that even very young infants are sensitive to the statistical structure of language input presented to them, and use the distributional regularities to induce simple grammars. But can such statistically-driven learning also explain the acquisition of more complex grammar, particularly when the grammar includes recursion? Recent claims (e.g., Hauser, Chomsky, and Fitch, 2002) have suggested that the answer is no, and that at least recursion must be an innate capacity of the human language acquisition device. In this talk evidence will be presented that indicates that, in fact, statistically-driven learning (embodied in recurrent neural networks) can indeed enable the learning of complex grammatical patterns, including those that involve recursion. When the results are generalized to idealized machines, it is found that the networks are at least equivalent to Push Down Automata. Perhaps more interestingly, with limited and finite resources (such as are presumed to exist in the human brain) these systems demonstrate patterns of performance that resemble those in humans.

A new simple /spl infin/OH neuron model as a biologically plausible principal component analyzer.

PubMed

Jankovic, M V

2003-01-01

A new approach to unsupervised learning in a single-layer neural network is discussed. An algorithm for unsupervised learning based upon the Hebbian learning rule is presented. A simple neuron model is analyzed. A dynamic neural model, which contains both feed-forward and feedback connections between the input and the output, has been adopted. The, proposed learning algorithm could be more correctly named self-supervised rather than unsupervised. The solution proposed here is a modified Hebbian rule, in which the modification of the synaptic strength is proportional not to pre- and postsynaptic activity, but instead to the presynaptic and averaged value of postsynaptic activity. It is shown that the model neuron tends to extract the principal component from a stationary input vector sequence. Usually accepted additional decaying terms for the stabilization of the original Hebbian rule are avoided. Implementation of the basic Hebbian scheme would not lead to unrealistic growth of the synaptic strengths, thanks to the adopted network structure.

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.

How do general practice residents use social networking sites in asynchronous distance learning?

PubMed

Maisonneuve, Hubert; Chambe, Juliette; Lorenzo, Mathieu; Pelaccia, Thierry

2015-09-21

Blended learning environments - involving both face-to-face and remote interactions - make it easier to adapt learning programs to constraints such as residents' location and low teacher-student ratio. Social networking sites (SNS) such as Facebook®, while not originally intended to be used as learning environments, may be adapted for the distance-learning part of training programs. The purpose of our study was to explore the use of SNS for asynchronous distance learning in a blended learning environment as well as its influence on learners' face-to-face interactions. We conducted a qualitative study and carried out semi-structured interviews. We performed purposeful sampling for maximal variation to include eight general practice residents in 2(nd) and 3(rd) year training. A thematic analysis was performed. The social integration of SNS facilitates the engagement of users in their learning tasks. This may also stimulate students' interactions and group cohesion when members meet up in person. Most of the general practice residents who work in the blended learning environment we studied had a positive appraisal on their use of SNS. In particular, we report a positive impact on their engagement in learning and their participation in discussions during face-to-face instruction. Further studies are needed in order to evaluate the effectiveness of SNS in blended learning environments and the appropriation of SNS by teachers.

Delay selection by spike-timing-dependent plasticity in recurrent networks of spiking neurons receiving oscillatory inputs.

PubMed

Kerr, Robert R; Burkitt, Anthony N; Thomas, Doreen A; Gilson, Matthieu; Grayden, David B

2013-01-01

Learning rules, such as spike-timing-dependent plasticity (STDP), change the structure of networks of neurons based on the firing activity. A network level understanding of these mechanisms can help infer how the brain learns patterns and processes information. Previous studies have shown that STDP selectively potentiates feed-forward connections that have specific axonal delays, and that this underlies behavioral functions such as sound localization in the auditory brainstem of the barn owl. In this study, we investigate how STDP leads to the selective potentiation of recurrent connections with different axonal and dendritic delays during oscillatory activity. We develop analytical models of learning with additive STDP in recurrent networks driven by oscillatory inputs, and support the results using simulations with leaky integrate-and-fire neurons. Our results show selective potentiation of connections with specific axonal delays, which depended on the input frequency. In addition, we demonstrate how this can lead to a network becoming selective in the amplitude of its oscillatory response to this frequency. We extend this model of axonal delay selection within a single recurrent network in two ways. First, we show the selective potentiation of connections with a range of both axonal and dendritic delays. Second, we show axonal delay selection between multiple groups receiving out-of-phase, oscillatory inputs. We discuss the application of these models to the formation and activation of neuronal ensembles or cell assemblies in the cortex, and also to missing fundamental pitch perception in the auditory brainstem.

SKYNET: an efficient and robust neural network training tool for machine learning in astronomy

NASA Astrophysics Data System (ADS)

Graff, Philip; Feroz, Farhan; Hobson, Michael P.; Lasenby, Anthony

2014-06-01

We present the first public release of our generic neural network training algorithm, called SKYNET. This efficient and robust machine learning tool is able to train large and deep feed-forward neural networks, including autoencoders, for use in a wide range of supervised and unsupervised learning applications, such as regression, classification, density estimation, clustering and dimensionality reduction. SKYNET uses a `pre-training' method to obtain a set of network parameters that has empirically been shown to be close to a good solution, followed by further optimization using a regularized variant of Newton's method, where the level of regularization is determined and adjusted automatically; the latter uses second-order derivative information to improve convergence, but without the need to evaluate or store the full Hessian matrix, by using a fast approximate method to calculate Hessian-vector products. This combination of methods allows for the training of complicated networks that are difficult to optimize using standard backpropagation techniques. SKYNET employs convergence criteria that naturally prevent overfitting, and also includes a fast algorithm for estimating the accuracy of network outputs. The utility and flexibility of SKYNET are demonstrated by application to a number of toy problems, and to astronomical problems focusing on the recovery of structure from blurred and noisy images, the identification of gamma-ray bursters, and the compression and denoising of galaxy images. The SKYNET software, which is implemented in standard ANSI C and fully parallelized using MPI, is available at http://www.mrao.cam.ac.uk/software/skynet/.

Melanoma segmentation based on deep learning.

PubMed

Zhang, Xiaoqing

2017-12-01

Malignant melanoma is one of the most deadly forms of skin cancer, which is one of the world's fastest-growing cancers. Early diagnosis and treatment is critical. In this study, a neural network structure is utilized to construct a broad and accurate basis for the diagnosis of skin cancer, thereby reducing screening errors. The technique is able to improve the efficacy for identification of normally indistinguishable lesions (such as pigment spots) versus clinically unknown lesions, and to ultimately improve the diagnostic accuracy. In the field of medical imaging, in general, using neural networks for image segmentation is relatively rare. The existing traditional machine-learning neural network algorithms still cannot completely solve the problem of information loss, nor detect the precise division of the boundary area. We use an improved neural network framework, described herein, to achieve efficacious feature learning, and satisfactory segmentation of melanoma images. The architecture of the network includes multiple convolution layers, dropout layers, softmax layers, multiple filters, and activation functions. The number of data sets can be increased via rotation of the training set. A non-linear activation function (such as ReLU and ELU) is employed to alleviate the problem of gradient disappearance, and RMSprop/Adam are incorporated to optimize the loss algorithm. A batch normalization layer is added between the convolution layer and the activation layer to solve the problem of gradient disappearance and explosion. Experiments, described herein, show that our improved neural network architecture achieves higher accuracy for segmentation of melanoma images as compared with existing processes.

Delay Selection by Spike-Timing-Dependent Plasticity in Recurrent Networks of Spiking Neurons Receiving Oscillatory Inputs

PubMed Central

Kerr, Robert R.; Burkitt, Anthony N.; Thomas, Doreen A.; Gilson, Matthieu; Grayden, David B.

2013-01-01

Learning rules, such as spike-timing-dependent plasticity (STDP), change the structure of networks of neurons based on the firing activity. A network level understanding of these mechanisms can help infer how the brain learns patterns and processes information. Previous studies have shown that STDP selectively potentiates feed-forward connections that have specific axonal delays, and that this underlies behavioral functions such as sound localization in the auditory brainstem of the barn owl. In this study, we investigate how STDP leads to the selective potentiation of recurrent connections with different axonal and dendritic delays during oscillatory activity. We develop analytical models of learning with additive STDP in recurrent networks driven by oscillatory inputs, and support the results using simulations with leaky integrate-and-fire neurons. Our results show selective potentiation of connections with specific axonal delays, which depended on the input frequency. In addition, we demonstrate how this can lead to a network becoming selective in the amplitude of its oscillatory response to this frequency. We extend this model of axonal delay selection within a single recurrent network in two ways. First, we show the selective potentiation of connections with a range of both axonal and dendritic delays. Second, we show axonal delay selection between multiple groups receiving out-of-phase, oscillatory inputs. We discuss the application of these models to the formation and activation of neuronal ensembles or cell assemblies in the cortex, and also to missing fundamental pitch perception in the auditory brainstem. PMID:23408878

Flexible Fusion Structure-Based Performance Optimization Learning for Multisensor Target Tracking

PubMed Central

Ge, Quanbo; Wei, Zhongliang; Cheng, Tianfa; Chen, Shaodong; Wang, Xiangfeng

2017-01-01

Compared with the fixed fusion structure, the flexible fusion structure with mixed fusion methods has better adjustment performance for the complex air task network systems, and it can effectively help the system to achieve the goal under the given constraints. Because of the time-varying situation of the task network system induced by moving nodes and non-cooperative target, and limitations such as communication bandwidth and measurement distance, it is necessary to dynamically adjust the system fusion structure including sensors and fusion methods in a given adjustment period. Aiming at this, this paper studies the design of a flexible fusion algorithm by using an optimization learning technology. The purpose is to dynamically determine the sensors’ numbers and the associated sensors to take part in the centralized and distributed fusion processes, respectively, herein termed sensor subsets selection. Firstly, two system performance indexes are introduced. Especially, the survivability index is presented and defined. Secondly, based on the two indexes and considering other conditions such as communication bandwidth and measurement distance, optimization models for both single target tracking and multi-target tracking are established. Correspondingly, solution steps are given for the two optimization models in detail. Simulation examples are demonstrated to validate the proposed algorithms. PMID:28481243

Preliminary Work for Examining the Scalability of Reinforcement Learning

NASA Technical Reports Server (NTRS)

Clouse, Jeff

1998-01-01

Researchers began studying automated agents that learn to perform multiple-step tasks early in the history of artificial intelligence (Samuel, 1963; Samuel, 1967; Waterman, 1970; Fikes, Hart & Nilsonn, 1972). Multiple-step tasks are tasks that can only be solved via a sequence of decisions, such as control problems, robotics problems, classic problem-solving, and game-playing. The objective of agents attempting to learn such tasks is to use the resources they have available in order to become more proficient at the tasks. In particular, each agent attempts to develop a good policy, a mapping from states to actions, that allows it to select actions that optimize a measure of its performance on the task; for example, reducing the number of steps necessary to complete the task successfully. Our study focuses on reinforcement learning, a set of learning techniques where the learner performs trial-and-error experiments in the task and adapts its policy based on the outcome of those experiments. Much of the work in reinforcement learning has focused on a particular, simple representation, where every problem state is represented explicitly in a table, and associated with each state are the actions that can be chosen in that state. A major advantage of this table lookup representation is that one can prove that certain reinforcement learning techniques will develop an optimal policy for the current task. The drawback is that the representation limits the application of reinforcement learning to multiple-step tasks with relatively small state-spaces. There has been a little theoretical work that proves that convergence to optimal solutions can be obtained when using generalization structures, but the structures are quite simple. The theory says little about complex structures, such as multi-layer, feedforward artificial neural networks (Rumelhart & McClelland, 1986), but empirical results indicate that the use of reinforcement learning with such structures is promising. These empirical results make no theoretical claims, nor compare the policies produced to optimal policies. A goal of our work is to be able to make the comparison between an optimal policy and one stored in an artificial neural network. A difficulty of performing such a study is finding a multiple-step task that is small enough that one can find an optimal policy using table lookup, yet large enough that, for practical purposes, an artificial neural network is really required. We have identified a limited form of the game OTHELLO as satisfying these requirements. The work we report here is in the very preliminary stages of research, but this paper provides background for the problem being studied and a description of our initial approach to examining the problem. In the remainder of this paper, we first describe reinforcement learning in more detail. Next, we present the game OTHELLO. Finally we argue that a restricted form of the game meets the requirements of our study, and describe our preliminary approach to finding an optimal solution to the problem.

Learning to generate combinatorial action sequences utilizing the initial sensitivity of deterministic dynamical systems.

PubMed

Nishimoto, Ryu; Tani, Jun

2004-09-01

This study shows how sensory-action sequences of imitating finite state machines (FSMs) can be learned by utilizing the deterministic dynamics of recurrent neural networks (RNNs). Our experiments indicated that each possible combinatorial sequence can be recalled by specifying its respective initial state value and also that fractal structures appear in this initial state mapping after the learning converges. We also observed that the sequences of mimicking FSMs are encoded utilizing the transient regions rather than the invariant sets of the evolved dynamical systems of the RNNs.

Deep learning for biomarker regression: application to osteoporosis and emphysema on chest CT scans

NASA Astrophysics Data System (ADS)

González, Germán.; Washko, George R.; San José Estépar, Raúl

2018-03-01

Introduction: Biomarker computation using deep-learning often relies on a two-step process, where the deep learning algorithm segments the region of interest and then the biomarker is measured. We propose an alternative paradigm, where the biomarker is estimated directly using a regression network. We showcase this image-tobiomarker paradigm using two biomarkers: the estimation of bone mineral density (BMD) and the estimation of lung percentage of emphysema from CT scans. Materials and methods: We use a large database of 9,925 CT scans to train, validate and test the network for which reference standard BMD and percentage emphysema have been already computed. First, the 3D dataset is reduced to a set of canonical 2D slices where the organ of interest is visible (either spine for BMD or lungs for emphysema). This data reduction is performed using an automatic object detector. Second, The regression neural network is composed of three convolutional layers, followed by a fully connected and an output layer. The network is optimized using a momentum optimizer with an exponential decay rate, using the root mean squared error as cost function. Results: The Pearson correlation coefficients obtained against the reference standards are r = 0.940 (p < 0.00001) and r = 0.976 (p < 0.00001) for BMD and percentage emphysema respectively. Conclusions: The deep-learning regression architecture can learn biomarkers from images directly, without indicating the structures of interest. This approach simplifies the development of biomarker extraction algorithms. The proposed data reduction based on object detectors conveys enough information to compute the biomarkers of interest.

A prediction model for cognitive performance in health ageing using diffusion tensor imaging with graph theory.

PubMed

Yun, Ruijuan; Lin, Chung-Chih; Wu, Shuicai; Huang, Chu-Chung; Lin, Ching-Po; Chao, Yi-Ping

2013-01-01

In this study, we employed diffusion tensor imaging (DTI) to construct brain structural network and then derive the connection matrices from 96 healthy elderly subjects. The correlation analysis between these topological properties of network based on graph theory and the Cognitive Abilities Screening Instrument (CASI) index were processed to extract the significant network characteristics. These characteristics were then integrated to estimate the models by various machine-learning algorithms to predict user's cognitive performance. From the results, linear regression model and Gaussian processes model showed presented better abilities with lower mean absolute errors of 5.8120 and 6.25 to predict the cognitive performance respectively. Moreover, these extracted topological properties of brain structural network derived from DTI also could be regarded as the bio-signatures for further evaluation of brain degeneration in healthy aged and early diagnosis of mild cognitive impairment (MCI).

Modelling students' knowledge organisation: Genealogical conceptual networks

NASA Astrophysics Data System (ADS)

Koponen, Ismo T.; Nousiainen, Maija

2018-04-01

Learning scientific knowledge is largely based on understanding what are its key concepts and how they are related. The relational structure of concepts also affects how concepts are introduced in teaching scientific knowledge. We model here how students organise their knowledge when they represent their understanding of how physics concepts are related. The model is based on assumptions that students use simple basic linking-motifs in introducing new concepts and mostly relate them to concepts that were introduced a few steps earlier, i.e. following a genealogical ordering. The resulting genealogical networks have relatively high local clustering coefficients of nodes but otherwise resemble networks obtained with an identical degree distribution of nodes but with random linking between them (i.e. the configuration-model). However, a few key nodes having a special structural role emerge and these nodes have a higher than average communicability betweenness centralities. These features agree with the empirically found properties of students' concept networks.

Constructing of Research-Oriented Learning Mode Based on Network Environment

ERIC Educational Resources Information Center

Wang, Ying; Li, Bing; Xie, Bai-zhi

2007-01-01

Research-oriented learning mode that based on network is significant to cultivate comprehensive-developing innovative person with network teaching in education for all-around development. This paper establishes a research-oriented learning mode by aiming at the problems existing in research-oriented learning based on network environment, and…

Implicit structured sequence learning: an fMRI study of the structural mere-exposure effect

PubMed Central

Folia, Vasiliki; Petersson, Karl Magnus

2014-01-01

In this event-related fMRI study we investigated the effect of 5 days of implicit acquisition on preference classification by means of an artificial grammar learning (AGL) paradigm based on the structural mere-exposure effect and preference classification using a simple right-linear unification grammar. This allowed us to investigate implicit AGL in a proper learning design by including baseline measurements prior to grammar exposure. After 5 days of implicit acquisition, the fMRI results showed activations in a network of brain regions including the inferior frontal (centered on BA 44/45) and the medial prefrontal regions (centered on BA 8/32). Importantly, and central to this study, the inclusion of a naive preference fMRI baseline measurement allowed us to conclude that these fMRI findings were the intrinsic outcomes of the learning process itself and not a reflection of a preexisting functionality recruited during classification, independent of acquisition. Support for the implicit nature of the knowledge utilized during preference classification on day 5 come from the fact that the basal ganglia, associated with implicit procedural learning, were activated during classification, while the medial temporal lobe system, associated with explicit declarative memory, was consistently deactivated. Thus, preference classification in combination with structural mere-exposure can be used to investigate structural sequence processing (syntax) in unsupervised AGL paradigms with proper learning designs. PMID:24550865

Implicit structured sequence learning: an fMRI study of the structural mere-exposure effect.

PubMed

Folia, Vasiliki; Petersson, Karl Magnus

2014-01-01

In this event-related fMRI study we investigated the effect of 5 days of implicit acquisition on preference classification by means of an artificial grammar learning (AGL) paradigm based on the structural mere-exposure effect and preference classification using a simple right-linear unification grammar. This allowed us to investigate implicit AGL in a proper learning design by including baseline measurements prior to grammar exposure. After 5 days of implicit acquisition, the fMRI results showed activations in a network of brain regions including the inferior frontal (centered on BA 44/45) and the medial prefrontal regions (centered on BA 8/32). Importantly, and central to this study, the inclusion of a naive preference fMRI baseline measurement allowed us to conclude that these fMRI findings were the intrinsic outcomes of the learning process itself and not a reflection of a preexisting functionality recruited during classification, independent of acquisition. Support for the implicit nature of the knowledge utilized during preference classification on day 5 come from the fact that the basal ganglia, associated with implicit procedural learning, were activated during classification, while the medial temporal lobe system, associated with explicit declarative memory, was consistently deactivated. Thus, preference classification in combination with structural mere-exposure can be used to investigate structural sequence processing (syntax) in unsupervised AGL paradigms with proper learning designs.

Maximum entropy methods for extracting the learned features of deep neural networks.

PubMed

Finnegan, Alex; Song, Jun S

2017-10-01

New architectures of multilayer artificial neural networks and new methods for training them are rapidly revolutionizing the application of machine learning in diverse fields, including business, social science, physical sciences, and biology. Interpreting deep neural networks, however, currently remains elusive, and a critical challenge lies in understanding which meaningful features a network is actually learning. We present a general method for interpreting deep neural networks and extracting network-learned features from input data. We describe our algorithm in the context of biological sequence analysis. Our approach, based on ideas from statistical physics, samples from the maximum entropy distribution over possible sequences, anchored at an input sequence and subject to constraints implied by the empirical function learned by a network. Using our framework, we demonstrate that local transcription factor binding motifs can be identified from a network trained on ChIP-seq data and that nucleosome positioning signals are indeed learned by a network trained on chemical cleavage nucleosome maps. Imposing a further constraint on the maximum entropy distribution also allows us to probe whether a network is learning global sequence features, such as the high GC content in nucleosome-rich regions. This work thus provides valuable mathematical tools for interpreting and extracting learned features from feed-forward neural networks.

A computational framework for the detection of subcortical brain dysmaturation in neonatal MRI using 3D Convolutional Neural Networks.

PubMed

Ceschin, Rafael; Zahner, Alexandria; Reynolds, William; Gaesser, Jenna; Zuccoli, Giulio; Lo, Cecilia W; Gopalakrishnan, Vanathi; Panigrahy, Ashok

2018-05-21

Deep neural networks are increasingly being used in both supervised learning for classification tasks and unsupervised learning to derive complex patterns from the input data. However, the successful implementation of deep neural networks using neuroimaging datasets requires adequate sample size for training and well-defined signal intensity based structural differentiation. There is a lack of effective automated diagnostic tools for the reliable detection of brain dysmaturation in the neonatal period, related to small sample size and complex undifferentiated brain structures, despite both translational research and clinical importance. Volumetric information alone is insufficient for diagnosis. In this study, we developed a computational framework for the automated classification of brain dysmaturation from neonatal MRI, by combining a specific deep neural network implementation with neonatal structural brain segmentation as a method for both clinical pattern recognition and data-driven inference into the underlying structural morphology. We implemented three-dimensional convolution neural networks (3D-CNNs) to specifically classify dysplastic cerebelli, a subset of surface-based subcortical brain dysmaturation, in term infants born with congenital heart disease. We obtained a 0.985 ± 0. 0241-classification accuracy of subtle cerebellar dysplasia in CHD using 10-fold cross-validation. Furthermore, the hidden layer activations and class activation maps depicted regional vulnerability of the superior surface of the cerebellum, (composed of mostly the posterior lobe and the midline vermis), in regards to differentiating the dysplastic process from normal tissue. The posterior lobe and the midline vermis provide regional differentiation that is relevant to not only to the clinical diagnosis of cerebellar dysplasia, but also genetic mechanisms and neurodevelopmental outcome correlates. These findings not only contribute to the detection and classification of a subset of neonatal brain dysmaturation, but also provide insight to the pathogenesis of cerebellar dysplasia in CHD. In addition, this is one of the first examples of the application of deep learning to a neuroimaging dataset, in which the hidden layer activation revealed diagnostically and biologically relevant features about the clinical pathogenesis. The code developed for this project is open source, published under the BSD License, and designed to be generalizable to applications both within and beyond neonatal brain imaging. Copyright © 2018 Elsevier Inc. All rights reserved.

Security barriers with automated reconnaissance

DOEpatents

McLaughlin, James O; Baird, Adam D; Tullis, Barclay J; Nolte, Roger Allen

2015-04-07

An intrusion delaying barrier includes primary and secondary physical structures and can be instrumented with multiple sensors incorporated into an electronic monitoring and alarm system. Such an instrumented intrusion delaying barrier may be used as a perimeter intrusion defense and assessment system (PIDAS). Problems with not providing effective delay to breaches by intentional intruders and/or terrorists who would otherwise evade detection are solved by attaching the secondary structures to the primary structure, and attaching at least some of the sensors to the secondary structures. By having multiple sensors of various types physically interconnected serves to enable sensors on different parts of the overall structure to respond to common disturbances and thereby provide effective corroboration that a disturbance is not merely a nuisance or false alarm. Use of a machine learning network such as a neural network exploits such corroboration.

Generative model selection using a scalable and size-independent complex network classifier

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

Motallebi, Sadegh, E-mail: motallebi@ce.sharif.edu; Aliakbary, Sadegh, E-mail: aliakbary@ce.sharif.edu; Habibi, Jafar, E-mail: jhabibi@sharif.edu

2013-12-15

Real networks exhibit nontrivial topological features, such as heavy-tailed degree distribution, high clustering, and small-worldness. Researchers have developed several generative models for synthesizing artificial networks that are structurally similar to real networks. An important research problem is to identify the generative model that best fits to a target network. In this paper, we investigate this problem and our goal is to select the model that is able to generate graphs similar to a given network instance. By the means of generating synthetic networks with seven outstanding generative models, we have utilized machine learning methods to develop a decision tree formore » model selection. Our proposed method, which is named “Generative Model Selection for Complex Networks,” outperforms existing methods with respect to accuracy, scalability, and size-independence.« less

Hippocampal brain-network coordination during volitional exploratory behavior enhances learning

PubMed Central

Voss, Joel L.; Gonsalves, Brian D.; Federmeier, Kara D.; Tranel, Daniel; Cohen, Neal J.

2010-01-01

Exploratory behaviors during learning determine what is studied and when, helping to optimize subsequent memory performance. We manipulated how much control subjects had over the position of a moving window through which they studied objects and their locations, in order to elucidate the cognitive and neural determinants of exploratory behaviors. Our behavioral, neuropsychological, and neuroimaging data indicate volitional control benefits memory performance, and is linked to a brain network centered on the hippocampus. Increases in correlated activity between the hippocampus and other areas were associated with specific aspects of memory, suggesting that volitional control optimizes interactions among specialized neural systems via the hippocampus. Memory is therefore an active process intrinsically linked to behavior. Furthermore, brain structures typically seen as passive participants in memory encoding (e.g., the hippocampus) are actually part of an active network that controls behavior dynamically as it unfolds. PMID:21102449

Hippocampal brain-network coordination during volitional exploratory behavior enhances learning.

PubMed

Voss, Joel L; Gonsalves, Brian D; Federmeier, Kara D; Tranel, Daniel; Cohen, Neal J

2011-01-01

Exploratory behaviors during learning determine what is studied and when, helping to optimize subsequent memory performance. To elucidate the cognitive and neural determinants of exploratory behaviors, we manipulated the control that human subjects had over the position of a moving window through which they studied objects and their locations. Our behavioral, neuropsychological and neuroimaging data indicate that volitional control benefits memory performance and is linked to a brain network that is centered on the hippocampus. Increases in correlated activity between the hippocampus and other areas were associated with specific aspects of memory, which suggests that volitional control optimizes interactions among specialized neural systems through the hippocampus. Memory is therefore an active process that is intrinsically linked to behavior. Furthermore, brain structures that are typically seen as passive participants in memory encoding (for example, the hippocampus) are actually part of an active network that controls behavior dynamically as it unfolds.

Relabeling exchange method (REM) for learning in neural networks

NASA Astrophysics Data System (ADS)

Wu, Wen; Mammone, Richard J.

1994-02-01

The supervised training of neural networks require the use of output labels which are usually arbitrarily assigned. In this paper it is shown that there is a significant difference in the rms error of learning when `optimal' label assignment schemes are used. We have investigated two efficient random search algorithms to solve the relabeling problem: the simulated annealing and the genetic algorithm. However, we found them to be computationally expensive. Therefore we shall introduce a new heuristic algorithm called the Relabeling Exchange Method (REM) which is computationally more attractive and produces optimal performance. REM has been used to organize the optimal structure for multi-layered perceptrons and neural tree networks. The method is a general one and can be implemented as a modification to standard training algorithms. The motivation of the new relabeling strategy is based on the present interpretation of dyslexia as an encoding problem.

Predicting the random drift of MEMS gyroscope based on K-means clustering and OLS RBF Neural Network

NASA Astrophysics Data System (ADS)

Wang, Zhen-yu; Zhang, Li-jie

2017-10-01

Measure error of the sensor can be effectively compensated with prediction. Aiming at large random drift error of MEMS(Micro Electro Mechanical System))gyroscope, an improved learning algorithm of Radial Basis Function(RBF) Neural Network(NN) based on K-means clustering and Orthogonal Least-Squares (OLS) is proposed in this paper. The algorithm selects the typical samples as the initial cluster centers of RBF NN firstly, candidates centers with K-means algorithm secondly, and optimizes the candidate centers with OLS algorithm thirdly, which makes the network structure simpler and makes the prediction performance better. Experimental results show that the proposed K-means clustering OLS learning algorithm can predict the random drift of MEMS gyroscope effectively, the prediction error of which is 9.8019e-007°/s and the prediction time of which is 2.4169e-006s

Social Trust Prediction Using Heterogeneous Networks

PubMed Central

HUANG, JIN; NIE, FEIPING; HUANG, HENG; TU, YI-CHENG; LEI, YU

2014-01-01

Along with increasing popularity of social websites, online users rely more on the trustworthiness information to make decisions, extract and filter information, and tag and build connections with other users. However, such social network data often suffer from severe data sparsity and are not able to provide users with enough information. Therefore, trust prediction has emerged as an important topic in social network research. Traditional approaches are primarily based on exploring trust graph topology itself. However, research in sociology and our life experience suggest that people who are in the same social circle often exhibit similar behaviors and tastes. To take advantage of the ancillary information for trust prediction, the challenge then becomes what to transfer and how to transfer. In this article, we address this problem by aggregating heterogeneous social networks and propose a novel joint social networks mining (JSNM) method. Our new joint learning model explores the user-group-level similarity between correlated graphs and simultaneously learns the individual graph structure; therefore, the shared structures and patterns from multiple social networks can be utilized to enhance the prediction tasks. As a result, we not only improve the trust prediction in the target graph but also facilitate other information retrieval tasks in the auxiliary graphs. To optimize the proposed objective function, we use the alternative technique to break down the objective function into several manageable subproblems. We further introduce the auxiliary function to solve the optimization problems with rigorously proved convergence. The extensive experiments have been conducted on both synthetic and real- world data. All empirical results demonstrate the effectiveness of our method. PMID:24729776

Social Trust Prediction Using Heterogeneous Networks.

PubMed

Huang, Jin; Nie, Feiping; Huang, Heng; Tu, Yi-Cheng; Lei, Yu

2013-11-01

Along with increasing popularity of social websites, online users rely more on the trustworthiness information to make decisions, extract and filter information, and tag and build connections with other users. However, such social network data often suffer from severe data sparsity and are not able to provide users with enough information. Therefore, trust prediction has emerged as an important topic in social network research. Traditional approaches are primarily based on exploring trust graph topology itself. However, research in sociology and our life experience suggest that people who are in the same social circle often exhibit similar behaviors and tastes. To take advantage of the ancillary information for trust prediction, the challenge then becomes what to transfer and how to transfer. In this article, we address this problem by aggregating heterogeneous social networks and propose a novel joint social networks mining (JSNM) method. Our new joint learning model explores the user-group-level similarity between correlated graphs and simultaneously learns the individual graph structure; therefore, the shared structures and patterns from multiple social networks can be utilized to enhance the prediction tasks. As a result, we not only improve the trust prediction in the target graph but also facilitate other information retrieval tasks in the auxiliary graphs. To optimize the proposed objective function, we use the alternative technique to break down the objective function into several manageable subproblems. We further introduce the auxiliary function to solve the optimization problems with rigorously proved convergence. The extensive experiments have been conducted on both synthetic and real- world data. All empirical results demonstrate the effectiveness of our method.

Accelerating Learning By Neural Networks

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad; Barhen, Jacob

1992-01-01

Electronic neural networks made to learn faster by use of terminal teacher forcing. Method of supervised learning involves addition of teacher forcing functions to excitations fed as inputs to output neurons. Initially, teacher forcing functions are strong enough to force outputs to desired values; subsequently, these functions decay with time. When learning successfully completed, terminal teacher forcing vanishes, and dynamics or neural network become equivalent to those of conventional neural network. Simulated neural network with terminal teacher forcing learned to produce close approximation of circular trajectory in 400 iterations.

Effects of low intensity noise from aircraft or from neighbourhood on cognitive learning and electrophysiological stress responses.

PubMed

Trimmel, Michael; Atzlsdorfer, Jürgen; Tupy, Nina; Trimmel, Karin

2012-11-01

The effects of low intensity noise on cognitive learning and autonomous physiological processes are of high practical relevance but are rarely addressed in empirical investigations. This study investigated the impact of neighbourhood noise (of 45 dB[A], n=20) and of noise coming from passing aircraft (of 48 dB[A] peak amplitude presented once per minute; n=19) during computer based learning of different texts (with three types of text structure, i.e. linear text, hierarchic hypertext, and network hypertext) in relation to a control group (35 dB[A], n=20). Using a between subjects design, reproduction scores, heart rate, and spontaneous skin conductance fluctuations were compared. Results showed impairments of reproduction in both noise conditions. Additionally, whereas in the control group and the neighbourhood noise group scores were better for network hypertext structure than for hierarchic hypertext, no effect of text structure on reproduction appeared in the aircraft noise group. Compared to the control group, for most of the learning period the number of spontaneous skin conductance fluctuations was higher for the aircraft noise group. For the neighbourhood noise group, fluctuations were higher during pre- and post task periods when noise stimulation was still present. Additionally, during the last 5 min of the 15 min learning period, an increased heart rate was found in the aircraft noise group. Data indicate remarkable cognitive and physiological effects of low intensity background noise. Some aspects of reproduction were impaired in the two noise groups. Cognitive learning, as indicated by reproduction scores, was changed structurally in the aircraft noise group and was accompanied by higher sympathetic activity. An additional cardiovascular load appeared for aircraft noise when combined with time pressure as indicated by heart rate for the announced last 5 min of the learning period during aircraft noise with a peak SPL of even 48 dB(A). Attentional mechanisms (attentional control) like being threatened by passing aircraft approaching the airport, higher demands of selective filtering, and difficulties in changing cognitive strategies during noise are discussed as underlying mechanisms. Copyright © 2011 Elsevier GmbH. All rights reserved.

Network congestion control algorithm based on Actor-Critic reinforcement learning model

NASA Astrophysics Data System (ADS)

Xu, Tao; Gong, Lina; Zhang, Wei; Li, Xuhong; Wang, Xia; Pan, Wenwen

2018-04-01

Aiming at the network congestion control problem, a congestion control algorithm based on Actor-Critic reinforcement learning model is designed. Through the genetic algorithm in the congestion control strategy, the network congestion problems can be better found and prevented. According to Actor-Critic reinforcement learning, the simulation experiment of network congestion control algorithm is designed. The simulation experiments verify that the AQM controller can predict the dynamic characteristics of the network system. Moreover, the learning strategy is adopted to optimize the network performance, and the dropping probability of packets is adaptively adjusted so as to improve the network performance and avoid congestion. Based on the above finding, it is concluded that the network congestion control algorithm based on Actor-Critic reinforcement learning model can effectively avoid the occurrence of TCP network congestion.

A mechanism of institutional isomorphism in referral networks among hospitals in Seoul, South Korea.

PubMed

Jung, Minsoo; Choi, Mankyu

2010-01-01

Hospitals engage in medical referral system relations voluntarily, by virtue of their own service capacities. These capacities include medical technology, equipment supply, and patient management, which are assessed individually by medical institutions in efforts to control costs and maintain efficiency in tertiary hospitals. This study assessed referral networks according to the institutional isomorphism theory of new economic sociology. As a result, the referral networks were shown to exhibit emergent structural hierarchy via cumulative clustering by established year and were not affected by attributive variables such as region, bed number, and year of establishment. In particular, the networks evidenced institutional isomorphism with certain central hospitals. As a consequence, personal indices were shown to decrease in accordance with its period, and only the structural index increased. Normative pressures cause organizations to become hierarchically homogenized, in accordance with the principle of organizational learning in specialized fields. Therefore, normative isomorphism on the basis of public domains should be considered an inherent factor in the development of referral networks.

The effects of deep network topology on mortality prediction.

PubMed

Hao Du; Ghassemi, Mohammad M; Mengling Feng

2016-08-01

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

Trans-species learning of cellular signaling systems with bimodal deep belief networks.

PubMed

Chen, Lujia; Cai, Chunhui; Chen, Vicky; Lu, Xinghua

2015-09-15

Model organisms play critical roles in biomedical research of human diseases and drug development. An imperative task is to translate information/knowledge acquired from model organisms to humans. In this study, we address a trans-species learning problem: predicting human cell responses to diverse stimuli, based on the responses of rat cells treated with the same stimuli. We hypothesized that rat and human cells share a common signal-encoding mechanism but employ different proteins to transmit signals, and we developed a bimodal deep belief network and a semi-restricted bimodal deep belief network to represent the common encoding mechanism and perform trans-species learning. These 'deep learning' models include hierarchically organized latent variables capable of capturing the statistical structures in the observed proteomic data in a distributed fashion. The results show that the models significantly outperform two current state-of-the-art classification algorithms. Our study demonstrated the potential of using deep hierarchical models to simulate cellular signaling systems. The software is available at the following URL: http://pubreview.dbmi.pitt.edu/TransSpeciesDeepLearning/. The data are available through SBV IMPROVER website, https://www.sbvimprover.com/challenge-2/overview, upon publication of the report by the organizers. xinghua@pitt.edu Supplementary data are available at Bioinformatics online. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

If we only knew what we know: principles for knowledge sharing across people, practices, and platforms.

PubMed

Dearing, James W; Greene, Sarah M; Stewart, Walter F; Williams, Andrew E

2011-03-01

The improvement of health outcomes for both individual patients and entire populations requires improvement in the array of structures that support decisions and activities by healthcare practitioners. Yet, many gaps remain in how even sophisticated healthcare organizations manage knowledge. Here we describe the value of a trans-institutional network for identifying and capturing how-to knowledge that contributes to improved outcomes. Organizing and sharing on-the-job experience would concentrate and organize the activities of individual practitioners and subject their rapid cycle improvement testing and refinement to a form of collective intelligence for subsequent diffusion back through the network. We use the existing Cancer Research Network as an example of how a loosely structured consortium of healthcare delivery organizations could create and grow an implementation registry to foster innovation and implementation success by communicating what works, how, and which practitioners are using each innovation. We focus on the principles and parameters that could be used as a basis for infrastructure design. As experiential knowledge from across institutions builds within such a system, the system could ultimately motivate rapid learning and adoption of best practices. Implications for research about healthcare IT, invention, and organizational learning are discussed.

Cooperative Learning for Distributed In-Network Traffic Classification

NASA Astrophysics Data System (ADS)

Joseph, S. B.; Loo, H. R.; Ismail, I.; Andromeda, T.; Marsono, M. N.

2017-04-01

Inspired by the concept of autonomic distributed/decentralized network management schemes, we consider the issue of information exchange among distributed network nodes to network performance and promote scalability for in-network monitoring. In this paper, we propose a cooperative learning algorithm for propagation and synchronization of network information among autonomic distributed network nodes for online traffic classification. The results show that network nodes with sharing capability perform better with a higher average accuracy of 89.21% (sharing data) and 88.37% (sharing clusters) compared to 88.06% for nodes without cooperative learning capability. The overall performance indicates that cooperative learning is promising for distributed in-network traffic classification.

System Complexity Reduction via Feature Selection

ERIC Educational Resources Information Center

Deng, Houtao

2011-01-01

This dissertation transforms a set of system complexity reduction problems to feature selection problems. Three systems are considered: classification based on association rules, network structure learning, and time series classification. Furthermore, two variable importance measures are proposed to reduce the feature selection bias in tree…

The Interactions of Relationships, Interest, and Self-Efficacy in Undergraduate Physics

NASA Astrophysics Data System (ADS)

Dou, Remy

This collected papers dissertation explores students' academic interactions in an active learning, introductory physics settings as they relate to the development of physics self-efficacy and interest. The motivation for this work extends from the national call to increase participation of students in the pursuit of science, technology, engineering, and mathematics (STEM) careers. Self-efficacy and interest are factors that play prominent roles in popular, evidence-based, career theories, including the Social cognitive career theory (SCCT) and the identity framework. Understanding how these constructs develop in light of the most pervasive characteristic of the active learning introductory physics classroom (i.e., peer-to-peer interactions) has implications on how students learn in a variety of introductory STEM classrooms and settings structured after constructivist and sociocultural learning theories. I collected data related to students' in-class interactions using the tools of social network analysis (SNA). Social network analysis has recently been shown to be an effective and useful way to examine the structure of student relationships that develop in and out of STEM classrooms. This set of studies furthers the implementation of SNA as a tool to examine self-efficacy and interest formation in the active learning physics classroom. Here I represent a variety of statistical applications of SNA, including bootstrapped linear regression (Chapter 2), structural equation modeling (Chapter 3), and hierarchical linear modeling for longitudinal analyses (Chapter 4). Self-efficacy data were collected using the Sources of Self-Efficacy for Science Courses - Physics survey (SOSESC-P), and interest data were collected using the physics identity survey. Data for these studies came from the Modeling Instruction sections of Introductory Physics with Calculus offered at Florida International University in the fall of 2014 and 2015. Analyses support the idea that students' perceptions of one another impact the development of their social network centrality, which in turn affects their self-efficacy building experiences and their overall self-efficacy. It was shown that unlike career theories that emphasize causal relationships between the development of self-efficacy and the subsequent growth of student interest, in this context student interest takes precedence before the development of student self-efficacy. This outcome also has various implications for career theories.

Temporal neural networks and transient analysis of complex engineering systems

NASA Astrophysics Data System (ADS)

Uluyol, Onder

A theory is introduced for a multi-layered Local Output Gamma Feedback (LOGF) neural network within the paradigm of Locally-Recurrent Globally-Feedforward neural networks. It is developed for the identification, prediction, and control tasks of spatio-temporal systems and allows for the presentation of different time scales through incorporation of a gamma memory. It is initially applied to the tasks of sunspot and Mackey-Glass series prediction as benchmarks, then it is extended to the task of power level control of a nuclear reactor at different fuel cycle conditions. The developed LOGF neuron model can also be viewed as a Transformed Input and State (TIS) Gamma memory for neural network architectures for temporal processing. The novel LOGF neuron model extends the static neuron model by incorporating into it a short-term memory structure in the form of a digital gamma filter. A feedforward neural network made up of LOGF neurons can thus be used to model dynamic systems. A learning algorithm based upon the Backpropagation-Through-Time (BTT) approach is derived. It is applicable for training a general L-layer LOGF neural network. The spatial and temporal weights and parameters of the network are iteratively optimized for a given problem using the derived learning algorithm.

node2vec: Scalable Feature Learning for Networks

PubMed Central

Grover, Aditya; Leskovec, Jure

2016-01-01

Prediction tasks over nodes and edges in networks require careful effort in engineering features used by learning algorithms. Recent research in the broader field of representation learning has led to significant progress in automating prediction by learning the features themselves. However, present feature learning approaches are not expressive enough to capture the diversity of connectivity patterns observed in networks. Here we propose node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks. In node2vec, we learn a mapping of nodes to a low-dimensional space of features that maximizes the likelihood of preserving network neighborhoods of nodes. We define a flexible notion of a node’s network neighborhood and design a biased random walk procedure, which efficiently explores diverse neighborhoods. Our algorithm generalizes prior work which is based on rigid notions of network neighborhoods, and we argue that the added flexibility in exploring neighborhoods is the key to learning richer representations. We demonstrate the efficacy of node2vec over existing state-of-the-art techniques on multi-label classification and link prediction in several real-world networks from diverse domains. Taken together, our work represents a new way for efficiently learning state-of-the-art task-independent representations in complex networks. PMID:27853626

Model-Free Optimal Tracking Control via Critic-Only Q-Learning.

PubMed

Luo, Biao; Liu, Derong; Huang, Tingwen; Wang, Ding

2016-10-01

Model-free control is an important and promising topic in control fields, which has attracted extensive attention in the past few years. In this paper, we aim to solve the model-free optimal tracking control problem of nonaffine nonlinear discrete-time systems. A critic-only Q-learning (CoQL) method is developed, which learns the optimal tracking control from real system data, and thus avoids solving the tracking Hamilton-Jacobi-Bellman equation. First, the Q-learning algorithm is proposed based on the augmented system, and its convergence is established. Using only one neural network for approximating the Q-function, the CoQL method is developed to implement the Q-learning algorithm. Furthermore, the convergence of the CoQL method is proved with the consideration of neural network approximation error. With the convergent Q-function obtained from the CoQL method, the adaptive optimal tracking control is designed based on the gradient descent scheme. Finally, the effectiveness of the developed CoQL method is demonstrated through simulation studies. The developed CoQL method learns with off-policy data and implements with a critic-only structure, thus it is easy to realize and overcome the inadequate exploration problem.

Vocal learning in the functionally referential food grunts of chimpanzees.

PubMed

Watson, Stuart K; Townsend, Simon W; Schel, Anne M; Wilke, Claudia; Wallace, Emma K; Cheng, Leveda; West, Victoria; Slocombe, Katie E

2015-02-16

One standout feature of human language is our ability to reference external objects and events with socially learned symbols, or words. Exploring the phylogenetic origins of this capacity is therefore key to a comprehensive understanding of the evolution of language. While non-human primates can produce vocalizations that refer to external objects in the environment, it is generally accepted that their acoustic structure is fixed and a product of arousal states. Indeed, it has been argued that the apparent lack of flexible control over the structure of referential vocalizations represents a key discontinuity with language. Here, we demonstrate vocal learning in the acoustic structure of referential food grunts in captive chimpanzees. We found that, following the integration of two groups of adult chimpanzees, the acoustic structure of referential food grunts produced for a specific food converged over 3 years. Acoustic convergence arose independently of preference for the food, and social network analyses indicated this only occurred after strong affiliative relationships were established between the original subgroups. We argue that these data represent the first evidence of non-human animals actively modifying and socially learning the structure of a meaningful referential vocalization from conspecifics. Our findings indicate that primate referential call structure is not simply determined by arousal and that the socially learned nature of referential words in humans likely has ancient evolutionary origins. Copyright © 2015 Elsevier Ltd. All rights reserved.

Building a Governance Strategy for CER: The Patient Outcomes Research to Advance Learning (PORTAL) Network Experience

PubMed Central

Paolino, Andrea R.; McGlynn, Elizabeth A.; Lieu, Tracy; Nelson, Andrew F.; Prausnitz, Stephanie; Horberg, Michael A.; Arterburn, David E.; Gould, Michael K.; Laws, Reesa L.; Steiner, John F.

2016-01-01

Introduction: The Patient Outcomes Research to Advance Learning (PORTAL) Network was established with funding from the Patient-Centered Outcomes Research Institute (PCORI) in 2014. The PORTAL team adapted governance structures and processes from past research network collaborations. We will review and outline the structures and processes of the PORTAL governance approach and describe how proactively focusing on priority areas helped us to facilitate an ambitious research agenda. Background: For years a variety of funders have supported large-scale infrastructure grants to promote the use of clinical datasets to answer important comparative effectiveness research (CER) questions. These awards have provided the impetus for health care systems to join forces in creating clinical data research networks. Often, these scientific networks do not develop governance processes proactively or systematically, and address issues only as problems arise. Even if network leaders and collaborators foresee the need to develop governance approaches, they may underestimate the time and effort required to develop sound processes. The resulting delays can impede research progress. Innovation: Because the PORTAL sites had built trust and a foundation of collaboration by participating with one another in past research networks, essential elements of effective governance such as guiding principles, decision making processes, project governance, data governance, and stakeholders in governance were familiar to PORTAL investigators. This trust and familiarity enabled the network to rapidly prioritize areas that required sound governance approaches: responding to new research opportunities, creating a culture of trust and collaboration, conducting individual studies, within the broader network, assigning responsibility and credit to scientific investigators, sharing data while protecting privacy/security, and allocating resources. The PORTAL Governance Document, complete with a Toolkit of Appendices is included for reference and for adaptation by other networks. Credibility: As a result of identifying project-based governance priorities (IRB approval, subcontracting, selection of new research including lead PI and participating sites, and authorship) and data governance priorities (reciprocal data use agreement, analytic plan procedures, and other tools for data governance), PORTAL established most of its governance structure by Month 6 of the 18 month project. This allowed science to progress and collaborators to experience first-hand how the structures and procedures functioned in the remaining 12 months of the project, leaving ample time to refine them and to develop new structures or processes as necessary. Discussion: The use of procedures and processes with which participating investigators and their home institutions were already familiar allowed project and regulatory requirements to be established quickly to protect patients, their data, and the health care systems that act as stewards for both. As the project progressed, PORTAL was able to test and adjust the structures it put place, and to make substantive revisions by Month 17. As a result, priority processes have been predictable, transparent and effective. Conclusion/Next steps: Strong governance practices are a stewardship responsibility of research networks to justify the trust of patients, health plan members, health care delivery organizations, and other stakeholders. Well-planned governance can reduce the time necessary to initiate the scientific activities of a network, a particular concern when the time frame to complete research is short. Effective network and data governance structures protect patient and institutional data as well as the interests of investigators and their institutions, and assures that the network has built an environment to meet the goals of the research. PMID:27141524

Building a Governance Strategy for CER: The Patient Outcomes Research to Advance Learning (PORTAL) Network Experience.

PubMed

Paolino, Andrea R; McGlynn, Elizabeth A; Lieu, Tracy; Nelson, Andrew F; Prausnitz, Stephanie; Horberg, Michael A; Arterburn, David E; Gould, Michael K; Laws, Reesa L; Steiner, John F

2016-01-01

The Patient Outcomes Research to Advance Learning (PORTAL) Network was established with funding from the Patient-Centered Outcomes Research Institute (PCORI) in 2014. The PORTAL team adapted governance structures and processes from past research network collaborations. We will review and outline the structures and processes of the PORTAL governance approach and describe how proactively focusing on priority areas helped us to facilitate an ambitious research agenda. For years a variety of funders have supported large-scale infrastructure grants to promote the use of clinical datasets to answer important comparative effectiveness research (CER) questions. These awards have provided the impetus for health care systems to join forces in creating clinical data research networks. Often, these scientific networks do not develop governance processes proactively or systematically, and address issues only as problems arise. Even if network leaders and collaborators foresee the need to develop governance approaches, they may underestimate the time and effort required to develop sound processes. The resulting delays can impede research progress. Because the PORTAL sites had built trust and a foundation of collaboration by participating with one another in past research networks, essential elements of effective governance such as guiding principles, decision making processes, project governance, data governance, and stakeholders in governance were familiar to PORTAL investigators. This trust and familiarity enabled the network to rapidly prioritize areas that required sound governance approaches: responding to new research opportunities, creating a culture of trust and collaboration, conducting individual studies, within the broader network, assigning responsibility and credit to scientific investigators, sharing data while protecting privacy/security, and allocating resources. The PORTAL Governance Document, complete with a Toolkit of Appendices is included for reference and for adaptation by other networks. As a result of identifying project-based governance priorities (IRB approval, subcontracting, selection of new research including lead PI and participating sites, and authorship) and data governance priorities (reciprocal data use agreement, analytic plan procedures, and other tools for data governance), PORTAL established most of its governance structure by Month 6 of the 18 month project. This allowed science to progress and collaborators to experience first-hand how the structures and procedures functioned in the remaining 12 months of the project, leaving ample time to refine them and to develop new structures or processes as necessary. The use of procedures and processes with which participating investigators and their home institutions were already familiar allowed project and regulatory requirements to be established quickly to protect patients, their data, and the health care systems that act as stewards for both. As the project progressed, PORTAL was able to test and adjust the structures it put place, and to make substantive revisions by Month 17. As a result, priority processes have been predictable, transparent and effective. Strong governance practices are a stewardship responsibility of research networks to justify the trust of patients, health plan members, health care delivery organizations, and other stakeholders. Well-planned governance can reduce the time necessary to initiate the scientific activities of a network, a particular concern when the time frame to complete research is short. Effective network and data governance structures protect patient and institutional data as well as the interests of investigators and their institutions, and assures that the network has built an environment to meet the goals of the research.

A Dictionary Learning Approach for Signal Sampling in Task-Based fMRI for Reduction of Big Data

PubMed Central

Ge, Bao; Li, Xiang; Jiang, Xi; Sun, Yifei; Liu, Tianming

2018-01-01

The exponential growth of fMRI big data offers researchers an unprecedented opportunity to explore functional brain networks. However, this opportunity has not been fully explored yet due to the lack of effective and efficient tools for handling such fMRI big data. One major challenge is that computing capabilities still lag behind the growth of large-scale fMRI databases, e.g., it takes many days to perform dictionary learning and sparse coding of whole-brain fMRI data for an fMRI database of average size. Therefore, how to reduce the data size but without losing important information becomes a more and more pressing issue. To address this problem, we propose a signal sampling approach for significant fMRI data reduction before performing structurally-guided dictionary learning and sparse coding of whole brain's fMRI data. We compared the proposed structurally guided sampling method with no sampling, random sampling and uniform sampling schemes, and experiments on the Human Connectome Project (HCP) task fMRI data demonstrated that the proposed method can achieve more than 15 times speed-up without sacrificing the accuracy in identifying task-evoked functional brain networks. PMID:29706880

A Dictionary Learning Approach for Signal Sampling in Task-Based fMRI for Reduction of Big Data.

PubMed

Ge, Bao; Li, Xiang; Jiang, Xi; Sun, Yifei; Liu, Tianming

2018-01-01

The exponential growth of fMRI big data offers researchers an unprecedented opportunity to explore functional brain networks. However, this opportunity has not been fully explored yet due to the lack of effective and efficient tools for handling such fMRI big data. One major challenge is that computing capabilities still lag behind the growth of large-scale fMRI databases, e.g., it takes many days to perform dictionary learning and sparse coding of whole-brain fMRI data for an fMRI database of average size. Therefore, how to reduce the data size but without losing important information becomes a more and more pressing issue. To address this problem, we propose a signal sampling approach for significant fMRI data reduction before performing structurally-guided dictionary learning and sparse coding of whole brain's fMRI data. We compared the proposed structurally guided sampling method with no sampling, random sampling and uniform sampling schemes, and experiments on the Human Connectome Project (HCP) task fMRI data demonstrated that the proposed method can achieve more than 15 times speed-up without sacrificing the accuracy in identifying task-evoked functional brain networks.

Decomposition and extraction: a new framework for visual classification.

PubMed

Fang, Yuqiang; Chen, Qiang; Sun, Lin; Dai, Bin; Yan, Shuicheng

2014-08-01

In this paper, we present a novel framework for visual classification based on hierarchical image decomposition and hybrid midlevel feature extraction. Unlike most midlevel feature learning methods, which focus on the process of coding or pooling, we emphasize that the mechanism of image composition also strongly influences the feature extraction. To effectively explore the image content for the feature extraction, we model a multiplicity feature representation mechanism through meaningful hierarchical image decomposition followed by a fusion step. In particularly, we first propose a new hierarchical image decomposition approach in which each image is decomposed into a series of hierarchical semantical components, i.e, the structure and texture images. Then, different feature extraction schemes can be adopted to match the decomposed structure and texture processes in a dissociative manner. Here, two schemes are explored to produce property related feature representations. One is based on a single-stage network over hand-crafted features and the other is based on a multistage network, which can learn features from raw pixels automatically. Finally, those multiple midlevel features are incorporated by solving a multiple kernel learning task. Extensive experiments are conducted on several challenging data sets for visual classification, and experimental results demonstrate the effectiveness of the proposed method.

Imaging learning and memory: classical conditioning.

PubMed

Schreurs, B G; Alkon, D L

2001-12-15

The search for the biological basis of learning and memory has, until recently, been constrained by the limits of technology to classic anatomic and electrophysiologic studies. With the advent of functional imaging, we have begun to delve into what, for many, was a "black box." We review several different types of imaging experiments, including steady state animal experiments that image the functional labeling of fixed tissues, and dynamic human studies based on functional imaging of the intact brain during learning. The data suggest that learning and memory involve a surprising conservation of mechanisms and the integrated networking of a number of structures and processes. Copyright 2001 Wiley-Liss, Inc.

Reinforced Adversarial Neural Computer for de Novo Molecular Design.

PubMed

Putin, Evgeny; Asadulaev, Arip; Ivanenkov, Yan; Aladinskiy, Vladimir; Sanchez-Lengeling, Benjamin; Aspuru-Guzik, Alán; Zhavoronkov, Alex

2018-06-12

In silico modeling is a crucial milestone in modern drug design and development. Although computer-aided approaches in this field are well-studied, the application of deep learning methods in this research area is at the beginning. In this work, we present an original deep neural network (DNN) architecture named RANC (Reinforced Adversarial Neural Computer) for the de novo design of novel small-molecule organic structures based on the generative adversarial network (GAN) paradigm and reinforcement learning (RL). As a generator RANC uses a differentiable neural computer (DNC), a category of neural networks, with increased generation capabilities due to the addition of an explicit memory bank, which can mitigate common problems found in adversarial settings. The comparative results have shown that RANC trained on the SMILES string representation of the molecules outperforms its first DNN-based counterpart ORGANIC by several metrics relevant to drug discovery: the number of unique structures, passing medicinal chemistry filters (MCFs), Muegge criteria, and high QED scores. RANC is able to generate structures that match the distributions of the key chemical features/descriptors (e.g., MW, logP, TPSA) and lengths of the SMILES strings in the training data set. Therefore, RANC can be reasonably regarded as a promising starting point to develop novel molecules with activity against different biological targets or pathways. In addition, this approach allows scientists to save time and covers a broad chemical space populated with novel and diverse compounds.

Progress with modeling activity landscapes in drug discovery.

PubMed

Vogt, Martin

2018-04-19

Activity landscapes (ALs) are representations and models of compound data sets annotated with a target-specific activity. In contrast to quantitative structure-activity relationship (QSAR) models, ALs aim at characterizing structure-activity relationships (SARs) on a large-scale level encompassing all active compounds for specific targets. The popularity of AL modeling has grown substantially with the public availability of large activity-annotated compound data sets. AL modeling crucially depends on molecular representations and similarity metrics used to assess structural similarity. Areas covered: The concepts of AL modeling are introduced and its basis in quantitatively assessing molecular similarity is discussed. The different types of AL modeling approaches are introduced. AL designs can broadly be divided into three categories: compound-pair based, dimensionality reduction, and network approaches. Recent developments for each of these categories are discussed focusing on the application of mathematical, statistical, and machine learning tools for AL modeling. AL modeling using chemical space networks is covered in more detail. Expert opinion: AL modeling has remained a largely descriptive approach for the analysis of SARs. Beyond mere visualization, the application of analytical tools from statistics, machine learning and network theory has aided in the sophistication of AL designs and provides a step forward in transforming ALs from descriptive to predictive tools. To this end, optimizing representations that encode activity relevant features of molecules might prove to be a crucial step.