The application of network teaching in applied optics teaching

NASA Astrophysics Data System (ADS)

Zhao, Huifu; Piao, Mingxu; Li, Lin; Liu, Dongmei

2017-08-01

Network technology has become a creative tool of changing human productivity, the rapid development of it has brought profound changes to our learning, working and life. Network technology has many advantages such as rich contents, various forms, convenient retrieval, timely communication and efficient combination of resources. Network information resources have become the new education resources, get more and more application in the education, has now become the teaching and learning tools. Network teaching enriches the teaching contents, changes teaching process from the traditional knowledge explanation into the new teaching process by establishing situation, independence and cooperation in the network technology platform. The teacher's role has shifted from teaching in classroom to how to guide students to learn better. Network environment only provides a good platform for the teaching, we can get a better teaching effect only by constantly improve the teaching content. Changchun university of science and technology introduced a BB teaching platform, on the platform, the whole optical classroom teaching and the classroom teaching can be improved. Teachers make assignments online, students learn independently offline or the group learned cooperatively, this expands the time and space of teaching. Teachers use hypertext form related knowledge of applied optics, rich cases and learning resources, set up the network interactive platform, homework submission system, message board, etc. The teaching platform simulated the learning interest of students and strengthens the interaction in the teaching.

Sea ice classification using fast learning neural networks

NASA Technical Reports Server (NTRS)

Dawson, M. S.; Fung, A. K.; Manry, M. T.

1992-01-01

A first learning neural network approach to the classification of sea ice is presented. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) were tested on simulated data sets based on the known dominant scattering characteristics of the target class. Four classes were used in the data simulation: open water, thick lossy saline ice, thin saline ice, and multiyear ice. The BP network was unable to consistently converge to less than 25 percent error while the FL method yielded an average error of approximately 1 percent on the first iteration of training. The fast learning method presented can significantly reduce the CPU time necessary to train a neural network as well as consistently yield higher classification accuracy than BP networks.

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.

Adaptive categorization of ART networks in robot behavior learning using game-theoretic formulation.

PubMed

Fung, Wai-keung; Liu, Yun-hui

2003-12-01

Adaptive Resonance Theory (ART) networks are employed in robot behavior learning. Two of the difficulties in online robot behavior learning, namely, (1) exponential memory increases with time, (2) difficulty for operators to specify learning tasks accuracy and control learning attention before learning. In order to remedy the aforementioned difficulties, an adaptive categorization mechanism is introduced in ART networks for perceptual and action patterns categorization in this paper. A game-theoretic formulation of adaptive categorization for ART networks is proposed for vigilance parameter adaptation for category size control on the categories formed. The proposed vigilance parameter update rule can help improving categorization performance in the aspect of category number stability and solve the problem of selecting initial vigilance parameter prior to pattern categorization in traditional ART networks. Behavior learning using physical robot is conducted to demonstrate the effectiveness of the proposed adaptive categorization mechanism in ART networks.

A Sharing Mind Map-Oriented Approach to Enhance Collaborative Mobile Learning with Digital Archiving Systems

ERIC Educational Resources Information Center

Chang, Jui-Hung; Chiu, Po-Sheng; Huang, Yueh-Min

2018-01-01

With the advances in mobile network technology, the use of portable devices and mobile networks for learning is not limited by time and space. Such use, in combination with appropriate learning strategies, can achieve a better effect. Despite the effectiveness of mobile learning, students' learning direction, progress, and achievement may differ.…

An Analysis of Density and Degree-Centrality According to the Social Networking Structure Formed in an Online Learning Environment

ERIC Educational Resources Information Center

Ergün, Esin; Usluel, Yasemin Koçak

2016-01-01

In this study, we assessed the communication structure in an educational online learning environment using social network analysis (SNA). The communication structure was examined with respect to time, and instructor's participation. The course was implemented using ELGG, a network learning environment, blended with face-to-face sessions over a…

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.

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.

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.

A Novel Connectionist Network for Solving Long Time-Lag Prediction Tasks

NASA Astrophysics Data System (ADS)

Johnson, Keith; MacNish, Cara

Traditional Recurrent Neural Networks (RNNs) perform poorly on learning tasks involving long time-lag dependencies. More recent approaches such as LSTM and its variants significantly improve on RNNs ability to learn this type of problem. We present an alternative approach to encoding temporal dependencies that associates temporal features with nodes rather than state values, where the nodes explicitly encode dependencies over variable time delays. We show promising results comparing the network's performance to LSTM variants on an extended Reber grammar task.

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

PubMed

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

2018-03-23

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

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.

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.

Creating and Sustaining Inquiry Spaces for Teacher Learning and System Transformation

ERIC Educational Resources Information Center

Kaser, Linda; Halbert, Judy

2014-01-01

Over a 15-year period, one Western Canadian province, British Columbia, has been exploring the potential of inquiry learning networks to deepen teacher professional learning and to influence the system as a whole. During this time, we have learned a great deal about shifting practice through inquiry networks. In this article, we provide a…

Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks

PubMed Central

Miconi, Thomas

2017-01-01

Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior. DOI: http://dx.doi.org/10.7554/eLife.20899.001 PMID:28230528

Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks.

PubMed

Miconi, Thomas

2017-02-23

Neural activity during cognitive tasks exhibits complex dynamics that flexibly encode task-relevant variables. Chaotic recurrent networks, which spontaneously generate rich dynamics, have been proposed as a model of cortical computation during cognitive tasks. However, existing methods for training these networks are either biologically implausible, and/or require a continuous, real-time error signal to guide learning. Here we show that a biologically plausible learning rule can train such recurrent networks, guided solely by delayed, phasic rewards at the end of each trial. Networks endowed with this learning rule can successfully learn nontrivial tasks requiring flexible (context-dependent) associations, memory maintenance, nonlinear mixed selectivities, and coordination among multiple outputs. The resulting networks replicate complex dynamics previously observed in animal cortex, such as dynamic encoding of task features and selective integration of sensory inputs. We conclude that recurrent neural networks offer a plausible model of cortical dynamics during both learning and performance of flexible behavior.

Inversion of surface parameters using fast learning neural networks

NASA Technical Reports Server (NTRS)

Dawson, M. S.; Olvera, J.; Fung, A. K.; Manry, M. T.

1992-01-01

A neural network approach to the inversion of surface scattering parameters is presented. Simulated data sets based on a surface scattering model are used so that the data may be viewed as taken from a completely known randomly rough surface. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) are tested on the simulated backscattering data. The RMS error of training the FL network is found to be less than one half the error of the BP network while requiring one to two orders of magnitude less CPU time. When applied to inversion of parameters from a statistically rough surface, the FL method is successful at recovering the surface permittivity, the surface correlation length, and the RMS surface height in less time and with less error than the BP network. Further applications of the FL neural network to the inversion of parameters from backscatter measurements of an inhomogeneous layer above a half space are shown.

Systemwide Implementation of Project-Based Learning: The Philadelphia Approach

ERIC Educational Resources Information Center

Schwalm, Jason; Tylek, Karen Smuck

2012-01-01

Citywide implementation of project-based learning highlights the benefits--and the challenges--of promoting exemplary practices across an entire out-of-school time (OST) network. In summer 2009, the City of Philadelphia and its intermediary, the Public Health Management Corporation (PHMC), introduced project-based learning to a network of more…

Learning State Space Dynamics in Recurrent Networks

NASA Astrophysics Data System (ADS)

Simard, Patrice Yvon

Fully recurrent (asymmetrical) networks can be used to learn temporal trajectories. The network is unfolded in time, and backpropagation is used to train the weights. The presence of recurrent connections creates internal states in the system which vary as a function of time. The resulting dynamics can provide interesting additional computing power but learning is made more difficult by the existence of internal memories. This study first exhibits the properties of recurrent networks in terms of convergence when the internal states of the system are unknown. A new energy functional is provided to change the weights of the units in order to the control the stability of the fixed points of the network's dynamics. The power of the resultant algorithm is illustrated with the simulation of a content addressable memory. Next, the more general case of time trajectories on a recurrent network is studied. An application is proposed in which trajectories are generated to draw letters as a function of an input. In another application of recurrent systems, a neural network certain temporal properties observed in human callosally sectioned brains. Finally the proposed algorithm for stabilizing dynamics around fixed points is extended to one for stabilizing dynamics around time trajectories. Its effects are illustrated on a network which generates Lisajous curves.

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

PubMed

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

2017-03-01

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

Multi-layer network utilizing rewarded spike time dependent plasticity to learn a foraging task

PubMed Central

2017-01-01

Neural networks with a single plastic layer employing reward modulated spike time dependent plasticity (STDP) are capable of learning simple foraging tasks. Here we demonstrate advanced pattern discrimination and continuous learning in a network of spiking neurons with multiple plastic layers. The network utilized both reward modulated and non-reward modulated STDP and implemented multiple mechanisms for homeostatic regulation of synaptic efficacy, including heterosynaptic plasticity, gain control, output balancing, activity normalization of rewarded STDP and hard limits on synaptic strength. We found that addition of a hidden layer of neurons employing non-rewarded STDP created neurons that responded to the specific combinations of inputs and thus performed basic classification of the input patterns. When combined with a following layer of neurons implementing rewarded STDP, the network was able to learn, despite the absence of labeled training data, discrimination between rewarding patterns and the patterns designated as punishing. Synaptic noise allowed for trial-and-error learning that helped to identify the goal-oriented strategies which were effective in task solving. The study predicts a critical set of properties of the spiking neuronal network with STDP that was sufficient to solve a complex foraging task involving pattern classification and decision making. PMID:28961245

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.

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.

Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting

PubMed Central

Ghazali, Rozaida; Herawan, Tutut

2016-01-01

Time series forecasting has gained much attention due to its many practical applications. Higher-order neural network with recurrent feedback is a powerful technique that has been used successfully for time series forecasting. It maintains fast learning and the ability to learn the dynamics of the time series over time. Network output feedback is the most common recurrent feedback for many recurrent neural network models. However, not much attention has been paid to the use of network error feedback instead of network output feedback. In this study, we propose a novel model, called Ridge Polynomial Neural Network with Error Feedback (RPNN-EF) that incorporates higher order terms, recurrence and error feedback. To evaluate the performance of RPNN-EF, we used four univariate time series with different forecasting horizons, namely star brightness, monthly smoothed sunspot numbers, daily Euro/Dollar exchange rate, and Mackey-Glass time-delay differential equation. We compared the forecasting performance of RPNN-EF with the ordinary Ridge Polynomial Neural Network (RPNN) and the Dynamic Ridge Polynomial Neural Network (DRPNN). Simulation results showed an average 23.34% improvement in Root Mean Square Error (RMSE) with respect to RPNN and an average 10.74% improvement with respect to DRPNN. That means that using network errors during training helps enhance the overall forecasting performance for the network. PMID:27959927

Ridge Polynomial Neural Network with Error Feedback for Time Series Forecasting.

PubMed

Waheeb, Waddah; Ghazali, Rozaida; Herawan, Tutut

2016-01-01

Time series forecasting has gained much attention due to its many practical applications. Higher-order neural network with recurrent feedback is a powerful technique that has been used successfully for time series forecasting. It maintains fast learning and the ability to learn the dynamics of the time series over time. Network output feedback is the most common recurrent feedback for many recurrent neural network models. However, not much attention has been paid to the use of network error feedback instead of network output feedback. In this study, we propose a novel model, called Ridge Polynomial Neural Network with Error Feedback (RPNN-EF) that incorporates higher order terms, recurrence and error feedback. To evaluate the performance of RPNN-EF, we used four univariate time series with different forecasting horizons, namely star brightness, monthly smoothed sunspot numbers, daily Euro/Dollar exchange rate, and Mackey-Glass time-delay differential equation. We compared the forecasting performance of RPNN-EF with the ordinary Ridge Polynomial Neural Network (RPNN) and the Dynamic Ridge Polynomial Neural Network (DRPNN). Simulation results showed an average 23.34% improvement in Root Mean Square Error (RMSE) with respect to RPNN and an average 10.74% improvement with respect to DRPNN. That means that using network errors during training helps enhance the overall forecasting performance for the network.

A model of human motor sequence learning explains facilitation and interference effects based on spike-timing dependent plasticity.

PubMed

Wang, Quan; Rothkopf, Constantin A; Triesch, Jochen

2017-08-01

The ability to learn sequential behaviors is a fundamental property of our brains. Yet a long stream of studies including recent experiments investigating motor sequence learning in adult human subjects have produced a number of puzzling and seemingly contradictory results. In particular, when subjects have to learn multiple action sequences, learning is sometimes impaired by proactive and retroactive interference effects. In other situations, however, learning is accelerated as reflected in facilitation and transfer effects. At present it is unclear what the underlying neural mechanism are that give rise to these diverse findings. Here we show that a recently developed recurrent neural network model readily reproduces this diverse set of findings. The self-organizing recurrent neural network (SORN) model is a network of recurrently connected threshold units that combines a simplified form of spike-timing dependent plasticity (STDP) with homeostatic plasticity mechanisms ensuring network stability, namely intrinsic plasticity (IP) and synaptic normalization (SN). When trained on sequence learning tasks modeled after recent experiments we find that it reproduces the full range of interference, facilitation, and transfer effects. We show how these effects are rooted in the network's changing internal representation of the different sequences across learning and how they depend on an interaction of training schedule and task similarity. Furthermore, since learning in the model is based on fundamental neuronal plasticity mechanisms, the model reveals how these plasticity mechanisms are ultimately responsible for the network's sequence learning abilities. In particular, we find that all three plasticity mechanisms are essential for the network to learn effective internal models of the different training sequences. This ability to form effective internal models is also the basis for the observed interference and facilitation effects. This suggests that STDP, IP, and SN may be the driving forces behind our ability to learn complex action sequences.

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.

Academic Social Networking Brings Web 2.0 Technologies to the Middle Grades

ERIC Educational Resources Information Center

Taranto, Gregory; Dalbon, Melissa; Gaetano, Julie

2011-01-01

The middle grades are an exciting time for adolescents to explore, learn, and collaborate with one another (National Middle School Association, 2010). By incorporating an academic social network as part of the classroom experience, collaboration and active learning take on new forms, and a transformation from passive learning to active learning…

A Learning Content Authoring Approach Based on Semantic Technologies and Social Networking: An Empirical Study

ERIC Educational Resources Information Center

Nesic, Sasa; Gasevic, Dragan; Jazayeri, Mehdi; Landoni, Monica

2011-01-01

Semantic web technologies have been applied to many aspects of learning content authoring including semantic annotation, semantic search, dynamic assembly, and personalization of learning content. At the same time, social networking services have started to play an important role in the authoring process by supporting authors' collaborative…

Learning strategies, study habits and social networking activity of undergraduate medical students.

PubMed

Bickerdike, Andrea; O'Deasmhunaigh, Conall; O'Flynn, Siun; O'Tuathaigh, Colm

2016-07-17

To determine learning strategies, study habits, and online social networking use of undergraduates at an Irish medical school, and their relationship with academic performance. A cross-sectional study was conducted in Year 2 and final year undergraduate-entry and graduate-entry students at an Irish medical school. Data about participants' demographics and educational background, study habits (including time management), and use of online media was collected using a self-report questionnaire. Participants' learning strategies were measured using the 18-item Approaches to Learning and Studying Inventory (ALSI). Year score percentage was the measure of academic achievement. The association between demographic/educational factors, learning strategies, study habits, and academic achievement was statistically analysed using regression analysis. Forty-two percent of students were included in this analysis (n=376). A last-minute "cramming" time management study strategy was associated with increased use of online social networks. Learning strategies differed between undergraduate- and graduate-entrants, with the latter less likely to adopt a 'surface approach' and more likely adopt a 'study monitoring' approach. Year score percentage was positively correlated with the 'effort management/organised studying' learning style. Poorer academic performance was associated with a poor time management approach to studying ("cramming") and increased use of the 'surface learning' strategy. Our study demonstrates that effort management and organised studying should be promoted, and surface learning discouraged, as part of any effort to optimise academic performance in medical school. Excessive use of social networking contributes to poor study habits, which are associated with reduced academic achievement.

Action-Driven Visual Object Tracking With Deep Reinforcement Learning.

PubMed

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

2018-06-01

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

Hebbian based learning with winner-take-all for spiking neural networks

NASA Astrophysics Data System (ADS)

Gupta, Ankur; Long, Lyle

2009-03-01

Learning methods for spiking neural networks are not as well developed as the traditional neural networks that widely use back-propagation training. We propose and implement a Hebbian based learning method with winner-take-all competition for spiking neural networks. This approach is spike time dependent which makes it naturally well suited for a network of spiking neurons. Homeostasis with Hebbian learning is implemented which ensures stability and quicker learning. Homeostasis implies that the net sum of incoming weights associated with a neuron remains the same. Winner-take-all is also implemented for competitive learning between output neurons. We implemented this learning rule on a biologically based vision processing system that we are developing, and use layers of leaky integrate and fire neurons. The network when presented with 4 bars (or Gabor filters) of different orientation learns to recognize the bar orientations (or Gabor filters). After training, each output neuron learns to recognize a bar at specific orientation and responds by firing more vigorously to that bar and less vigorously to others. These neurons are found to have bell shaped tuning curves and are similar to the simple cells experimentally observed by Hubel and Wiesel in the striate cortex of cat and monkey.

Learning oncogenetic networks by reducing to mixed integer linear programming.

PubMed

Shahrabi Farahani, Hossein; Lagergren, Jens

2013-01-01

Cancer can be a result of accumulation of different types of genetic mutations such as copy number aberrations. The data from tumors are cross-sectional and do not contain the temporal order of the genetic events. Finding the order in which the genetic events have occurred and progression pathways are of vital importance in understanding the disease. In order to model cancer progression, we propose Progression Networks, a special case of Bayesian networks, that are tailored to model disease progression. Progression networks have similarities with Conjunctive Bayesian Networks (CBNs) [1],a variation of Bayesian networks also proposed for modeling disease progression. We also describe a learning algorithm for learning Bayesian networks in general and progression networks in particular. We reduce the hard problem of learning the Bayesian and progression networks to Mixed Integer Linear Programming (MILP). MILP is a Non-deterministic Polynomial-time complete (NP-complete) problem for which very good heuristics exists. We tested our algorithm on synthetic and real cytogenetic data from renal cell carcinoma. We also compared our learned progression networks with the networks proposed in earlier publications. The software is available on the website https://bitbucket.org/farahani/diprog.

Dynamic functional connectivity shapes individual differences in associative learning.

PubMed

Fatima, Zainab; Kovacevic, Natasha; Misic, Bratislav; McIntosh, Anthony Randal

2016-11-01

Current neuroscientific research has shown that the brain reconfigures its functional interactions at multiple timescales. Here, we sought to link transient changes in functional brain networks to individual differences in behavioral and cognitive performance by using an active learning paradigm. Participants learned associations between pairs of unrelated visual stimuli by using feedback. Interindividual behavioral variability was quantified with a learning rate measure. By using a multivariate statistical framework (partial least squares), we identified patterns of network organization across multiple temporal scales (within a trial, millisecond; across a learning session, minute) and linked these to the rate of change in behavioral performance (fast and slow). Results indicated that posterior network connectivity was present early in the trial for fast, and later in the trial for slow performers. In contrast, connectivity in an associative memory network (frontal, striatal, and medial temporal regions) occurred later in the trial for fast, and earlier for slow performers. Time-dependent changes in the posterior network were correlated with visual/spatial scores obtained from independent neuropsychological assessments, with fast learners performing better on visual/spatial subtests. No relationship was found between functional connectivity dynamics in the memory network and visual/spatial test scores indicative of cognitive skill. By using a comprehensive set of measures (behavioral, cognitive, and neurophysiological), we report that individual variations in learning-related performance change are supported by differences in cognitive ability and time-sensitive connectivity in functional neural networks. Hum Brain Mapp 37:3911-3928, 2016. © 2016 Wiley Periodicals, Inc. © 2016 Wiley Periodicals, Inc.

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.

Learning Boolean Networks in HepG2 cells using ToxCast High-Content Imaging Data (SOT annual meeting)

EPA Science Inventory

Cells adapt to their environment via homeostatic processes that are regulated by complex molecular networks. Our objective was to learn key elements of these networks in HepG2 cells using ToxCast High-content imaging (HCI) measurements taken over three time points (1, 24, and 72h...

Performances of Machine Learning Algorithms for Binary Classification of Network Anomaly Detection System

NASA Astrophysics Data System (ADS)

Nawir, Mukrimah; Amir, Amiza; Lynn, Ong Bi; Yaakob, Naimah; Badlishah Ahmad, R.

2018-05-01

The rapid growth of technologies might endanger them to various network attacks due to the nature of data which are frequently exchange their data through Internet and large-scale data that need to be handle. Moreover, network anomaly detection using machine learning faced difficulty when dealing the involvement of dataset where the number of labelled network dataset is very few in public and this caused many researchers keep used the most commonly network dataset (KDDCup99) which is not relevant to employ the machine learning (ML) algorithms for a classification. Several issues regarding these available labelled network datasets are discussed in this paper. The aim of this paper to build a network anomaly detection system using machine learning algorithms that are efficient, effective and fast processing. The finding showed that AODE algorithm is performed well in term of accuracy and processing time for binary classification towards UNSW-NB15 dataset.

Gradient calculations for dynamic recurrent neural networks: a survey.

PubMed

Pearlmutter, B A

1995-01-01

Surveys learning algorithms for recurrent neural networks with hidden units and puts the various techniques into a common framework. The authors discuss fixed point learning algorithms, namely recurrent backpropagation and deterministic Boltzmann machines, and nonfixed point algorithms, namely backpropagation through time, Elman's history cutoff, and Jordan's output feedback architecture. Forward propagation, an on-line technique that uses adjoint equations, and variations thereof, are also discussed. In many cases, the unified presentation leads to generalizations of various sorts. The author discusses advantages and disadvantages of temporally continuous neural networks in contrast to clocked ones continues with some "tricks of the trade" for training, using, and simulating continuous time and recurrent neural networks. The author presents some simulations, and at the end, addresses issues of computational complexity and learning speed.

Learning a trajectory using adjoint functions and teacher forcing

NASA Technical Reports Server (NTRS)

Toomarian, Nikzad B.; Barhen, Jacob

1992-01-01

A new methodology for faster supervised temporal learning in nonlinear neural networks is presented which builds upon the concept of adjoint operators to allow fast computation of the gradients of an error functional with respect to all parameters of the neural architecture, and exploits the concept of teacher forcing to incorporate information on the desired output into the activation dynamics. The importance of the initial or final time conditions for the adjoint equations is discussed. A new algorithm is presented in which the adjoint equations are solved simultaneously (i.e., forward in time) with the activation dynamics of the neural network. We also indicate how teacher forcing can be modulated in time as learning proceeds. The results obtained show that the learning time is reduced by one to two orders of magnitude with respect to previously published results, while trajectory tracking is significantly improved. The proposed methodology makes hardware implementation of temporal learning attractive for real-time applications.

Cascade Back-Propagation Learning in Neural Networks

NASA Technical Reports Server (NTRS)

Duong, Tuan A.

2003-01-01

The cascade back-propagation (CBP) algorithm is the basis of a conceptual design for accelerating learning in artificial neural networks. The neural networks would be implemented as analog very-large-scale integrated (VLSI) circuits, and circuits to implement the CBP algorithm would be fabricated on the same VLSI circuit chips with the neural networks. Heretofore, artificial neural networks have learned slowly because it has been necessary to train them via software, for lack of a good on-chip learning technique. The CBP algorithm is an on-chip technique that provides for continuous learning in real time. Artificial neural networks are trained by example: A network is presented with training inputs for which the correct outputs are known, and the algorithm strives to adjust the weights of synaptic connections in the network to make the actual outputs approach the correct outputs. The input data are generally divided into three parts. Two of the parts, called the "training" and "cross-validation" sets, respectively, must be such that the corresponding input/output pairs are known. During training, the cross-validation set enables verification of the status of the input-to-output transformation learned by the network to avoid over-learning. The third part of the data, termed the "test" set, consists of the inputs that are required to be transformed into outputs; this set may or may not include the training set and/or the cross-validation set. Proposed neural-network circuitry for on-chip learning would be divided into two distinct networks; one for training and one for validation. Both networks would share the same synaptic weights.

Resource constrained design of artificial neural networks using comparator neural network

NASA Technical Reports Server (NTRS)

Wah, Benjamin W.; Karnik, Tanay S.

1992-01-01

We present a systematic design method executed under resource constraints for automating the design of artificial neural networks using the back error propagation algorithm. Our system aims at finding the best possible configuration for solving the given application with proper tradeoff between the training time and the network complexity. The design of such a system is hampered by three related problems. First, there are infinitely many possible network configurations, each may take an exceedingly long time to train; hence, it is impossible to enumerate and train all of them to completion within fixed time, space, and resource constraints. Second, expert knowledge on predicting good network configurations is heuristic in nature and is application dependent, rendering it difficult to characterize fully in the design process. A learning procedure that refines this knowledge based on examples on training neural networks for various applications is, therefore, essential. Third, the objective of the network to be designed is ill-defined, as it is based on a subjective tradeoff between the training time and the network cost. A design process that proposes alternate configurations under different cost-performance tradeoff is important. We have developed a Design System which schedules the available time, divided into quanta, for testing alternative network configurations. Its goal is to select/generate and test alternative network configurations in each quantum, and find the best network when time is expended. Since time is limited, a dynamic schedule that determines the network configuration to be tested in each quantum is developed. The schedule is based on relative comparison of predicted training times of alternative network configurations using comparator network paradigm. The comparator network has been trained to compare training times for a large variety of traces of TSSE-versus-time collected during back-propagation learning of various applications.

Competitive STDP Learning of Overlapping Spatial Patterns.

PubMed

Krunglevicius, Dalius

2015-08-01

Spike-timing-dependent plasticity (STDP) is a set of Hebbian learning rules firmly based on biological evidence. It has been demonstrated that one of the STDP learning rules is suited for learning spatiotemporal patterns. When multiple neurons are organized in a simple competitive spiking neural network, this network is capable of learning multiple distinct patterns. If patterns overlap significantly (i.e., patterns are mutually inclusive), however, competition would not preclude trained neuron's responding to a new pattern and adjusting synaptic weights accordingly. This letter presents a simple neural network that combines vertical inhibition and Euclidean distance-dependent synaptic strength factor. This approach helps to solve the problem of pattern size-dependent parameter optimality and significantly reduces the probability of a neuron's forgetting an already learned pattern. For demonstration purposes, the network was trained for the first ten letters of the Braille alphabet.

Predicting the survival of diabetes using neural network

NASA Astrophysics Data System (ADS)

Mamuda, Mamman; Sathasivam, Saratha

2017-08-01

Data mining techniques at the present time are used in predicting diseases of health care industries. Neural Network is one among the prevailing method in data mining techniques of an intelligent field for predicting diseases in health care industries. This paper presents a study on the prediction of the survival of diabetes diseases using different learning algorithms from the supervised learning algorithms of neural network. Three learning algorithms are considered in this study: (i) The levenberg-marquardt learning algorithm (ii) The Bayesian regulation learning algorithm and (iii) The scaled conjugate gradient learning algorithm. The network is trained using the Pima Indian Diabetes Dataset with the help of MATLAB R2014(a) software. The performance of each algorithm is further discussed through regression analysis. The prediction accuracy of the best algorithm is further computed to validate the accurate prediction

QUEST: Eliminating Online Supervised Learning for Efficient Classification Algorithms.

PubMed

Zwartjes, Ardjan; Havinga, Paul J M; Smit, Gerard J M; Hurink, Johann L

2016-10-01

In this work, we introduce QUEST (QUantile Estimation after Supervised Training), an adaptive classification algorithm for Wireless Sensor Networks (WSNs) that eliminates the necessity for online supervised learning. Online processing is important for many sensor network applications. Transmitting raw sensor data puts high demands on the battery, reducing network life time. By merely transmitting partial results or classifications based on the sampled data, the amount of traffic on the network can be significantly reduced. Such classifications can be made by learning based algorithms using sampled data. An important issue, however, is the training phase of these learning based algorithms. Training a deployed sensor network requires a lot of communication and an impractical amount of human involvement. QUEST is a hybrid algorithm that combines supervised learning in a controlled environment with unsupervised learning on the location of deployment. Using the SITEX02 dataset, we demonstrate that the presented solution works with a performance penalty of less than 10% in 90% of the tests. Under some circumstances, it even outperforms a network of classifiers completely trained with supervised learning. As a result, the need for on-site supervised learning and communication for training is completely eliminated by our solution.

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.

Path integration of head direction: updating a packet of neural activity at the correct speed using neuronal time constants.

PubMed

Walters, D M; Stringer, S M

2010-07-01

A key question in understanding the neural basis of path integration is how individual, spatially responsive, neurons may self-organize into networks that can, through learning, integrate velocity signals to update a continuous representation of location within an environment. It is of vital importance that this internal representation of position is updated at the correct speed, and in real time, to accurately reflect the motion of the animal. In this article, we present a biologically plausible model of velocity path integration of head direction that can solve this problem using neuronal time constants to effect natural time delays, over which associations can be learned through associative Hebbian learning rules. The model comprises a linked continuous attractor network and competitive network. In simulation, we show that the same model is able to learn two different speeds of rotation when implemented with two different values for the time constant, and without the need to alter any other model parameters. The proposed model could be extended to path integration of place in the environment, and path integration of spatial view.

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.

Time Series Forecasting of Daily Reference Evapotranspiration by Neural Network Ensemble Learning for Irrigation System

NASA Astrophysics Data System (ADS)

Manikumari, N.; Murugappan, A.; Vinodhini, G.

2017-07-01

Time series forecasting has gained remarkable interest of researchers in the last few decades. Neural networks based time series forecasting have been employed in various application areas. Reference Evapotranspiration (ETO) is one of the most important components of the hydrologic cycle and its precise assessment is vital in water balance and crop yield estimation, water resources system design and management. This work aimed at achieving accurate time series forecast of ETO using a combination of neural network approaches. This work was carried out using data collected in the command area of VEERANAM Tank during the period 2004 - 2014 in India. In this work, the Neural Network (NN) models were combined by ensemble learning in order to improve the accuracy for forecasting Daily ETO (for the year 2015). Bagged Neural Network (Bagged-NN) and Boosted Neural Network (Boosted-NN) ensemble learning were employed. It has been proved that Bagged-NN and Boosted-NN ensemble models are better than individual NN models in terms of accuracy. Among the ensemble models, Boosted-NN reduces the forecasting errors compared to Bagged-NN and individual NNs. Regression co-efficient, Mean Absolute Deviation, Mean Absolute Percentage error and Root Mean Square Error also ascertain that Boosted-NN lead to improved ETO forecasting performance.

An investigation of fMRI time series stationarity during motor sequence learning foot tapping tasks.

PubMed

Muhei-aldin, Othman; VanSwearingen, Jessie; Karim, Helmet; Huppert, Theodore; Sparto, Patrick J; Erickson, Kirk I; Sejdić, Ervin

2014-04-30

Understanding complex brain networks using functional magnetic resonance imaging (fMRI) is of great interest to clinical and scientific communities. To utilize advanced analysis methods such as graph theory for these investigations, the stationarity of fMRI time series needs to be understood as it has important implications on the choice of appropriate approaches for the analysis of complex brain networks. In this paper, we investigated the stationarity of fMRI time series acquired from twelve healthy participants while they performed a motor (foot tapping sequence) learning task. Since prior studies have documented that learning is associated with systematic changes in brain activation, a sequence learning task is an optimal paradigm to assess the degree of non-stationarity in fMRI time-series in clinically relevant brain areas. We predicted that brain regions involved in a "learning network" would demonstrate non-stationarity and may violate assumptions associated with some advanced analysis approaches. Six blocks of learning, and six control blocks of a foot tapping sequence were performed in a fixed order. The reverse arrangement test was utilized to investigate the time series stationarity. Our analysis showed some non-stationary signals with a time varying first moment as a major source of non-stationarity. We also demonstrated a decreased number of non-stationarities in the third block as a result of priming and repetition. Most of the current literature does not examine stationarity prior to processing. The implication of our findings is that future investigations analyzing complex brain networks should utilize approaches robust to non-stationarities, as graph-theoretical approaches can be sensitive to non-stationarities present in data. Copyright © 2014 Elsevier B.V. All rights reserved.

Educational Design and Networked Learning: Patterns, Pattern Languages and Design Practice

ERIC Educational Resources Information Center

Goodyear, Peter

2005-01-01

There is a growing demand for advice about effective, time efficient ways of using ICT to support student learning in higher education. This paper uses one such area of activity--networked learning--as a context in which to outline a novel approach to educational design. The paper makes two main contributions. It provides a high level view of the…

Finite time convergent learning law for continuous neural networks.

PubMed

Chairez, Isaac

2014-02-01

This paper addresses the design of a discontinuous finite time convergent learning law for neural networks with continuous dynamics. The neural network was used here to obtain a non-parametric model for uncertain systems described by a set of ordinary differential equations. The source of uncertainties was the presence of some external perturbations and poor knowledge of the nonlinear function describing the system dynamics. A new adaptive algorithm based on discontinuous algorithms was used to adjust the weights of the neural network. The adaptive algorithm was derived by means of a non-standard Lyapunov function that is lower semi-continuous and differentiable in almost the whole space. A compensator term was included in the identifier to reject some specific perturbations using a nonlinear robust algorithm. Two numerical examples demonstrated the improvements achieved by the learning algorithm introduced in this paper compared to classical schemes with continuous learning methods. The first one dealt with a benchmark problem used in the paper to explain how the discontinuous learning law works. The second one used the methane production model to show the benefits in engineering applications of the learning law proposed in this paper. Copyright © 2013 Elsevier Ltd. All rights reserved.

Lifelong learning of human actions with deep neural network self-organization.

PubMed

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

2017-12-01

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

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.

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.

Self Improving Methods for Materials and Process Design

DTIC Science & Technology

1998-08-31

using inductive coupling techniques. The first phase of the work focuses on developing an artificial neural network learning for function approximation...developing an artificial neural network learning algorithm for time-series prediction. The third phase of the work focuses on model selection. We have

Nonparametric Density Estimation Based on Self-Organizing Incremental Neural Network for Large Noisy Data.

PubMed

Nakamura, Yoshihiro; Hasegawa, Osamu

2017-01-01

With the ongoing development and expansion of communication networks and sensors, massive amounts of data are continuously generated in real time from real environments. Beforehand, prediction of a distribution underlying such data is difficult; furthermore, the data include substantial amounts of noise. These factors make it difficult to estimate probability densities. To handle these issues and massive amounts of data, we propose a nonparametric density estimator that rapidly learns data online and has high robustness. Our approach is an extension of both kernel density estimation (KDE) and a self-organizing incremental neural network (SOINN); therefore, we call our approach KDESOINN. An SOINN provides a clustering method that learns about the given data as networks of prototype of data; more specifically, an SOINN can learn the distribution underlying the given data. Using this information, KDESOINN estimates the probability density function. The results of our experiments show that KDESOINN outperforms or achieves performance comparable to the current state-of-the-art approaches in terms of robustness, learning time, and accuracy.

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

The Time Course of Task-Specific Memory Consolidation Effects in Resting State Networks

PubMed Central

Sami, Saber; Robertson, Edwin M.

2014-01-01

Previous studies have reported functionally localized changes in resting-state brain activity following a short period of motor learning, but their relationship with memory consolidation and their dependence on the form of learning is unclear. We investigate these questions with implicit or explicit variants of the serial reaction time task (SRTT). fMRI resting-state functional connectivity was measured in human subjects before the tasks, and 0.1, 0.5, and 6 h after learning. There was significant improvement in procedural skill in both groups, with the group learning under explicit conditions showing stronger initial acquisition, and greater improvement at the 6 h retest. Immediately following acquisition, this group showed enhanced functional connectivity in networks including frontal and cerebellar areas and in the visual cortex. Thirty minutes later, enhanced connectivity was observed between cerebellar nuclei, thalamus, and basal ganglia, whereas at 6 h there was enhanced connectivity in a sensory-motor cortical network. In contrast, immediately after acquisition under implicit conditions, there was increased connectivity in a network including precentral and sensory-motor areas, whereas after 30 min a similar cerebello-thalamo-basal ganglionic network was seen as in explicit learning. Finally, 6 h after implicit learning, we found increased connectivity in medial temporal cortex, but reduction in precentral and sensory-motor areas. Our findings are consistent with predictions that two variants of the SRTT task engage dissociable functional networks, although there are also networks in common. We also show a converging and diverging pattern of flux between prefrontal, sensory-motor, and parietal areas, and subcortical circuits across a 6 h consolidation period. PMID:24623776

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.

Optimal mapping of neural-network learning on message-passing multicomputers

NASA Technical Reports Server (NTRS)

Chu, Lon-Chan; Wah, Benjamin W.

1992-01-01

A minimization of learning-algorithm completion time is sought in the present optimal-mapping study of the learning process in multilayer feed-forward artificial neural networks (ANNs) for message-passing multicomputers. A novel approximation algorithm for mappings of this kind is derived from observations of the dominance of a parallel ANN algorithm over its communication time. Attention is given to both static and dynamic mapping schemes for systems with static and dynamic background workloads, as well as to experimental results obtained for simulated mappings on multicomputers with dynamic background workloads.

Neural network based speech synthesizer: A preliminary report

NASA Technical Reports Server (NTRS)

Villarreal, James A.; Mcintire, Gary

1987-01-01

A neural net based speech synthesis project is discussed. The novelty is that the reproduced speech was extracted from actual voice recordings. In essence, the neural network learns the timing, pitch fluctuations, connectivity between individual sounds, and speaking habits unique to that individual person. The parallel distributed processing network used for this project is the generalized backward propagation network which has been modified to also learn sequences of actions or states given in a particular plan.

Spatiotemporal topology and temporal sequence identification with an adaptive time-delay neural network

NASA Astrophysics Data System (ADS)

Lin, Daw-Tung; Ligomenides, Panos A.; Dayhoff, Judith E.

1993-08-01

Inspired from the time delays that occur in neurobiological signal transmission, we describe an adaptive time delay neural network (ATNN) which is a powerful dynamic learning technique for spatiotemporal pattern transformation and temporal sequence identification. The dynamic properties of this network are formulated through the adaptation of time-delays and synapse weights, which are adjusted on-line based on gradient descent rules according to the evolution of observed inputs and outputs. We have applied the ATNN to examples that possess spatiotemporal complexity, with temporal sequences that are completed by the network. The ATNN is able to be applied to pattern completion. Simulation results show that the ATNN learns the topology of a circular and figure eight trajectories within 500 on-line training iterations, and reproduces the trajectory dynamically with very high accuracy. The ATNN was also trained to model the Fourier series expansion of the sum of different odd harmonics. The resulting network provides more flexibility and efficiency than the TDNN and allows the network to seek optimal values for time-delays as well as optimal synapse weights.

The race to learn: spike timing and STDP can coordinate learning and recall in CA3.

PubMed

Nolan, Christopher R; Wyeth, Gordon; Milford, Michael; Wiles, Janet

2011-06-01

The CA3 region of the hippocampus has long been proposed as an autoassociative network performing pattern completion on known inputs. The dentate gyrus (DG) region is often proposed as a network performing the complementary function of pattern separation. Neural models of pattern completion and separation generally designate explicit learning phases to encode new information and assume an ideal fixed threshold at which to stop learning new patterns and begin recalling known patterns. Memory systems are significantly more complex in practice, with the degree of memory recall depending on context-specific goals. Here, we present our spike-timing separation and completion (STSC) model of the entorhinal cortex (EC), DG, and CA3 network, ascribing to each region a role similar to that in existing models but adding a temporal dimension by using a spiking neural network. Simulation results demonstrate that (a) spike-timing dependent plasticity in the EC-CA3 synapses provides a pattern completion ability without recurrent CA3 connections, (b) the race between activation of CA3 cells via EC-CA3 synapses and activation of the same cells via DG-CA3 synapses distinguishes novel from known inputs, and (c) modulation of the EC-CA3 synapses adjusts the learned versus test input similarity required to evoke a direct CA3 response prior to any DG activity, thereby adjusting the pattern completion threshold. These mechanisms suggest that spike timing can arbitrate between learning and recall based on the novelty of each individual input, ensuring control of the learn-recall decision resides in the same subsystem as the learned memories themselves. The proposed modulatory signal does not override this decision but biases the system toward either learning or recall. The model provides an explanation for empirical observations that a reduction in novelty produces a corresponding reduction in the latency of responses in CA3 and CA1. Copyright © 2010 Wiley-Liss, Inc.

Spiking neural networks for handwritten digit recognition-Supervised learning and network optimization.

PubMed

Kulkarni, Shruti R; Rajendran, Bipin

2018-07-01

We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications. Copyright © 2018 Elsevier Ltd. All rights reserved.

Evaluation of multi-level social learning for sustainable landscapes: perspective of a development initiative in Bergslagen, Sweden.

PubMed

Axelsson, Robert; Angelstam, Per; Myhrman, Lennart; Sädbom, Stefan; Ivarsson, Milis; Elbakidze, Marine; Andersson, Kenneth; Cupa, Petr; Diry, Christian; Doyon, Frederic; Drotz, Marcus K; Hjorth, Arne; Hermansson, Jan Olof; Kullberg, Thomas; Lickers, F Henry; McTaggart, Johanna; Olsson, Anders; Pautov, Yurij; Svensson, Lennart; Törnblom, Johan

2013-03-01

To implement policies about sustainable landscapes and rural development necessitates social learning about states and trends of sustainability indicators, norms that define sustainability, and adaptive multi-level governance. We evaluate the extent to which social learning at multiple governance levels for sustainable landscapes occur in 18 local development initiatives in the network of Sustainable Bergslagen in Sweden. We mapped activities over time, and interviewed key actors in the network about social learning. While activities resulted in exchange of experiences and some local solutions, a major challenge was to secure systematic social learning and make new knowledge explicit at multiple levels. None of the development initiatives used a systematic approach to secure social learning, and sustainability assessments were not made systematically. We discuss how social learning can be improved, and how a learning network of development initiatives could be realized.

Learning Time-Varying Coverage Functions

PubMed Central

Du, Nan; Liang, Yingyu; Balcan, Maria-Florina; Song, Le

2015-01-01

Coverage functions are an important class of discrete functions that capture the law of diminishing returns arising naturally from applications in social network analysis, machine learning, and algorithmic game theory. In this paper, we propose a new problem of learning time-varying coverage functions, and develop a novel parametrization of these functions using random features. Based on the connection between time-varying coverage functions and counting processes, we also propose an efficient parameter learning algorithm based on likelihood maximization, and provide a sample complexity analysis. We applied our algorithm to the influence function estimation problem in information diffusion in social networks, and show that with few assumptions about the diffusion processes, our algorithm is able to estimate influence significantly more accurately than existing approaches on both synthetic and real world data. PMID:25960624

Learning Time-Varying Coverage Functions.

PubMed

Du, Nan; Liang, Yingyu; Balcan, Maria-Florina; Song, Le

2014-12-08

Coverage functions are an important class of discrete functions that capture the law of diminishing returns arising naturally from applications in social network analysis, machine learning, and algorithmic game theory. In this paper, we propose a new problem of learning time-varying coverage functions, and develop a novel parametrization of these functions using random features. Based on the connection between time-varying coverage functions and counting processes, we also propose an efficient parameter learning algorithm based on likelihood maximization, and provide a sample complexity analysis. We applied our algorithm to the influence function estimation problem in information diffusion in social networks, and show that with few assumptions about the diffusion processes, our algorithm is able to estimate influence significantly more accurately than existing approaches on both synthetic and real world data.

A rapid learning and dynamic stepwise updating algorithm for flat neural networks and the application to time-series prediction.

PubMed

Chen, C P; Wan, J Z

1999-01-01

A fast learning algorithm is proposed to find an optimal weights of the flat neural networks (especially, the functional-link network). Although the flat networks are used for nonlinear function approximation, they can be formulated as linear systems. Thus, the weights of the networks can be solved easily using a linear least-square method. This formulation makes it easier to update the weights instantly for both a new added pattern and a new added enhancement node. A dynamic stepwise updating algorithm is proposed to update the weights of the system on-the-fly. The model is tested on several time-series data including an infrared laser data set, a chaotic time-series, a monthly flour price data set, and a nonlinear system identification problem. The simulation results are compared to existing models in which more complex architectures and more costly training are needed. The results indicate that the proposed model is very attractive to real-time processes.

Social Learning Networks: From Data Analytics to Active Sensing

DTIC Science & Technology

2017-10-13

time updating of user models that in turn dictate the learning path of each student . In particular, we have designed , implemented, and evaluated our...decision, unless so designated by other documentation. 9. SPONSORING/MONITORING AGENCY NAME(S) AND ADDRESS (ES) U.S. Army Research Office P.O. Box...social network that exists between students , instructors, and modules of learning. Between 2015 and 2017, we completed a variety of data-driven

Learning and retrieval behavior in recurrent neural networks with pre-synaptic dependent homeostatic plasticity

NASA Astrophysics Data System (ADS)

Mizusaki, Beatriz E. P.; Agnes, Everton J.; Erichsen, Rubem; Brunnet, Leonardo G.

2017-08-01

The plastic character of brain synapses is considered to be one of the foundations for the formation of memories. There are numerous kinds of such phenomenon currently described in the literature, but their role in the development of information pathways in neural networks with recurrent architectures is still not completely clear. In this paper we study the role of an activity-based process, called pre-synaptic dependent homeostatic scaling, in the organization of networks that yield precise-timed spiking patterns. It encodes spatio-temporal information in the synaptic weights as it associates a learned input with a specific response. We introduce a correlation measure to evaluate the precision of the spiking patterns and explore the effects of different inhibitory interactions and learning parameters. We find that large learning periods are important in order to improve the network learning capacity and discuss this ability in the presence of distinct inhibitory currents.

Learning and optimization with cascaded VLSI neural network building-block chips

NASA Technical Reports Server (NTRS)

Duong, T.; Eberhardt, S. P.; Tran, M.; Daud, T.; Thakoor, A. P.

1992-01-01

To demonstrate the versatility of the building-block approach, two neural network applications were implemented on cascaded analog VLSI chips. Weights were implemented using 7-b multiplying digital-to-analog converter (MDAC) synapse circuits, with 31 x 32 and 32 x 32 synapses per chip. A novel learning algorithm compatible with analog VLSI was applied to the two-input parity problem. The algorithm combines dynamically evolving architecture with limited gradient-descent backpropagation for efficient and versatile supervised learning. To implement the learning algorithm in hardware, synapse circuits were paralleled for additional quantization levels. The hardware-in-the-loop learning system allocated 2-5 hidden neurons for parity problems. Also, a 7 x 7 assignment problem was mapped onto a cascaded 64-neuron fully connected feedback network. In 100 randomly selected problems, the network found optimal or good solutions in most cases, with settling times in the range of 7-100 microseconds.

Deep learning on temporal-spectral data for anomaly detection

NASA Astrophysics Data System (ADS)

Ma, King; Leung, Henry; Jalilian, Ehsan; Huang, Daniel

2017-05-01

Detecting anomalies is important for continuous monitoring of sensor systems. One significant challenge is to use sensor data and autonomously detect changes that cause different conditions to occur. Using deep learning methods, we are able to monitor and detect changes as a result of some disturbance in the system. We utilize deep neural networks for sequence analysis of time series. We use a multi-step method for anomaly detection. We train the network to learn spectral and temporal features from the acoustic time series. We test our method using fiber-optic acoustic data from a pipeline.

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.

LDCM Ground System. Network Lesson Learned

NASA Technical Reports Server (NTRS)

Gal-Edd, Jonathan

2010-01-01

This slide presentation reviews the Landsat Data Continuity Mission (LDCM) and the lessons learned in implementing the network that was assembled to allow for the acquisition, archiving and distribution of the data from the Landsat mission. The objective of the LDCM is to continue the acquisition, archiving, and distribution of moderate-resolution multispectral imagery affording global, synoptic, and repetitive coverage of the earth's land surface at a scale where natural and human-induced changes can be detected, differentiated, characterized, and monitored over time. It includes a review of the ground network, including a block diagram of the ground network elements (GNE) and a review of the RF design and testing. Also included is a listing of the lessons learned.

How synapses can enhance sensibility of a neural network

NASA Astrophysics Data System (ADS)

Protachevicz, P. R.; Borges, F. S.; Iarosz, K. C.; Caldas, I. L.; Baptista, M. S.; Viana, R. L.; Lameu, E. L.; Macau, E. E. N.; Batista, A. M.

2018-02-01

In this work, we study the dynamic range in a neural network modelled by cellular automaton. We consider deterministic and non-deterministic rules to simulate electrical and chemical synapses. Chemical synapses have an intrinsic time-delay and are susceptible to parameter variations guided by learning Hebbian rules of behaviour. The learning rules are related to neuroplasticity that describes change to the neural connections in the brain. Our results show that chemical synapses can abruptly enhance sensibility of the neural network, a manifestation that can become even more predominant if learning rules of evolution are applied to the chemical synapses.

A recurrent neural network for classification of unevenly sampled variable stars

NASA Astrophysics Data System (ADS)

Naul, Brett; Bloom, Joshua S.; Pérez, Fernando; van der Walt, Stéfan

2018-02-01

Astronomical surveys of celestial sources produce streams of noisy time series measuring flux versus time (`light curves'). Unlike in many other physical domains, however, large (and source-specific) temporal gaps in data arise naturally due to intranight cadence choices as well as diurnal and seasonal constraints1-5. With nightly observations of millions of variable stars and transients from upcoming surveys4,6, efficient and accurate discovery and classification techniques on noisy, irregularly sampled data must be employed with minimal human-in-the-loop involvement. Machine learning for inference tasks on such data traditionally requires the laborious hand-coding of domain-specific numerical summaries of raw data (`features')7. Here, we present a novel unsupervised autoencoding recurrent neural network8 that makes explicit use of sampling times and known heteroskedastic noise properties. When trained on optical variable star catalogues, this network produces supervised classification models that rival other best-in-class approaches. We find that autoencoded features learned in one time-domain survey perform nearly as well when applied to another survey. These networks can continue to learn from new unlabelled observations and may be used in other unsupervised tasks, such as forecasting and anomaly detection.

Replicating receptive fields of simple and complex cells in primary visual cortex in a neuronal network model with temporal and population sparseness and reliability.

PubMed

Tanaka, Takuma; Aoyagi, Toshio; Kaneko, Takeshi

2012-10-01

We propose a new principle for replicating receptive field properties of neurons in the primary visual cortex. We derive a learning rule for a feedforward network, which maintains a low firing rate for the output neurons (resulting in temporal sparseness) and allows only a small subset of the neurons in the network to fire at any given time (resulting in population sparseness). Our learning rule also sets the firing rates of the output neurons at each time step to near-maximum or near-minimum levels, resulting in neuronal reliability. The learning rule is simple enough to be written in spatially and temporally local forms. After the learning stage is performed using input image patches of natural scenes, output neurons in the model network are found to exhibit simple-cell-like receptive field properties. When the output of these simple-cell-like neurons are input to another model layer using the same learning rule, the second-layer output neurons after learning become less sensitive to the phase of gratings than the simple-cell-like input neurons. In particular, some of the second-layer output neurons become completely phase invariant, owing to the convergence of the connections from first-layer neurons with similar orientation selectivity to second-layer neurons in the model network. We examine the parameter dependencies of the receptive field properties of the model neurons after learning and discuss their biological implications. We also show that the localized learning rule is consistent with experimental results concerning neuronal plasticity and can replicate the receptive fields of simple and complex cells.

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

PubMed

Kim, Lok-Won

2018-05-01

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

Coevolutionary, coexisting learning and teaching agents model for prisoner’s dilemma games enhancing cooperation with assortative heterogeneous networks

NASA Astrophysics Data System (ADS)

Tanimoto, Jun

2013-07-01

Unlike other natural network systems, assortativity can be observed in most human social networks, although it has been reported that a social dilemma situation represented by the prisoner’s dilemma favors dissortativity to enhance cooperation. We established a new coevolutionary model for both agents’ strategy and network topology, where teaching and learning agents coexist. Remarkably, this model enables agents’ enhancing cooperation more than a learners-only model on a time-frozen scale-free network and produces an underlying assortative network with a fair degree of power-law distribution. The model may imply how and why assortative networks are adaptive in human society.

Memristive neural network for on-line learning and tracking with brain-inspired spike timing dependent plasticity.

PubMed

Pedretti, G; Milo, V; Ambrogio, S; Carboni, R; Bianchi, S; Calderoni, A; Ramaswamy, N; Spinelli, A S; Ielmini, D

2017-07-13

Brain-inspired computation can revolutionize information technology by introducing machines capable of recognizing patterns (images, speech, video) and interacting with the external world in a cognitive, humanlike way. Achieving this goal requires first to gain a detailed understanding of the brain operation, and second to identify a scalable microelectronic technology capable of reproducing some of the inherent functions of the human brain, such as the high synaptic connectivity (~10 4 ) and the peculiar time-dependent synaptic plasticity. Here we demonstrate unsupervised learning and tracking in a spiking neural network with memristive synapses, where synaptic weights are updated via brain-inspired spike timing dependent plasticity (STDP). The synaptic conductance is updated by the local time-dependent superposition of pre- and post-synaptic spikes within a hybrid one-transistor/one-resistor (1T1R) memristive synapse. Only 2 synaptic states, namely the low resistance state (LRS) and the high resistance state (HRS), are sufficient to learn and recognize patterns. Unsupervised learning of a static pattern and tracking of a dynamic pattern of up to 4 × 4 pixels are demonstrated, paving the way for intelligent hardware technology with up-scaled memristive neural networks.

Centralized Networks to Generate Human Body Motions

PubMed Central

Vakulenko, Sergei; Radulescu, Ovidiu; Morozov, Ivan

2017-01-01

We consider continuous-time recurrent neural networks as dynamical models for the simulation of human body motions. These networks consist of a few centers and many satellites connected to them. The centers evolve in time as periodical oscillators with different frequencies. The center states define the satellite neurons’ states by a radial basis function (RBF) network. To simulate different motions, we adjust the parameters of the RBF networks. Our network includes a switching module that allows for turning from one motion to another. Simulations show that this model allows us to simulate complicated motions consisting of many different dynamical primitives. We also use the model for learning human body motion from markers’ trajectories. We find that center frequencies can be learned from a small number of markers and can be transferred to other markers, such that our technique seems to be capable of correcting for missing information resulting from sparse control marker settings. PMID:29240694

Centralized Networks to Generate Human Body Motions.

PubMed

Vakulenko, Sergei; Radulescu, Ovidiu; Morozov, Ivan; Weber, Andres

2017-12-14

We consider continuous-time recurrent neural networks as dynamical models for the simulation of human body motions. These networks consist of a few centers and many satellites connected to them. The centers evolve in time as periodical oscillators with different frequencies. The center states define the satellite neurons' states by a radial basis function (RBF) network. To simulate different motions, we adjust the parameters of the RBF networks. Our network includes a switching module that allows for turning from one motion to another. Simulations show that this model allows us to simulate complicated motions consisting of many different dynamical primitives. We also use the model for learning human body motion from markers' trajectories. We find that center frequencies can be learned from a small number of markers and can be transferred to other markers, such that our technique seems to be capable of correcting for missing information resulting from sparse control marker settings.

Efficient Training of Supervised Spiking Neural Network via Accurate Synaptic-Efficiency Adjustment Method.

PubMed

Xie, Xiurui; Qu, Hong; Yi, Zhang; Kurths, Jurgen

2017-06-01

The spiking neural network (SNN) is the third generation of neural networks and performs remarkably well in cognitive tasks, such as pattern recognition. The temporal neural encode mechanism found in biological hippocampus enables SNN to possess more powerful computation capability than networks with other encoding schemes. However, this temporal encoding approach requires neurons to process information serially on time, which reduces learning efficiency significantly. To keep the powerful computation capability of the temporal encoding mechanism and to overcome its low efficiency in the training of SNNs, a new training algorithm, the accurate synaptic-efficiency adjustment method is proposed in this paper. Inspired by the selective attention mechanism of the primate visual system, our algorithm selects only the target spike time as attention areas, and ignores voltage states of the untarget ones, resulting in a significant reduction of training time. Besides, our algorithm employs a cost function based on the voltage difference between the potential of the output neuron and the firing threshold of the SNN, instead of the traditional precise firing time distance. A normalized spike-timing-dependent-plasticity learning window is applied to assigning this error to different synapses for instructing their training. Comprehensive simulations are conducted to investigate the learning properties of our algorithm, with input neurons emitting both single spike and multiple spikes. Simulation results indicate that our algorithm possesses higher learning performance than the existing other methods and achieves the state-of-the-art efficiency in the training of SNN.

Self-organized neural maps of human protein sequences.

PubMed Central

Ferrán, E. A.; Pflugfelder, B.; Ferrara, P.

1994-01-01

We have recently described a method based on artificial neural networks to cluster protein sequences into families. The network was trained with Kohonen's unsupervised learning algorithm using, as inputs, the matrix patterns derived from the dipeptide composition of the proteins. We present here a large-scale application of that method to classify the 1,758 human protein sequences stored in the SwissProt database (release 19.0), whose lengths are greater than 50 amino acids. In the final 2-dimensional topologically ordered map of 15 x 15 neurons, proteins belonging to known families were associated with the same neuron or with neighboring ones. Also, as an attempt to reduce the time-consuming learning procedure, we compared 2 learning protocols: one of 500 epochs (100 SUN CPU-hours [CPU-h]), and another one of 30 epochs (6.7 CPU-h). A further reduction of learning-computing time, by a factor of about 3.3, with similar protein clustering results, was achieved using a matrix of 11 x 11 components to represent the sequences. Although network training is time consuming, the classification of a new protein in the final ordered map is very fast (14.6 CPU-seconds). We also show a comparison between the artificial neural network approach and conventional methods of biosequence analysis. PMID:8019421

Neural learning of constrained nonlinear transformations

NASA Technical Reports Server (NTRS)

Barhen, Jacob; Gulati, Sandeep; Zak, Michail

1989-01-01

Two issues that are fundamental to developing autonomous intelligent robots, namely, rudimentary learning capability and dexterous manipulation, are examined. A powerful neural learning formalism is introduced for addressing a large class of nonlinear mapping problems, including redundant manipulator inverse kinematics, commonly encountered during the design of real-time adaptive control mechanisms. Artificial neural networks with terminal attractor dynamics are used. The rapid network convergence resulting from the infinite local stability of these attractors allows the development of fast neural learning algorithms. Approaches to manipulator inverse kinematics are reviewed, the neurodynamics model is discussed, and the neural learning algorithm is presented.

Agent-based real-time signal coordination in congested networks.

DOT National Transportation Integrated Search

2014-01-01

This study is the continuation of a previous NEXTRANS study on agent-based reinforcement : learning methods for signal coordination in congested networks. In the previous study, the : formulation of a real-time agent-based traffic signal control in o...

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.

Unsupervised learning of digit recognition using spike-timing-dependent plasticity

PubMed Central

Diehl, Peter U.; Cook, Matthew

2015-01-01

In order to understand how the mammalian neocortex is performing computations, two things are necessary; we need to have a good understanding of the available neuronal processing units and mechanisms, and we need to gain a better understanding of how those mechanisms are combined to build functioning systems. Therefore, in recent years there is an increasing interest in how spiking neural networks (SNN) can be used to perform complex computations or solve pattern recognition tasks. However, it remains a challenging task to design SNNs which use biologically plausible mechanisms (especially for learning new patterns), since most such SNN architectures rely on training in a rate-based network and subsequent conversion to a SNN. We present a SNN for digit recognition which is based on mechanisms with increased biological plausibility, i.e., conductance-based instead of current-based synapses, spike-timing-dependent plasticity with time-dependent weight change, lateral inhibition, and an adaptive spiking threshold. Unlike most other systems, we do not use a teaching signal and do not present any class labels to the network. Using this unsupervised learning scheme, our architecture achieves 95% accuracy on the MNIST benchmark, which is better than previous SNN implementations without supervision. The fact that we used no domain-specific knowledge points toward the general applicability of our network design. Also, the performance of our network scales well with the number of neurons used and shows similar performance for four different learning rules, indicating robustness of the full combination of mechanisms, which suggests applicability in heterogeneous biological neural networks. PMID:26941637

Deep neural networks for direct, featureless learning through observation: The case of two-dimensional spin models

NASA Astrophysics Data System (ADS)

Mills, Kyle; Tamblyn, Isaac

2018-03-01

We demonstrate the capability of a convolutional deep neural network in predicting the nearest-neighbor energy of the 4 ×4 Ising model. Using its success at this task, we motivate the study of the larger 8 ×8 Ising model, showing that the deep neural network can learn the nearest-neighbor Ising Hamiltonian after only seeing a vanishingly small fraction of configuration space. Additionally, we show that the neural network has learned both the energy and magnetization operators with sufficient accuracy to replicate the low-temperature Ising phase transition. We then demonstrate the ability of the neural network to learn other spin models, teaching the convolutional deep neural network to accurately predict the long-range interaction of a screened Coulomb Hamiltonian, a sinusoidally attenuated screened Coulomb Hamiltonian, and a modified Potts model Hamiltonian. In the case of the long-range interaction, we demonstrate the ability of the neural network to recover the phase transition with equivalent accuracy to the numerically exact method. Furthermore, in the case of the long-range interaction, the benefits of the neural network become apparent; it is able to make predictions with a high degree of accuracy, and do so 1600 times faster than a CUDA-optimized exact calculation. Additionally, we demonstrate how the neural network succeeds at these tasks by looking at the weights learned in a simplified demonstration.

The Collaboratory Notebook: A Networked Knowledge-Building Environment for Project Learning.

ERIC Educational Resources Information Center

O'Neill, D. Kevin; Gomez, Louis M.

The Collaboratory Notebook, developed as part of the Learning Through Collaborative Visualization Project (CoVis), is a networked, multimedia knowledge-building environment which has been designed to help students, teachers and scientists share inquiry over the boundaries of time and space. CoVis is an attempt to change the way that science is…

Leveraging the Potential of Personal Learning Networks for Teacher Professional Development

ERIC Educational Resources Information Center

Maloney, Katherine J.

2016-01-01

In times of exponential change, high quality, cost-effective teacher professional development is an urgent need that personal learning networks (PLNs) promise to address. The purpose of the qualitative case study was to (a) explore, understand, and describe how PreK-12 educators, who are members of The Educator's PLN and Classroom 2.0 communities,…

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

Naming Game with Multiple Hearers

NASA Astrophysics Data System (ADS)

Li, Bing; Chen, Guanrong; Chow, Tommy W. S.

2013-05-01

A new model called Naming Game with Multiple Hearers (NGMH) is proposed in this paper. A naming game over a population of individuals aims to reach consensus on the name of an object through pair-wise local interactions among all the individuals. The proposed NGMH model describes the learning process of a new word, in a population with one speaker and multiple hearers, at each interaction towards convergence. The characteristics of NGMH are examined on three types of network topologies, namely ER random-graph network, WS small-world network, and BA scale-free network. Comparative analysis on the convergence time is performed, revealing that the topology with a larger average (node) degree can reach consensus faster than the others over the same population. It is found that, for a homogeneous network, the average degree is the limiting value of the number of hearers, which reduces the individual ability of learning new words, consequently decreasing the convergence time; for a scale-free network, this limiting value is the deviation of the average degree. It is also found that a network with a larger clustering coefficient takes longer time to converge; especially a small-word network with smallest rewiring possibility takes longest time to reach convergence. As more new nodes are being added to scale-free networks with different degree distributions, their convergence time appears to be robust against the network-size variation. Most new findings reported in this paper are different from that of the single-speaker/single-hearer naming games documented in the literature.

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.

Active learning of cortical connectivity from two-photon imaging data.

PubMed

Bertrán, Martín A; Martínez, Natalia L; Wang, Ye; Dunson, David; Sapiro, Guillermo; Ringach, Dario

2018-01-01

Understanding how groups of neurons interact within a network is a fundamental question in system neuroscience. Instead of passively observing the ongoing activity of a network, we can typically perturb its activity, either by external sensory stimulation or directly via techniques such as two-photon optogenetics. A natural question is how to use such perturbations to identify the connectivity of the network efficiently. Here we introduce a method to infer sparse connectivity graphs from in-vivo, two-photon imaging of population activity in response to external stimuli. A novel aspect of the work is the introduction of a recommended distribution, incrementally learned from the data, to optimally refine the inferred network. Unlike existing system identification techniques, this "active learning" method automatically focuses its attention on key undiscovered areas of the network, instead of targeting global uncertainty indicators like parameter variance. We show how active learning leads to faster inference while, at the same time, provides confidence intervals for the network parameters. We present simulations on artificial small-world networks to validate the methods and apply the method to real data. Analysis of frequency of motifs recovered show that cortical networks are consistent with a small-world topology model.

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.

Incremental Support Vector Machine Framework for Visual Sensor Networks

NASA Astrophysics Data System (ADS)

Awad, Mariette; Jiang, Xianhua; Motai, Yuichi

2006-12-01

Motivated by the emerging requirements of surveillance networks, we present in this paper an incremental multiclassification support vector machine (SVM) technique as a new framework for action classification based on real-time multivideo collected by homogeneous sites. The technique is based on an adaptation of least square SVM (LS-SVM) formulation but extends beyond the static image-based learning of current SVM methodologies. In applying the technique, an initial supervised offline learning phase is followed by a visual behavior data acquisition and an online learning phase during which the cluster head performs an ensemble of model aggregations based on the sensor nodes inputs. The cluster head then selectively switches on designated sensor nodes for future incremental learning. Combining sensor data offers an improvement over single camera sensing especially when the latter has an occluded view of the target object. The optimization involved alleviates the burdens of power consumption and communication bandwidth requirements. The resulting misclassification error rate, the iterative error reduction rate of the proposed incremental learning, and the decision fusion technique prove its validity when applied to visual sensor networks. Furthermore, the enabled online learning allows an adaptive domain knowledge insertion and offers the advantage of reducing both the model training time and the information storage requirements of the overall system which makes it even more attractive for distributed sensor networks communication.

Socioscape: Real-Time Analysis of Dynamic Heterogeneous Networks In Complex Socio-Cultural Systems

DTIC Science & Technology

2015-10-22

Cluster Mixed-Membership Blockmodel for Time-Evolving Networks, Proceedings of the 14th International Conference on Artifical Intelligence and...Learning With Simultaneous Orthogonal Matching Pursuit, Proceedings of the 13th International Conference on Artifical Intelligence and Statistics

SuperSpike: Supervised Learning in Multilayer Spiking Neural Networks.

PubMed

Zenke, Friedemann; Ganguli, Surya

2018-06-01

A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in silico. Here we revisit the problem of supervised learning in temporally coding multilayer spiking neural networks. First, by using a surrogate gradient approach, we derive SuperSpike, a nonlinear voltage-based three-factor learning rule capable of training multilayer networks of deterministic integrate-and-fire neurons to perform nonlinear computations on spatiotemporal spike patterns. Second, inspired by recent results on feedback alignment, we compare the performance of our learning rule under different credit assignment strategies for propagating output errors to hidden units. Specifically, we test uniform, symmetric, and random feedback, finding that simpler tasks can be solved with any type of feedback, while more complex tasks require symmetric feedback. In summary, our results open the door to obtaining a better scientific understanding of learning and computation in spiking neural networks by advancing our ability to train them to solve nonlinear problems involving transformations between different spatiotemporal spike time patterns.

Modification Of Learning Rate With Lvq Model Improvement In Learning Backpropagation

NASA Astrophysics Data System (ADS)

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

2017-12-01

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

Second Language Word Learning through Repetition and Imitation: Functional Networks as a Function of Learning Phase and Language Distance.

PubMed

Ghazi-Saidi, Ladan; Ansaldo, Ana Ines

2017-01-01

Introduction and Aim : Repetition and imitation are among the oldest second language (L2) teaching approaches and are frequently used in the context of L2 learning and language therapy, despite some heavy criticism. Current neuroimaging techniques allow the neural mechanisms underlying repetition and imitation to be examined. This fMRI study examines the influence of verbal repetition and imitation on network configuration. Integration changes within and between the cognitive control and language networks were studied, in a pair of linguistically close languages (Spanish and French), and compared to our previous work on a distant language pair (Ghazi-Saidi et al., 2013). Methods : Twelve healthy native Spanish-speaking (L1) adults, and 12 healthy native Persian-speaking adults learned 130 new French (L2) words, through a computerized audiovisual repetition and imitation program. The program presented colored photos of objects. Participants were instructed to look at each photo and pronounce its name as closely as possible to the native template (imitate). Repetition was encouraged as many times as necessary to learn the object's name; phonological cues were provided if necessary. Participants practiced for 15 min, over 30 days, and were tested while naming the same items during fMRI scanning, at week 1 (shallow learning phase) and week 4 (consolidation phase) of training. To compare this set of data with our previous work on Persian speakers, a similar data analysis plan including accuracy rates (AR), response times (RT), and functional integration values for the language and cognitive control network at each measure point was included, with further L1-L2 direct comparisons across the two populations. Results and Discussion : The evidence shows that learning L2 words through repetition induces neuroplasticity at the network level. Specifically, L2 word learners showed increased network integration after 3 weeks of training, with both close and distant language pairs. Moreover, higher network integration was observed in the learners with the close language pair, suggesting that repetition effects on network configuration vary as a function of task complexity.

A regularization approach to continuous learning with an application to financial derivatives pricing.

PubMed

Ormoneit, D

1999-12-01

We consider the training of neural networks in cases where the nonlinear relationship of interest gradually changes over time. One possibility to deal with this problem is by regularization where a variation penalty is added to the usual mean squared error criterion. To learn the regularized network weights we suggest the Iterative Extended Kalman Filter (IEKF) as a learning rule, which may be derived from a Bayesian perspective on the regularization problem. A primary application of our algorithm is in financial derivatives pricing, where neural networks may be used to model the dependency of the derivatives' price on one or several underlying assets. After giving a brief introduction to the problem of derivatives pricing we present experiments with German stock index options data showing that a regularized neural network trained with the IEKF outperforms several benchmark models and alternative learning procedures. In particular, the performance may be greatly improved using a newly designed neural network architecture that accounts for no-arbitrage pricing restrictions.

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

Dynamical genetic programming in XCSF.

PubMed

Preen, Richard J; Bull, Larry

2013-01-01

A number of representation schemes have been presented for use within learning classifier systems, ranging from binary encodings to artificial neural networks. This paper presents results from an investigation into using a temporally dynamic symbolic representation within the XCSF learning classifier system. In particular, dynamical arithmetic networks are used to represent the traditional condition-action production system rules to solve continuous-valued reinforcement learning problems and to perform symbolic regression, finding competitive performance with traditional genetic programming on a number of composite polynomial tasks. In addition, the network outputs are later repeatedly sampled at varying temporal intervals to perform multistep-ahead predictions of a financial time series.

Coevolution of strategy-selection time scale and cooperation in spatial prisoner's dilemma game

NASA Astrophysics Data System (ADS)

Rong, Zhihai; Wu, Zhi-Xi; Chen, Guanrong

2013-06-01

In this paper, we investigate a networked prisoner's dilemma game where individuals' strategy-selection time scale evolves based on their historical learning information. We show that the more times the current strategy of an individual is learnt by his neighbors, the longer time he will stick on the successful behavior by adaptively adjusting the lifetime of the adopted strategy. Through characterizing the extent of success of the individuals with normalized payoffs, we show that properly using the learned information can form a positive feedback mechanism between cooperative behavior and its lifetime, which can boost cooperation on square lattices and scale-free networks.

RM-SORN: a reward-modulated self-organizing recurrent neural network.

PubMed

Aswolinskiy, Witali; Pipa, Gordon

2015-01-01

Neural plasticity plays an important role in learning and memory. Reward-modulation of plasticity offers an explanation for the ability of the brain to adapt its neural activity to achieve a rewarded goal. Here, we define a neural network model that learns through the interaction of Intrinsic Plasticity (IP) and reward-modulated Spike-Timing-Dependent Plasticity (STDP). IP enables the network to explore possible output sequences and STDP, modulated by reward, reinforces the creation of the rewarded output sequences. The model is tested on tasks for prediction, recall, non-linear computation, pattern recognition, and sequence generation. It achieves performance comparable to networks trained with supervised learning, while using simple, biologically motivated plasticity rules, and rewarding strategies. The results confirm the importance of investigating the interaction of several plasticity rules in the context of reward-modulated learning and whether reward-modulated self-organization can explain the amazing capabilities of the brain.

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

Evaluation of multilayer perceptron algorithms for an analysis of network flow data

NASA Astrophysics Data System (ADS)

Bieniasz, Jedrzej; Rawski, Mariusz; Skowron, Krzysztof; Trzepiński, Mateusz

2016-09-01

The volume of exchanged information through IP networks is larger than ever and still growing. It creates a space for both benign and malicious activities. The second one raises awareness on security network devices, as well as network infrastructure and a system as a whole. One of the basic tools to prevent cyber attacks is Network Instrusion Detection System (NIDS). NIDS could be realized as a signature-based detector or an anomaly-based one. In the last few years the emphasis has been placed on the latter type, because of the possibility of applying smart and intelligent solutions. An ideal NIDS of next generation should be composed of self-learning algorithms that could react on known and unknown malicious network activities respectively. In this paper we evaluated a machine learning approach for detection of anomalies in IP network data represented as NetFlow records. We considered Multilayer Perceptron (MLP) as the classifier and we used two types of learning algorithms - Backpropagation (BP) and Particle Swarm Optimization (PSO). This paper includes a comprehensive survey on determining the most optimal MLP learning algorithm for the classification problem in application to network flow data. The performance, training time and convergence of BP and PSO methods were compared. The results show that PSO algorithm implemented by the authors outperformed other solutions if accuracy of classifications is considered. The major disadvantage of PSO is training time, which could be not acceptable for larger data sets or in real network applications. At the end we compared some key findings with the results from the other papers to show that in all cases results from this study outperformed them.

Time-oriented hierarchical method for computation of principal components using subspace learning algorithm.

PubMed

Jankovic, Marko; Ogawa, Hidemitsu

2004-10-01

Principal Component Analysis (PCA) and Principal Subspace Analysis (PSA) are classic techniques in statistical data analysis, feature extraction and data compression. Given a set of multivariate measurements, PCA and PSA provide a smaller set of "basis vectors" with less redundancy, and a subspace spanned by them, respectively. Artificial neurons and neural networks have been shown to perform PSA and PCA when gradient ascent (descent) learning rules are used, which is related to the constrained maximization (minimization) of statistical objective functions. Due to their low complexity, such algorithms and their implementation in neural networks are potentially useful in cases of tracking slow changes of correlations in the input data or in updating eigenvectors with new samples. In this paper we propose PCA learning algorithm that is fully homogeneous with respect to neurons. The algorithm is obtained by modification of one of the most famous PSA learning algorithms--Subspace Learning Algorithm (SLA). Modification of the algorithm is based on Time-Oriented Hierarchical Method (TOHM). The method uses two distinct time scales. On a faster time scale PSA algorithm is responsible for the "behavior" of all output neurons. On a slower scale, output neurons will compete for fulfillment of their "own interests". On this scale, basis vectors in the principal subspace are rotated toward the principal eigenvectors. At the end of the paper it will be briefly analyzed how (or why) time-oriented hierarchical method can be used for transformation of any of the existing neural network PSA method, into PCA method.

Real-time individualized training vectors for experiential learning.

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

Willis, Matt; Tucker, Eilish Marie; Raybourn, Elaine Marie

2011-01-01

Military training utilizing serious games or virtual worlds potentially generate data that can be mined to better understand how trainees learn in experiential exercises. Few data mining approaches for deployed military training games exist. Opportunities exist to collect and analyze these data, as well as to construct a full-history learner model. Outcomes discussed in the present document include results from a quasi-experimental research study on military game-based experiential learning, the deployment of an online game for training evidence collection, and results from a proof-of-concept pilot study on the development of individualized training vectors. This Lab Directed Research & Development (LDRD)more » project leveraged products within projects, such as Titan (Network Grand Challenge), Real-Time Feedback and Evaluation System, (America's Army Adaptive Thinking and Leadership, DARWARS Ambush! NK), and Dynamic Bayesian Networks to investigate whether machine learning capabilities could perform real-time, in-game similarity vectors of learner performance, toward adaptation of content delivery, and quantitative measurement of experiential learning.« less

A Social Learning Management System Supporting Feedback for Incorrect Answers Based on Social Network Services

ERIC Educational Resources Information Center

Son, Jiseong; Kim, Jeong-Dong; Na, Hong-Seok; Baik, Doo-Kwon

2016-01-01

In this research, we propose a Social Learning Management System (SLMS) enabling real-time and reliable feedback for incorrect answers by learners using a social network service (SNS). The proposed system increases the accuracy of learners' assessment results by using a confidence scale and a variety of social feedback that is created and shared…

Adaptive enhancement of learning protocol in hippocampal cultured networks grown on multielectrode arrays

PubMed Central

Pimashkin, Alexey; Gladkov, Arseniy; Mukhina, Irina; Kazantsev, Victor

2013-01-01

Learning in neuronal networks can be investigated using dissociated cultures on multielectrode arrays supplied with appropriate closed-loop stimulation. It was shown in previous studies that weakly respondent neurons on the electrodes can be trained to increase their evoked spiking rate within a predefined time window after the stimulus. Such neurons can be associated with weak synaptic connections in nearby culture network. The stimulation leads to the increase in the connectivity and in the response. However, it was not possible to perform the learning protocol for the neurons on electrodes with relatively strong synaptic inputs and responding at higher rates. We proposed an adaptive closed-loop stimulation protocol capable to achieve learning even for the highly respondent electrodes. It means that the culture network can reorganize appropriately its synaptic connectivity to generate a desired response. We introduced an adaptive reinforcement condition accounting for the response variability in control stimulation. It significantly enhanced the learning protocol to a large number of responding electrodes independently on its base response level. We also found that learning effect preserved after 4–6 h after training. PMID:23745105

Learning and coding in biological neural networks

NASA Astrophysics Data System (ADS)

Fiete, Ila Rani

How can large groups of neurons that locally modify their activities learn to collectively perform a desired task? Do studies of learning in small networks tell us anything about learning in the fantastically large collection of neurons that make up a vertebrate brain? What factors do neurons optimize by encoding sensory inputs or motor commands in the way they do? In this thesis I present a collection of four theoretical works: each of the projects was motivated by specific constraints and complexities of biological neural networks, as revealed by experimental studies; together, they aim to partially address some of the central questions of neuroscience posed above. We first study the role of sparse neural activity, as seen in the coding of sequential commands in a premotor area responsible for birdsong. We show that the sparse coding of temporal sequences in the songbird brain can, in a network where the feedforward plastic weights must translate the sparse sequential code into a time-varying muscle code, facilitate learning by minimizing synaptic interference. Next, we propose a biologically plausible synaptic plasticity rule that can perform goal-directed learning in recurrent networks of voltage-based spiking neurons that interact through conductances. Learning is based on the correlation of noisy local activity with a global reward signal; we prove that this rule performs stochastic gradient ascent on the reward. Thus, if the reward signal quantifies network performance on some desired task, the plasticity rule provably drives goal-directed learning in the network. To assess the convergence properties of the learning rule, we compare it with a known example of learning in the brain. Song-learning in finches is a clear example of a learned behavior, with detailed available neurophysiological data. With our learning rule, we train an anatomically accurate model birdsong network that drives a sound source to mimic an actual zebrafinch song. Simulation and theoretical results on the scalability of this rule show that learning with stochastic gradient ascent may be adequately fast to explain learning in the bird. Finally, we address the more general issue of the scalability of stochastic gradient learning on quadratic cost surfaces in linear systems, as a function of system size and task characteristics, by deriving analytical expressions for the learning curves.

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.

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.

Automatic recognition of holistic functional brain networks using iteratively optimized convolutional neural networks (IO-CNN) with weak label initialization.

PubMed

Zhao, Yu; Ge, Fangfei; Liu, Tianming

2018-07-01

fMRI data decomposition techniques have advanced significantly from shallow models such as Independent Component Analysis (ICA) and Sparse Coding and Dictionary Learning (SCDL) to deep learning models such Deep Belief Networks (DBN) and Convolutional Autoencoder (DCAE). However, interpretations of those decomposed networks are still open questions due to the lack of functional brain atlases, no correspondence across decomposed or reconstructed networks across different subjects, and significant individual variabilities. Recent studies showed that deep learning, especially deep convolutional neural networks (CNN), has extraordinary ability of accommodating spatial object patterns, e.g., our recent works using 3D CNN for fMRI-derived network classifications achieved high accuracy with a remarkable tolerance for mistakenly labelled training brain networks. However, the training data preparation is one of the biggest obstacles in these supervised deep learning models for functional brain network map recognitions, since manual labelling requires tedious and time-consuming labours which will sometimes even introduce label mistakes. Especially for mapping functional networks in large scale datasets such as hundreds of thousands of brain networks used in this paper, the manual labelling method will become almost infeasible. In response, in this work, we tackled both the network recognition and training data labelling tasks by proposing a new iteratively optimized deep learning CNN (IO-CNN) framework with an automatic weak label initialization, which enables the functional brain networks recognition task to a fully automatic large-scale classification procedure. Our extensive experiments based on ABIDE-II 1099 brains' fMRI data showed the great promise of our IO-CNN framework. Copyright © 2018 Elsevier B.V. All rights reserved.

Large-Scale Simulations of Plastic Neural Networks on Neuromorphic Hardware

PubMed Central

Knight, James C.; Tully, Philip J.; Kaplan, Bernhard A.; Lansner, Anders; Furber, Steve B.

2016-01-01

SpiNNaker is a digital, neuromorphic architecture designed for simulating large-scale spiking neural networks at speeds close to biological real-time. Rather than using bespoke analog or digital hardware, the basic computational unit of a SpiNNaker system is a general-purpose ARM processor, allowing it to be programmed to simulate a wide variety of neuron and synapse models. This flexibility is particularly valuable in the study of biological plasticity phenomena. A recently proposed learning rule based on the Bayesian Confidence Propagation Neural Network (BCPNN) paradigm offers a generic framework for modeling the interaction of different plasticity mechanisms using spiking neurons. However, it can be computationally expensive to simulate large networks with BCPNN learning since it requires multiple state variables for each synapse, each of which needs to be updated every simulation time-step. We discuss the trade-offs in efficiency and accuracy involved in developing an event-based BCPNN implementation for SpiNNaker based on an analytical solution to the BCPNN equations, and detail the steps taken to fit this within the limited computational and memory resources of the SpiNNaker architecture. We demonstrate this learning rule by learning temporal sequences of neural activity within a recurrent attractor network which we simulate at scales of up to 2.0 × 104 neurons and 5.1 × 107 plastic synapses: the largest plastic neural network ever to be simulated on neuromorphic hardware. We also run a comparable simulation on a Cray XC-30 supercomputer system and find that, if it is to match the run-time of our SpiNNaker simulation, the super computer system uses approximately 45× more power. This suggests that cheaper, more power efficient neuromorphic systems are becoming useful discovery tools in the study of plasticity in large-scale brain models. PMID:27092061

Mirrored STDP Implements Autoencoder Learning in a Network of Spiking Neurons.

PubMed

Burbank, Kendra S

2015-12-01

The autoencoder algorithm is a simple but powerful unsupervised method for training neural networks. Autoencoder networks can learn sparse distributed codes similar to those seen in cortical sensory areas such as visual area V1, but they can also be stacked to learn increasingly abstract representations. Several computational neuroscience models of sensory areas, including Olshausen & Field's Sparse Coding algorithm, can be seen as autoencoder variants, and autoencoders have seen extensive use in the machine learning community. Despite their power and versatility, autoencoders have been difficult to implement in a biologically realistic fashion. The challenges include their need to calculate differences between two neuronal activities and their requirement for learning rules which lead to identical changes at feedforward and feedback connections. Here, we study a biologically realistic network of integrate-and-fire neurons with anatomical connectivity and synaptic plasticity that closely matches that observed in cortical sensory areas. Our choice of synaptic plasticity rules is inspired by recent experimental and theoretical results suggesting that learning at feedback connections may have a different form from learning at feedforward connections, and our results depend critically on this novel choice of plasticity rules. Specifically, we propose that plasticity rules at feedforward versus feedback connections are temporally opposed versions of spike-timing dependent plasticity (STDP), leading to a symmetric combined rule we call Mirrored STDP (mSTDP). We show that with mSTDP, our network follows a learning rule that approximately minimizes an autoencoder loss function. When trained with whitened natural image patches, the learned synaptic weights resemble the receptive fields seen in V1. Our results use realistic synaptic plasticity rules to show that the powerful autoencoder learning algorithm could be within the reach of real biological networks.

Mirrored STDP Implements Autoencoder Learning in a Network of Spiking Neurons

PubMed Central

Burbank, Kendra S.

2015-01-01

The autoencoder algorithm is a simple but powerful unsupervised method for training neural networks. Autoencoder networks can learn sparse distributed codes similar to those seen in cortical sensory areas such as visual area V1, but they can also be stacked to learn increasingly abstract representations. Several computational neuroscience models of sensory areas, including Olshausen & Field’s Sparse Coding algorithm, can be seen as autoencoder variants, and autoencoders have seen extensive use in the machine learning community. Despite their power and versatility, autoencoders have been difficult to implement in a biologically realistic fashion. The challenges include their need to calculate differences between two neuronal activities and their requirement for learning rules which lead to identical changes at feedforward and feedback connections. Here, we study a biologically realistic network of integrate-and-fire neurons with anatomical connectivity and synaptic plasticity that closely matches that observed in cortical sensory areas. Our choice of synaptic plasticity rules is inspired by recent experimental and theoretical results suggesting that learning at feedback connections may have a different form from learning at feedforward connections, and our results depend critically on this novel choice of plasticity rules. Specifically, we propose that plasticity rules at feedforward versus feedback connections are temporally opposed versions of spike-timing dependent plasticity (STDP), leading to a symmetric combined rule we call Mirrored STDP (mSTDP). We show that with mSTDP, our network follows a learning rule that approximately minimizes an autoencoder loss function. When trained with whitened natural image patches, the learned synaptic weights resemble the receptive fields seen in V1. Our results use realistic synaptic plasticity rules to show that the powerful autoencoder learning algorithm could be within the reach of real biological networks. PMID:26633645

Reinforcement Learning of Two-Joint Virtual Arm Reaching in a Computer Model of Sensorimotor Cortex

PubMed Central

Neymotin, Samuel A.; Chadderdon, George L.; Kerr, Cliff C.; Francis, Joseph T.; Lytton, William W.

2014-01-01

Neocortical mechanisms of learning sensorimotor control involve a complex series of interactions at multiple levels, from synaptic mechanisms to cellular dynamics to network connectomics. We developed a model of sensory and motor neocortex consisting of 704 spiking model neurons. Sensory and motor populations included excitatory cells and two types of interneurons. Neurons were interconnected with AMPA/NMDA and GABAA synapses. We trained our model using spike-timing-dependent reinforcement learning to control a two-joint virtual arm to reach to a fixed target. For each of 125 trained networks, we used 200 training sessions, each involving 15 s reaches to the target from 16 starting positions. Learning altered network dynamics, with enhancements to neuronal synchrony and behaviorally relevant information flow between neurons. After learning, networks demonstrated retention of behaviorally relevant memories by using proprioceptive information to perform reach-to-target from multiple starting positions. Networks dynamically controlled which joint rotations to use to reach a target, depending on current arm position. Learning-dependent network reorganization was evident in both sensory and motor populations: learned synaptic weights showed target-specific patterning optimized for particular reach movements. Our model embodies an integrative hypothesis of sensorimotor cortical learning that could be used to interpret future electrophysiological data recorded in vivo from sensorimotor learning experiments. We used our model to make the following predictions: learning enhances synchrony in neuronal populations and behaviorally relevant information flow across neuronal populations, enhanced sensory processing aids task-relevant motor performance and the relative ease of a particular movement in vivo depends on the amount of sensory information required to complete the movement. PMID:24047323

Sea level forecasts using neural networks

NASA Astrophysics Data System (ADS)

Röske, Frank

1997-03-01

In this paper, a new method for predicting the sea level employing a neural network approach is introduced. It was designed to improve the prediction of the sea level along the German North Sea Coast under standard conditions. The sea level at any given time depends upon the tides as well as meteorological and oceanographic factors, such as the winds and external surges induced by air pressure. Since tidal predictions are already sufficiently accurate, they have been subtracted from the observed sea levels. The differences will be predicted up to 18 hours in advance. In this paper, the differences are called anomalies. The prediction of the sea level each hour is distinguished from its predictions at the times of high and low tide. For this study, Cuxhaven was selected as a reference site. The predictions made using neural networks were compared for accuracy with the prognoses prepared using six models: two hydrodynamic models, a statistical model, a nearest neighbor model, which is based on analogies, the persistence model, and the verbal forecasts that are broadcast and kept on record by the Sea Level Forecast Service of the Federal Maritime and Hydrography Agency (BSH) in Hamburg. Predictions were calculated for the year 1993 and compared with the actual levels measured. Artificial neural networks are capable of learning. By applying them to the prediction of sea levels, learning from past events has been attempted. It was also attempted to make the experiences of expert forecasters objective. Instead of using the wide-spread back-propagation networks, the self-organizing feature map of Kohonen, or “Kohonen network”, was applied. The fundamental principle of this network is the transformation of the signal similarity into the neighborhood of the neurons while preserving the topology of the signal space. The self-organization procedure of Kohonen networks can be visualized. To make predictions, these networks have been subdivided into a part describing the past state and another part describing the prediction. Both parts have been chosen according to methods of auto- and multiregression. A Kohonen network that has finished learning can be interpreted to be an adaptive table of such descriptions. To avoid overloading the Kohonen networks, the time series, made as complete as possible, were reduced to a learnable data set by means of two selection methods. The minimal distance method as a part of the cluster analysis was used, which selects representative temporal patterns. A novel method called circular group reduction was developed, which selects extreme patterns. This method is used as a supplement to the first one. To help the Kohonen network maintain its memory, the number of neurons and the maximum learning time were chosen according to the number of learning samples. To improve convergence, a combination of criteria was developed to break off learning, which could shown to be conform with the self-organization procedure. Kohonen networks were also applied in an autoregressive manner for the prediction of meteorological variables, especially wind. However, the quality of these predictions was inferior to those of the Marine Weather Service (SWA) in Hamburg, which is part of the German Weather Service (DWD) in Offenbach. High and low tide anomalies were predicted using Kohonen networks for multiregressions. The verbal predictions of high tide anomalies of the BSH Sea Level Forecasting Service were the most precise of all six comparison models. By using the Kohonen networks, it was even possible to improve these predictions and reduce their average error by 1 cm, from 15 to 14 cm.The precision of the Kohonen networks improved as their number of neurons increased and as their weight vectors became smaller. Since there were no major changes in the statistical properties of measurements made over mediumrange time scales, such networks that have completed learning were placed at the Sea Level Forecast Service. However, over the long term, there can be changes in these properties due to climate changes and deepening of the Elbe River. Therefore, the training process of the networks should be repeated periodically taking longer time series into consideration.

Artificial neuron-glia networks learning approach based on cooperative coevolution.

PubMed

Mesejo, Pablo; Ibáñez, Oscar; Fernández-Blanco, Enrique; Cedrón, Francisco; Pazos, Alejandro; Porto-Pazos, Ana B

2015-06-01

Artificial Neuron-Glia Networks (ANGNs) are a novel bio-inspired machine learning approach. They extend classical Artificial Neural Networks (ANNs) by incorporating recent findings and suppositions about the way information is processed by neural and astrocytic networks in the most evolved living organisms. Although ANGNs are not a consolidated method, their performance against the traditional approach, i.e. without artificial astrocytes, was already demonstrated on classification problems. However, the corresponding learning algorithms developed so far strongly depends on a set of glial parameters which are manually tuned for each specific problem. As a consequence, previous experimental tests have to be done in order to determine an adequate set of values, making such manual parameter configuration time-consuming, error-prone, biased and problem dependent. Thus, in this paper, we propose a novel learning approach for ANGNs that fully automates the learning process, and gives the possibility of testing any kind of reasonable parameter configuration for each specific problem. This new learning algorithm, based on coevolutionary genetic algorithms, is able to properly learn all the ANGNs parameters. Its performance is tested on five classification problems achieving significantly better results than ANGN and competitive results with ANN approaches.

Quantized Iterative Learning Consensus Tracking of Digital Networks With Limited Information Communication.

PubMed

Xiong, Wenjun; Yu, Xinghuo; Chen, Yao; Gao, Jie

2017-06-01

This brief investigates the quantized iterative learning problem for digital networks with time-varying topologies. The information is first encoded as symbolic data and then transmitted. After the data are received, a decoder is used by the receiver to get an estimate of the sender's state. Iterative learning quantized communication is considered in the process of encoding and decoding. A sufficient condition is then presented to achieve the consensus tracking problem in a finite interval using the quantized iterative learning controllers. Finally, simulation results are given to illustrate the usefulness of the developed criterion.

Learning to forget: continual prediction with LSTM.

PubMed

Gers, F A; Schmidhuber, J; Cummins, F

2000-10-01

Long short-term memory (LSTM; Hochreiter & Schmidhuber, 1997) can solve numerous tasks not solvable by previous learning algorithms for recurrent neural networks (RNNs). We identify a weakness of LSTM networks processing continual input streams that are not a priori segmented into subsequences with explicitly marked ends at which the network's internal state could be reset. Without resets, the state may grow indefinitely and eventually cause the network to break down. Our remedy is a novel, adaptive "forget gate" that enables an LSTM cell to learn to reset itself at appropriate times, thus releasing internal resources. We review illustrative benchmark problems on which standard LSTM outperforms other RNN algorithms. All algorithms (including LSTM) fail to solve continual versions of these problems. LSTM with forget gates, however, easily solves them, and in an elegant way.

Neural correlates of skill acquisition: decreased cortical activity during a serial interception sequence learning task.

PubMed

Gobel, Eric W; Parrish, Todd B; Reber, Paul J

2011-10-15

Learning of complex motor skills requires learning of component movements as well as the sequential structure of their order and timing. Using a Serial Interception Sequence Learning (SISL) task, participants learned a sequence of precisely timed interception responses through training with a repeating sequence. Following initial implicit learning of the repeating sequence, functional MRI data were collected during performance of that known sequence and compared with activity evoked during novel sequences of actions, novel timing patterns, or both. Reduced activity was observed during the practiced sequence in a distributed bilateral network including extrastriate occipital, parietal, and premotor cortical regions. These reductions in evoked activity likely reflect improved efficiency in visuospatial processing, spatio-motor integration, motor planning, and motor execution for the trained sequence, which is likely supported by nondeclarative skill learning. In addition, the practiced sequence evoked increased activity in the left ventral striatum and medial prefrontal cortex, while the posterior cingulate was more active during periods of better performance. Many prior studies of perceptual-motor skill learning have found increased activity in motor areas of the frontal cortex (e.g., motor and premotor cortex, SMA) and striatal areas (e.g., the putamen). The change in activity observed here (i.e., decreased activity across a cortical network) may reflect skill learning that is predominantly expressed through more accurate performance rather than decreased reaction time. Copyright © 2011 Elsevier Inc. All rights reserved.

Neural Correlates of Skill Acquisition: Decreased Cortical Activity During a Serial Interception Sequence Learning Task

PubMed Central

Gobel, Eric W.; Parrish, Todd B.; Reber, Paul J.

2011-01-01

Learning of complex motor skills requires learning of component movements as well as the sequential structure of their order and timing. Using a Serial Interception Sequence Learning (SISL) task, participants learned a sequence of precisely timed interception responses through training with a repeating sequence. Following initial implicit learning of the repeating sequence, functional MRI data were collected during performance of that known sequence and compared with activity evoked during novel sequences of actions, novel timing patterns, or both. Reduced activity was observed during the practiced sequence in a distributed bilateral network including extrastriate occipital, parietal, and premotor cortical regions. These reductions in evoked activity likely reflect improved efficiency in visuospatial processing, spatio-motor integration, motor planning, and motor execution for the trained sequence, which is likely supported by nondeclarative skill learning. In addition, the practiced sequence evoked increased activity in the left ventral striatum and medial prefrontal cortex, while the posterior cingulate was more active during periods of better performance. Many prior studies of perceptual-motor skill learning have found increased activity in motor areas of frontal cortex (e.g., motor and premotor cortex, SMA) and striatal areas (e.g., the putamen). The change in activity observed here (i.e., decreased activity across a cortical network) may reflect skill learning that is predominantly expressed through more accurate performance rather than decreased reaction time. PMID:21771663

Neural networks supporting switching, hypothesis testing, and rule application

PubMed Central

Liu, Zhiya; Braunlich, Kurt; Wehe, Hillary S.; Seger, Carol A.

2015-01-01

We identified dynamic changes in recruitment of neural connectivity networks across three phases of a flexible rule learning and set-shifting task similar to the Wisconsin Card Sort Task: switching, rule learning via hypothesis testing, and rule application. During fMRI scanning, subjects viewed pairs of stimuli that differed across four dimensions (letter, color, size, screen location), chose one stimulus, and received feedback. Subjects were informed that the correct choice was determined by a simple unidimensional rule, for example “choose the blue letter.” Once each rule had been learned and correctly applied for 4-7 trials, subjects were cued via either negative feedback or visual cues to switch to learning a new rule. Task performance was divided into three phases: Switching (first trial after receiving the switch cue), hypothesis testing (subsequent trials through the last error trial), and rule application (correct responding after the rule was learned). We used both univariate analysis to characterize activity occurring within specific regions of the brain, and a multivariate method, constrained principal component analysis for fMRI (fMRI-CPCA), to investigate how distributed regions coordinate to subserve different processes. As hypothesized, switching was subserved by a limbic network including the ventral striatum, thalamus, and parahippocampal gyrus, in conjunction with cortical salience network regions including the anterior cingulate and frontoinsular cortex. Activity in the ventral striatum was associated with switching regardless of how switching was cued; visually cued shifts were associated with additional visual cortical activity. After switching, as subjects moved into the hypothesis testing phase, a broad fronto-parietal-striatal network (associated with the cognitive control, dorsal attention, and salience networks) increased in activity. This network was sensitive to rule learning speed, with greater extended activity for the slowest learning speed late in the time course of learning. As subjects shifted from hypothesis testing to rule application, activity in this network decreased and activity in the somatomotor and default mode networks increased. PMID:26197092

Neural networks supporting switching, hypothesis testing, and rule application.

PubMed

Liu, Zhiya; Braunlich, Kurt; Wehe, Hillary S; Seger, Carol A

2015-10-01

We identified dynamic changes in recruitment of neural connectivity networks across three phases of a flexible rule learning and set-shifting task similar to the Wisconsin Card Sort Task: switching, rule learning via hypothesis testing, and rule application. During fMRI scanning, subjects viewed pairs of stimuli that differed across four dimensions (letter, color, size, screen location), chose one stimulus, and received feedback. Subjects were informed that the correct choice was determined by a simple unidimensional rule, for example "choose the blue letter". Once each rule had been learned and correctly applied for 4-7 trials, subjects were cued via either negative feedback or visual cues to switch to learning a new rule. Task performance was divided into three phases: Switching (first trial after receiving the switch cue), hypothesis testing (subsequent trials through the last error trial), and rule application (correct responding after the rule was learned). We used both univariate analysis to characterize activity occurring within specific regions of the brain, and a multivariate method, constrained principal component analysis for fMRI (fMRI-CPCA), to investigate how distributed regions coordinate to subserve different processes. As hypothesized, switching was subserved by a limbic network including the ventral striatum, thalamus, and parahippocampal gyrus, in conjunction with cortical salience network regions including the anterior cingulate and frontoinsular cortex. Activity in the ventral striatum was associated with switching regardless of how switching was cued; visually cued shifts were associated with additional visual cortical activity. After switching, as subjects moved into the hypothesis testing phase, a broad fronto-parietal-striatal network (associated with the cognitive control, dorsal attention, and salience networks) increased in activity. This network was sensitive to rule learning speed, with greater extended activity for the slowest learning speed late in the time course of learning. As subjects shifted from hypothesis testing to rule application, activity in this network decreased and activity in the somatomotor and default mode networks increased. Copyright © 2015 Elsevier Ltd. All rights reserved.

Categorization and decision-making in a neurobiologically plausible spiking network using a STDP-like learning rule.

PubMed

Beyeler, Michael; Dutt, Nikil D; Krichmar, Jeffrey L

2013-12-01

Understanding how the human brain is able to efficiently perceive and understand a visual scene is still a field of ongoing research. Although many studies have focused on the design and optimization of neural networks to solve visual recognition tasks, most of them either lack neurobiologically plausible learning rules or decision-making processes. Here we present a large-scale model of a hierarchical spiking neural network (SNN) that integrates a low-level memory encoding mechanism with a higher-level decision process to perform a visual classification task in real-time. The model consists of Izhikevich neurons and conductance-based synapses for realistic approximation of neuronal dynamics, a spike-timing-dependent plasticity (STDP) synaptic learning rule with additional synaptic dynamics for memory encoding, and an accumulator model for memory retrieval and categorization. The full network, which comprised 71,026 neurons and approximately 133 million synapses, ran in real-time on a single off-the-shelf graphics processing unit (GPU). The network was constructed on a publicly available SNN simulator that supports general-purpose neuromorphic computer chips. The network achieved 92% correct classifications on MNIST in 100 rounds of random sub-sampling, which is comparable to other SNN approaches and provides a conservative and reliable performance metric. Additionally, the model correctly predicted reaction times from psychophysical experiments. Because of the scalability of the approach and its neurobiological fidelity, the current model can be extended to an efficient neuromorphic implementation that supports more generalized object recognition and decision-making architectures found in the brain. Copyright © 2013 Elsevier Ltd. All rights reserved.

Emergent Auditory Feature Tuning in a Real-Time Neuromorphic VLSI System.

PubMed

Sheik, Sadique; Coath, Martin; Indiveri, Giacomo; Denham, Susan L; Wennekers, Thomas; Chicca, Elisabetta

2012-01-01

Many sounds of ecological importance, such as communication calls, are characterized by time-varying spectra. However, most neuromorphic auditory models to date have focused on distinguishing mainly static patterns, under the assumption that dynamic patterns can be learned as sequences of static ones. In contrast, the emergence of dynamic feature sensitivity through exposure to formative stimuli has been recently modeled in a network of spiking neurons based on the thalamo-cortical architecture. The proposed network models the effect of lateral and recurrent connections between cortical layers, distance-dependent axonal transmission delays, and learning in the form of Spike Timing Dependent Plasticity (STDP), which effects stimulus-driven changes in the pattern of network connectivity. In this paper we demonstrate how these principles can be efficiently implemented in neuromorphic hardware. In doing so we address two principle problems in the design of neuromorphic systems: real-time event-based asynchronous communication in multi-chip systems, and the realization in hybrid analog/digital VLSI technology of neural computational principles that we propose underlie plasticity in neural processing of dynamic stimuli. The result is a hardware neural network that learns in real-time and shows preferential responses, after exposure, to stimuli exhibiting particular spectro-temporal patterns. The availability of hardware on which the model can be implemented, makes this a significant step toward the development of adaptive, neurobiologically plausible, spike-based, artificial sensory systems.

Emergent Auditory Feature Tuning in a Real-Time Neuromorphic VLSI System

PubMed Central

Sheik, Sadique; Coath, Martin; Indiveri, Giacomo; Denham, Susan L.; Wennekers, Thomas; Chicca, Elisabetta

2011-01-01

Many sounds of ecological importance, such as communication calls, are characterized by time-varying spectra. However, most neuromorphic auditory models to date have focused on distinguishing mainly static patterns, under the assumption that dynamic patterns can be learned as sequences of static ones. In contrast, the emergence of dynamic feature sensitivity through exposure to formative stimuli has been recently modeled in a network of spiking neurons based on the thalamo-cortical architecture. The proposed network models the effect of lateral and recurrent connections between cortical layers, distance-dependent axonal transmission delays, and learning in the form of Spike Timing Dependent Plasticity (STDP), which effects stimulus-driven changes in the pattern of network connectivity. In this paper we demonstrate how these principles can be efficiently implemented in neuromorphic hardware. In doing so we address two principle problems in the design of neuromorphic systems: real-time event-based asynchronous communication in multi-chip systems, and the realization in hybrid analog/digital VLSI technology of neural computational principles that we propose underlie plasticity in neural processing of dynamic stimuli. The result is a hardware neural network that learns in real-time and shows preferential responses, after exposure, to stimuli exhibiting particular spectro-temporal patterns. The availability of hardware on which the model can be implemented, makes this a significant step toward the development of adaptive, neurobiologically plausible, spike-based, artificial sensory systems. PMID:22347163

Person re-identification over camera networks using multi-task distance metric learning.

PubMed

Ma, Lianyang; Yang, Xiaokang; Tao, Dacheng

2014-08-01

Person reidentification in a camera network is a valuable yet challenging problem to solve. Existing methods learn a common Mahalanobis distance metric by using the data collected from different cameras and then exploit the learned metric for identifying people in the images. However, the cameras in a camera network have different settings and the recorded images are seriously affected by variability in illumination conditions, camera viewing angles, and background clutter. Using a common metric to conduct person reidentification tasks on different camera pairs overlooks the differences in camera settings; however, it is very time-consuming to label people manually in images from surveillance videos. For example, in most existing person reidentification data sets, only one image of a person is collected from each of only two cameras; therefore, directly learning a unique Mahalanobis distance metric for each camera pair is susceptible to over-fitting by using insufficiently labeled data. In this paper, we reformulate person reidentification in a camera network as a multitask distance metric learning problem. The proposed method designs multiple Mahalanobis distance metrics to cope with the complicated conditions that exist in typical camera networks. We address the fact that these Mahalanobis distance metrics are different but related, and learned by adding joint regularization to alleviate over-fitting. Furthermore, by extending, we present a novel multitask maximally collapsing metric learning (MtMCML) model for person reidentification in a camera network. Experimental results demonstrate that formulating person reidentification over camera networks as multitask distance metric learning problem can improve performance, and our proposed MtMCML works substantially better than other current state-of-the-art person reidentification methods.

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

Comparative Studies of Prediction Strategies for Solar X-ray Time Series

NASA Astrophysics Data System (ADS)

Muranushi, T.; Hattori, T.; Jin, Q.; Hishinuma, T.; Tominaga, M.; Nakagawa, K.; Fujiwara, Y.; Nakamura, T.; Sakaue, T.; Takahashi, T.; Seki, D.; Namekata, K.; Tei, A.; Ban, M.; Kawamura, A. D.; Hada-Muranushi, Y.; Asai, A.; Nemoto, S.; Shibata, K.

2016-12-01

Crucial virtues for operational space weather forecast are real-timeforecast ability, forecast precision and customizability to userneeds. The recent development of deep-learning makes it veryattractive to space weather, because (1) it learns gradually incomingdata, (2) it exhibits superior accuracy over conventional algorithmsin many fields, and (3) it makes the customization of the forecasteasier because it accepts raw images.However, the best deep-learning applications are only attainable bycareful human designers that understands both the mechanism of deeplearning and the application field. Therefore, we need to foster youngresearchers to enter the field of machine-learning aided forecast. So,we have held a seminar every Monday with undergraduate and graduatestudents from May to August 2016.We will review the current status of space weather science and theautomated real-time space weather forecast engine UFCORIN. Then, weintroduce the deep-learning space weather forecast environments wehave set up using Python and Chainer on students' laptop computers.We have started from simple image classification neural network, thenimplemented space-weather neural network that predicts future X-rayflux of the Sun based on the past X-ray lightcurve and magnetic fieldline-of-sight images.In order to perform each forecast faster, we have focused on simplelightcurve-to-lightcurve forecast, and performed comparative surveysby changing following parameters: The size and topology of the neural network Batchsize Neural network hyperparameters such as learning rates to optimize the preduction accuracy, and time for prediction.We have found how to design compact, fast but accurate neural networkto perform forecast. Our forecasters can perform predictionexperiment for four-year timespan in a few minutes, and achieveslog-scale errors of the order of 1. Our studies is ongoing, and inour talk we will review our progress till December.

Trading Speed and Accuracy by Coding Time: A Coupled-circuit Cortical Model

PubMed Central

Standage, Dominic; You, Hongzhi; Wang, Da-Hui; Dorris, Michael C.

2013-01-01

Our actions take place in space and time, but despite the role of time in decision theory and the growing acknowledgement that the encoding of time is crucial to behaviour, few studies have considered the interactions between neural codes for objects in space and for elapsed time during perceptual decisions. The speed-accuracy trade-off (SAT) provides a window into spatiotemporal interactions. Our hypothesis is that temporal coding determines the rate at which spatial evidence is integrated, controlling the SAT by gain modulation. Here, we propose that local cortical circuits are inherently suited to the relevant spatial and temporal coding. In simulations of an interval estimation task, we use a generic local-circuit model to encode time by ‘climbing’ activity, seen in cortex during tasks with a timing requirement. The model is a network of simulated pyramidal cells and inhibitory interneurons, connected by conductance synapses. A simple learning rule enables the network to quickly produce new interval estimates, which show signature characteristics of estimates by experimental subjects. Analysis of network dynamics formally characterizes this generic, local-circuit timing mechanism. In simulations of a perceptual decision task, we couple two such networks. Network function is determined only by spatial selectivity and NMDA receptor conductance strength; all other parameters are identical. To trade speed and accuracy, the timing network simply learns longer or shorter intervals, driving the rate of downstream decision processing by spatially non-selective input, an established form of gain modulation. Like the timing network's interval estimates, decision times show signature characteristics of those by experimental subjects. Overall, we propose, demonstrate and analyse a generic mechanism for timing, a generic mechanism for modulation of decision processing by temporal codes, and we make predictions for experimental verification. PMID:23592967

ATM: The Key To Harnessing the Power of Networked Multimedia.

ERIC Educational Resources Information Center

Gross, Rod

1996-01-01

ATM (Asynchronous Transfer Mode) network technology handles the real-time continuous traffic flow necessary to support desktop multimedia applications. Describes network applications already used: desktop video collaboration, distance learning, and broadcasting video delivery. Examines the architecture of ATM technology, video delivery and sound…

Higher-Order Neural Networks Recognize Patterns

NASA Technical Reports Server (NTRS)

Reid, Max B.; Spirkovska, Lilly; Ochoa, Ellen

1996-01-01

Networks of higher order have enhanced capabilities to distinguish between different two-dimensional patterns and to recognize those patterns. Also enhanced capabilities to "learn" patterns to be recognized: "trained" with far fewer examples and, therefore, in less time than necessary to train comparable first-order neural networks.

Dynamic reconfiguration of human brain functional networks through neurofeedback.

PubMed

Haller, Sven; Kopel, Rotem; Jhooti, Permi; Haas, Tanja; Scharnowski, Frank; Lovblad, Karl-Olof; Scheffler, Klaus; Van De Ville, Dimitri

2013-11-01

Recent fMRI studies demonstrated that functional connectivity is altered following cognitive tasks (e.g., learning) or due to various neurological disorders. We tested whether real-time fMRI-based neurofeedback can be a tool to voluntarily reconfigure brain network interactions. To disentangle learning-related from regulation-related effects, we first trained participants to voluntarily regulate activity in the auditory cortex (training phase) and subsequently asked participants to exert learned voluntary self-regulation in the absence of feedback (transfer phase without learning). Using independent component analysis (ICA), we found network reconfigurations (increases in functional network connectivity) during the neurofeedback training phase between the auditory target region and (1) the auditory pathway; (2) visual regions related to visual feedback processing; (3) insula related to introspection and self-regulation and (4) working memory and high-level visual attention areas related to cognitive effort. Interestingly, the auditory target region was identified as the hub of the reconfigured functional networks without a-priori assumptions. During the transfer phase, we again found specific functional connectivity reconfiguration between auditory and attention network confirming the specific effect of self-regulation on functional connectivity. Functional connectivity to working memory related networks was no longer altered consistent with the absent demand on working memory. We demonstrate that neurofeedback learning is mediated by widespread changes in functional connectivity. In contrast, applying learned self-regulation involves more limited and specific network changes in an auditory setup intended as a model for tinnitus. Hence, neurofeedback training might be used to promote recovery from neurological disorders that are linked to abnormal patterns of brain connectivity. Copyright © 2013 Elsevier Inc. All rights reserved.

Neural networks for continuous online learning and control.

PubMed

Choy, Min Chee; Srinivasan, Dipti; Cheu, Ruey Long

2006-11-01

This paper proposes a new hybrid neural network (NN) model that employs a multistage online learning process to solve the distributed control problem with an infinite horizon. Various techniques such as reinforcement learning and evolutionary algorithm are used to design the multistage online learning process. For this paper, the infinite horizon distributed control problem is implemented in the form of real-time distributed traffic signal control for intersections in a large-scale traffic network. The hybrid neural network model is used to design each of the local traffic signal controllers at the respective intersections. As the state of the traffic network changes due to random fluctuation of traffic volumes, the NN-based local controllers will need to adapt to the changing dynamics in order to provide effective traffic signal control and to prevent the traffic network from becoming overcongested. Such a problem is especially challenging if the local controllers are used for an infinite horizon problem where online learning has to take place continuously once the controllers are implemented into the traffic network. A comprehensive simulation model of a section of the Central Business District (CBD) of Singapore has been developed using PARAMICS microscopic simulation program. As the complexity of the simulation increases, results show that the hybrid NN model provides significant improvement in traffic conditions when evaluated against an existing traffic signal control algorithm as well as a new, continuously updated simultaneous perturbation stochastic approximation-based neural network (SPSA-NN). Using the hybrid NN model, the total mean delay of each vehicle has been reduced by 78% and the total mean stoppage time of each vehicle has been reduced by 84% compared to the existing traffic signal control algorithm. This shows the efficacy of the hybrid NN model in solving large-scale traffic signal control problem in a distributed manner. Also, it indicates the possibility of using the hybrid NN model for other applications that are similar in nature as the infinite horizon distributed control problem.

Feedback control stabilization of critical dynamics via resource transport on multilayer networks: How glia enable learning dynamics in the brain

NASA Astrophysics Data System (ADS)

Virkar, Yogesh S.; Shew, Woodrow L.; Restrepo, Juan G.; Ott, Edward

2016-10-01

Learning and memory are acquired through long-lasting changes in synapses. In the simplest models, such synaptic potentiation typically leads to runaway excitation, but in reality there must exist processes that robustly preserve overall stability of the neural system dynamics. How is this accomplished? Various approaches to this basic question have been considered. Here we propose a particularly compelling and natural mechanism for preserving stability of learning neural systems. This mechanism is based on the global processes by which metabolic resources are distributed to the neurons by glial cells. Specifically, we introduce and study a model composed of two interacting networks: a model neural network interconnected by synapses that undergo spike-timing-dependent plasticity; and a model glial network interconnected by gap junctions that diffusively transport metabolic resources among the glia and, ultimately, to neural synapses where they are consumed. Our main result is that the biophysical constraints imposed by diffusive transport of metabolic resources through the glial network can prevent runaway growth of synaptic strength, both during ongoing activity and during learning. Our findings suggest a previously unappreciated role for glial transport of metabolites in the feedback control stabilization of neural network dynamics during learning.

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.

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.

Cascaded VLSI Chips Help Neural Network To Learn

NASA Technical Reports Server (NTRS)

Duong, Tuan A.; Daud, Taher; Thakoor, Anilkumar P.

1993-01-01

Cascading provides 12-bit resolution needed for learning. Using conventional silicon chip fabrication technology of VLSI, fully connected architecture consisting of 32 wide-range, variable gain, sigmoidal neurons along one diagonal and 7-bit resolution, electrically programmable, synaptic 32 x 31 weight matrix implemented on neuron-synapse chip. To increase weight nominally from 7 to 13 bits, synapses on chip individually cascaded with respective synapses on another 32 x 32 matrix chip with 7-bit resolution synapses only (without neurons). Cascade correlation algorithm varies number of layers effectively connected into network; adds hidden layers one at a time during learning process in such way as to optimize overall number of neurons and complexity and configuration of network.

Overcoming catastrophic forgetting in neural networks

PubMed Central

Kirkpatrick, James; Pascanu, Razvan; Rabinowitz, Neil; Veness, Joel; Desjardins, Guillaume; Rusu, Andrei A.; Milan, Kieran; Quan, John; Ramalho, Tiago; Grabska-Barwinska, Agnieszka; Hassabis, Demis; Clopath, Claudia; Kumaran, Dharshan; Hadsell, Raia

2017-01-01

The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Until now neural networks have not been capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models. We show that it is possible to overcome this limitation and train networks that can maintain expertise on tasks that they have not experienced for a long time. Our approach remembers old tasks by selectively slowing down learning on the weights important for those tasks. We demonstrate our approach is scalable and effective by solving a set of classification tasks based on a hand-written digit dataset and by learning several Atari 2600 games sequentially. PMID:28292907

Networks of Learning

NASA Astrophysics Data System (ADS)

Bettencourt, Luis; Kaiser, David

2004-03-01

Based on an a historically documented example of scientific discovery - Feynman diagrams as the main calculational tool of theoretical high energy Physics - we map the time evolution of the social network of early adopters through in the US, UK, Japan and the USSR. The spread of the technique for total number of users in each region is then modelled in terms of epidemic models, highlighting parallel and divergent aspects of this analogy. We also show that transient social arrangements develop as the idea is introduced and learned, which later disappear as the technique becomes common knowledge. Such early transient is characterized by abnormally low connectivity distribution powers and by high clustering. This interesting early non-equilibrium stage of network evolution is captured by a new dynamical model for network evolution, which coincides in its long time limit with familiar preferential aggregation dynamics.

Visualising the Invisible: A Network Approach to Reveal the Informal Social Side of Student Learning

ERIC Educational Resources Information Center

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

2012-01-01

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…

Toxicological Tipping Points: Learning Boolean Networks from High-Content Imaging Data. (BOSC meeting)

EPA Science Inventory

The objective of this work is to elucidate biological networks underlying cellular tipping points using time-course data. We discretized the high-content imaging (HCI) data and inferred Boolean networks (BNs) that could accurately predict dynamic cellular trajectories. We found t...

Differential Encoding of Time by Prefrontal and Striatal Network Dynamics.

PubMed

Bakhurin, Konstantin I; Goudar, Vishwa; Shobe, Justin L; Claar, Leslie D; Buonomano, Dean V; Masmanidis, Sotiris C

2017-01-25

Telling time is fundamental to many forms of learning and behavior, including the anticipation of rewarding events. Although the neural mechanisms underlying timing remain unknown, computational models have proposed that the brain represents time in the dynamics of neural networks. Consistent with this hypothesis, changing patterns of neural activity dynamically in a number of brain areas-including the striatum and cortex-has been shown to encode elapsed time. To date, however, no studies have explicitly quantified and contrasted how well different areas encode time by recording large numbers of units simultaneously from more than one area. Here, we performed large-scale extracellular recordings in the striatum and orbitofrontal cortex of mice that learned the temporal relationship between a stimulus and a reward and reported their response with anticipatory licking. We used a machine-learning algorithm to quantify how well populations of neurons encoded elapsed time from stimulus onset. Both the striatal and cortical networks encoded time, but the striatal network outperformed the orbitofrontal cortex, a finding replicated both in simultaneously and nonsimultaneously recorded corticostriatal datasets. The striatal network was also more reliable in predicting when the animals would lick up to ∼1 s before the actual lick occurred. Our results are consistent with the hypothesis that temporal information is encoded in a widely distributed manner throughout multiple brain areas, but that the striatum may have a privileged role in timing because it has a more accurate "clock" as it integrates information across multiple cortical areas. The neural representation of time is thought to be distributed across multiple functionally specialized brain structures, including the striatum and cortex. However, until now, the neural code for time has not been compared quantitatively between these areas. Here, we performed large-scale recordings in the striatum and orbitofrontal cortex of mice trained on a stimulus-reward association task involving a delay period and used a machine-learning algorithm to quantify how well populations of simultaneously recorded neurons encoded elapsed time from stimulus onset. We found that, although both areas encoded time, the striatum consistently outperformed the orbitofrontal cortex. These results suggest that the striatum may refine the code for time by integrating information from multiple inputs. Copyright © 2017 the authors 0270-6474/17/370854-17$15.00/0.

A spiking neural network based on the basal ganglia functional anatomy.

PubMed

Baladron, Javier; Hamker, Fred H

2015-07-01

We introduce a spiking neural network of the basal ganglia capable of learning stimulus-action associations. We model learning in the three major basal ganglia pathways, direct, indirect and hyperdirect, by spike time dependent learning and considering the amount of dopamine available (reward). Moreover, we allow to learn a cortico-thalamic pathway that bypasses the basal ganglia. As a result the system develops new functionalities for the different basal ganglia pathways: The direct pathway selects actions by disinhibiting the thalamus, the hyperdirect one suppresses alternatives and the indirect pathway learns to inhibit common mistakes. Numerical experiments show that the system is capable of learning sets of either deterministic or stochastic rules. Copyright © 2015 Elsevier Ltd. All rights reserved.

A New Local Bipolar Autoassociative Memory Based on External Inputs of Discrete Recurrent Neural Networks With Time Delay.

PubMed

Zhou, Caigen; Zeng, Xiaoqin; Luo, Chaomin; Zhang, Huaguang

In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.

A study of network education application on nursing staff continuing education effectiveness and staff's satisfaction.

PubMed

Lin, Juin-Shu; Yen-Chi, Liao; Lee, Ting-Ting

2006-01-01

The rapid development of computer technology pushes Internet's popularity and makes daily services more timely and convenient. Meanwhile, it also becomes a trend for nursing practice to implement network education model to break the distance barriers and for nurses to obtain more knowledge. The purpose of this study was to investigate the relationship of nursing staff's information competency, satisfaction and outcomes of network education. After completing 4 weeks of network education, a total of 218 nurses answered the on-line questionnaires. The results revealed that nurses who joined the computer training course for less than 3 hours per week, without networking connection devices and with college degree, had the lower nursing informatics competency; while nurses who were older, at N4 position, with on-line course experience and participated for more than 4 hours each week, had higher nursing informatics competency. Those who participated in the network education course less than 4 hours per week were less satisfied. There were significant differences between nursing positions before and after having the network education. Nurses who had higher nursing information competency also had higher satisfaction toward the network education. Network education not only enhances learners' computer competency but also improves their learning satisfaction. By promoting the network education and improving nurses' hardware/software skills and knowledge, nurses can use networks to access learning resources. Healthcare institutions should also enhance computer infrastructure, and to establish the standards for certificate courses to increase the learning motivation and learning outcome.

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.

Real-time cerebellar neuroprosthetic system based on a spiking neural network model of motor learning.

PubMed

Xu, Tao; Xiao, Na; Zhai, Xiaolong; Kwan Chan, Pak; Tin, Chung

2018-02-01

Damage to the brain, as a result of various medical conditions, impacts the everyday life of patients and there is still no complete cure to neurological disorders. Neuroprostheses that can functionally replace the damaged neural circuit have recently emerged as a possible solution to these problems. Here we describe the development of a real-time cerebellar neuroprosthetic system to substitute neural function in cerebellar circuitry for learning delay eyeblink conditioning (DEC). The system was empowered by a biologically realistic spiking neural network (SNN) model of the cerebellar neural circuit, which considers the neuronal population and anatomical connectivity of the network. The model simulated synaptic plasticity critical for learning DEC. This SNN model was carefully implemented on a field programmable gate array (FPGA) platform for real-time simulation. This hardware system was interfaced in in vivo experiments with anesthetized rats and it used neural spikes recorded online from the animal to learn and trigger conditioned eyeblink in the animal during training. This rat-FPGA hybrid system was able to process neuronal spikes in real-time with an embedded cerebellum model of ~10 000 neurons and reproduce learning of DEC with different inter-stimulus intervals. Our results validated that the system performance is physiologically relevant at both the neural (firing pattern) and behavioral (eyeblink pattern) levels. This integrated system provides the sufficient computation power for mimicking the cerebellar circuit in real-time. The system interacts with the biological system naturally at the spike level and can be generalized for including other neural components (neuron types and plasticity) and neural functions for potential neuroprosthetic applications.

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

Artificial neural network with backpropagation learning to predict mean monthly total ozone in Arosa, Switzerland

NASA Astrophysics Data System (ADS)

Chattopadhyay, Surajit; Bandyopadhyay, Goutami

2007-01-01

Present study deals with the mean monthly total ozone time series over Arosa, Switzerland. The study period is 1932-1971. First of all, the total ozone time series has been identified as a complex system and then Artificial Neural Networks models in the form of Multilayer Perceptron with back propagation learning have been developed. The models are Single-hidden-layer and Two-hidden-layer Perceptrons with sigmoid activation function. After sequential learning with learning rate 0.9 the peak total ozone period (February-May) concentrations of mean monthly total ozone have been predicted by the two neural net models. After training and validation, both of the models are found skillful. But, Two-hidden-layer Perceptron is found to be more adroit in predicting the mean monthly total ozone concentrations over the aforesaid period.

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.

A Survey of Student Attitudes on the Use of Social Networking to Build Learning Communities

ERIC Educational Resources Information Center

Arndt, Timothy

2012-01-01

Post-secondary students are increasingly receiving instruction by distance learning. This mode of learning can result in the students learning in isolation, with bad results in learning outcomes. The same type of isolation can occur for part-time students and those who are working while taking classes. In such circumstances, we believe that it…

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.

On the applicability of STDP-based learning mechanisms to spiking neuron network models

NASA Astrophysics Data System (ADS)

Sboev, A.; Vlasov, D.; Serenko, A.; Rybka, R.; Moloshnikov, I.

2016-11-01

The ways to creating practically effective method for spiking neuron networks learning, that would be appropriate for implementing in neuromorphic hardware and at the same time based on the biologically plausible plasticity rules, namely, on STDP, are discussed. The influence of the amount of correlation between input and output spike trains on the learnability by different STDP rules is evaluated. A usability of alternative combined learning schemes, involving artificial and spiking neuron models is demonstrated on the iris benchmark task and on the practical task of gender recognition.

Intelligent process mapping through systematic improvement of heuristics

NASA Technical Reports Server (NTRS)

Ieumwananonthachai, Arthur; Aizawa, Akiko N.; Schwartz, Steven R.; Wah, Benjamin W.; Yan, Jerry C.

1992-01-01

The present system for automatic learning/evaluation of novel heuristic methods applicable to the mapping of communication-process sets on a computer network has its basis in the testing of a population of competing heuristic methods within a fixed time-constraint. The TEACHER 4.1 prototype learning system implemented or learning new postgame analysis heuristic methods iteratively generates and refines the mappings of a set of communicating processes on a computer network. A systematic exploration of the space of possible heuristic methods is shown to promise significant improvement.

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.

Diversity Networking Reception

NASA Astrophysics Data System (ADS)

2014-03-01

Join us at the APS Diversity Reception to relax, network with colleagues, and learn about programs and initiatives for women, underrepresented minorities, and LGBT physicists. You'll have a great time meeting friends in a supportive environment and making connections.

Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines.

PubMed

Neftci, Emre O; Pedroni, Bruno U; Joshi, Siddharth; Al-Shedivat, Maruan; Cauwenberghs, Gert

2016-01-01

Recent studies have shown that synaptic unreliability is a robust and sufficient mechanism for inducing the stochasticity observed in cortex. Here, we introduce Synaptic Sampling Machines (S2Ms), a class of neural network models that uses synaptic stochasticity as a means to Monte Carlo sampling and unsupervised learning. Similar to the original formulation of Boltzmann machines, these models can be viewed as a stochastic counterpart of Hopfield networks, but where stochasticity is induced by a random mask over the connections. Synaptic stochasticity plays the dual role of an efficient mechanism for sampling, and a regularizer during learning akin to DropConnect. A local synaptic plasticity rule implementing an event-driven form of contrastive divergence enables the learning of generative models in an on-line fashion. S2Ms perform equally well using discrete-timed artificial units (as in Hopfield networks) or continuous-timed leaky integrate and fire neurons. The learned representations are remarkably sparse and robust to reductions in bit precision and synapse pruning: removal of more than 75% of the weakest connections followed by cursory re-learning causes a negligible performance loss on benchmark classification tasks. The spiking neuron-based S2Ms outperform existing spike-based unsupervised learners, while potentially offering substantial advantages in terms of power and complexity, and are thus promising models for on-line learning in brain-inspired hardware.

Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines

PubMed Central

Neftci, Emre O.; Pedroni, Bruno U.; Joshi, Siddharth; Al-Shedivat, Maruan; Cauwenberghs, Gert

2016-01-01

Recent studies have shown that synaptic unreliability is a robust and sufficient mechanism for inducing the stochasticity observed in cortex. Here, we introduce Synaptic Sampling Machines (S2Ms), a class of neural network models that uses synaptic stochasticity as a means to Monte Carlo sampling and unsupervised learning. Similar to the original formulation of Boltzmann machines, these models can be viewed as a stochastic counterpart of Hopfield networks, but where stochasticity is induced by a random mask over the connections. Synaptic stochasticity plays the dual role of an efficient mechanism for sampling, and a regularizer during learning akin to DropConnect. A local synaptic plasticity rule implementing an event-driven form of contrastive divergence enables the learning of generative models in an on-line fashion. S2Ms perform equally well using discrete-timed artificial units (as in Hopfield networks) or continuous-timed leaky integrate and fire neurons. The learned representations are remarkably sparse and robust to reductions in bit precision and synapse pruning: removal of more than 75% of the weakest connections followed by cursory re-learning causes a negligible performance loss on benchmark classification tasks. The spiking neuron-based S2Ms outperform existing spike-based unsupervised learners, while potentially offering substantial advantages in terms of power and complexity, and are thus promising models for on-line learning in brain-inspired hardware. PMID:27445650

Adaptive Neurons For Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Tawel, Raoul

1990-01-01

Training time decreases dramatically. In improved mathematical model of neural-network processor, temperature of neurons (in addition to connection strengths, also called weights, of synapses) varied during supervised-learning phase of operation according to mathematical formalism and not heuristic rule. Evidence that biological neural networks also process information at neuronal level.

Labeled Postings for Asynchronous Interaction

ERIC Educational Resources Information Center

ChanLin, Lih-Juan; Chen, Yong-Ting; Chan, Kung-Chi

2009-01-01

The Internet promotes computer-mediated communications, and so asynchronous learning network systems permit more flexibility in time, space, and interaction than synchronous mode of learning. The key point of asynchronous learning is the materials for web-aided teaching and the flow of knowledge. This research focuses on improving online…

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.

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.

Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding

PubMed Central

Gardner, Brian; Grüning, André

2016-01-01

Precise spike timing as a means to encode information in neural networks is biologically supported, and is advantageous over frequency-based codes by processing input features on a much shorter time-scale. For these reasons, much recent attention has been focused on the development of supervised learning rules for spiking neural networks that utilise a temporal coding scheme. However, despite significant progress in this area, there still lack rules that have a theoretical basis, and yet can be considered biologically relevant. Here we examine the general conditions under which synaptic plasticity most effectively takes place to support the supervised learning of a precise temporal code. As part of our analysis we examine two spike-based learning methods: one of which relies on an instantaneous error signal to modify synaptic weights in a network (INST rule), and the other one relying on a filtered error signal for smoother synaptic weight modifications (FILT rule). We test the accuracy of the solutions provided by each rule with respect to their temporal encoding precision, and then measure the maximum number of input patterns they can learn to memorise using the precise timings of individual spikes as an indication of their storage capacity. Our results demonstrate the high performance of the FILT rule in most cases, underpinned by the rule’s error-filtering mechanism, which is predicted to provide smooth convergence towards a desired solution during learning. We also find the FILT rule to be most efficient at performing input pattern memorisations, and most noticeably when patterns are identified using spikes with sub-millisecond temporal precision. In comparison with existing work, we determine the performance of the FILT rule to be consistent with that of the highly efficient E-learning Chronotron rule, but with the distinct advantage that our FILT rule is also implementable as an online method for increased biological realism. PMID:27532262

Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding.

PubMed

Gardner, Brian; Grüning, André

2016-01-01

Precise spike timing as a means to encode information in neural networks is biologically supported, and is advantageous over frequency-based codes by processing input features on a much shorter time-scale. For these reasons, much recent attention has been focused on the development of supervised learning rules for spiking neural networks that utilise a temporal coding scheme. However, despite significant progress in this area, there still lack rules that have a theoretical basis, and yet can be considered biologically relevant. Here we examine the general conditions under which synaptic plasticity most effectively takes place to support the supervised learning of a precise temporal code. As part of our analysis we examine two spike-based learning methods: one of which relies on an instantaneous error signal to modify synaptic weights in a network (INST rule), and the other one relying on a filtered error signal for smoother synaptic weight modifications (FILT rule). We test the accuracy of the solutions provided by each rule with respect to their temporal encoding precision, and then measure the maximum number of input patterns they can learn to memorise using the precise timings of individual spikes as an indication of their storage capacity. Our results demonstrate the high performance of the FILT rule in most cases, underpinned by the rule's error-filtering mechanism, which is predicted to provide smooth convergence towards a desired solution during learning. We also find the FILT rule to be most efficient at performing input pattern memorisations, and most noticeably when patterns are identified using spikes with sub-millisecond temporal precision. In comparison with existing work, we determine the performance of the FILT rule to be consistent with that of the highly efficient E-learning Chronotron rule, but with the distinct advantage that our FILT rule is also implementable as an online method for increased biological realism.

A forecast-based STDP rule suitable for neuromorphic implementation.

PubMed

Davies, S; Galluppi, F; Rast, A D; Furber, S B

2012-08-01

Artificial neural networks increasingly involve spiking dynamics to permit greater computational efficiency. This becomes especially attractive for on-chip implementation using dedicated neuromorphic hardware. However, both spiking neural networks and neuromorphic hardware have historically found difficulties in implementing efficient, effective learning rules. The best-known spiking neural network learning paradigm is Spike Timing Dependent Plasticity (STDP) which adjusts the strength of a connection in response to the time difference between the pre- and post-synaptic spikes. Approaches that relate learning features to the membrane potential of the post-synaptic neuron have emerged as possible alternatives to the more common STDP rule, with various implementations and approximations. Here we use a new type of neuromorphic hardware, SpiNNaker, which represents the flexible "neuromimetic" architecture, to demonstrate a new approach to this problem. Based on the standard STDP algorithm with modifications and approximations, a new rule, called STDP TTS (Time-To-Spike) relates the membrane potential with the Long Term Potentiation (LTP) part of the basic STDP rule. Meanwhile, we use the standard STDP rule for the Long Term Depression (LTD) part of the algorithm. We show that on the basis of the membrane potential it is possible to make a statistical prediction of the time needed by the neuron to reach the threshold, and therefore the LTP part of the STDP algorithm can be triggered when the neuron receives a spike. In our system these approximations allow efficient memory access, reducing the overall computational time and the memory bandwidth required. The improvements here presented are significant for real-time applications such as the ones for which the SpiNNaker system has been designed. We present simulation results that show the efficacy of this algorithm using one or more input patterns repeated over the whole time of the simulation. On-chip results show that the STDP TTS algorithm allows the neural network to adapt and detect the incoming pattern with improvements both in the reliability of, and the time required for, consistent output. Through the approximations we suggest in this paper, we introduce a learning rule that is easy to implement both in event-driven simulators and in dedicated hardware, reducing computational complexity relative to the standard STDP rule. Such a rule offers a promising solution, complementary to standard STDP evaluation algorithms, for real-time learning using spiking neural networks in time-critical applications. Copyright © 2012 Elsevier Ltd. All rights reserved.

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.

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

Students' Framing of Language Learning Practices in Social Networking Sites

ERIC Educational Resources Information Center

Lantz-Andersson, Annika; Vigmo, Sylvi; Bowen, Rhonwen

2012-01-01

The amount of time that people, especially young people, spend on communicative activities in social media is rapidly increasing. We are facing new arenas with great potential for learning in general and for language learning in particular, but their impact on learning is not yet acknowledged as such in educational practice (e.g., Conole, 2010;…

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.

Forecasting financial asset processes: stochastic dynamics via learning neural networks.

PubMed

Giebel, S; Rainer, M

2010-01-01

Models for financial asset dynamics usually take into account their inherent unpredictable nature by including a suitable stochastic component into their process. Unknown (forward) values of financial assets (at a given time in the future) are usually estimated as expectations of the stochastic asset under a suitable risk-neutral measure. This estimation requires the stochastic model to be calibrated to some history of sufficient length in the past. Apart from inherent limitations, due to the stochastic nature of the process, the predictive power is also limited by the simplifying assumptions of the common calibration methods, such as maximum likelihood estimation and regression methods, performed often without weights on the historic time series, or with static weights only. Here we propose a novel method of "intelligent" calibration, using learning neural networks in order to dynamically adapt the parameters of the stochastic model. Hence we have a stochastic process with time dependent parameters, the dynamics of the parameters being themselves learned continuously by a neural network. The back propagation in training the previous weights is limited to a certain memory length (in the examples we consider 10 previous business days), which is similar to the maximal time lag of autoregressive processes. We demonstrate the learning efficiency of the new algorithm by tracking the next-day forecasts for the EURTRY and EUR-HUF exchange rates each.

Staged Inference using Conditional Deep Learning for energy efficient real-time smart diagnosis.

PubMed

Parsa, Maryam; Panda, Priyadarshini; Sen, Shreyas; Roy, Kaushik

2017-07-01

Recent progress in biosensor technology and wearable devices has created a formidable opportunity for remote healthcare monitoring systems as well as real-time diagnosis and disease prevention. The use of data mining techniques is indispensable for analysis of the large pool of data generated by the wearable devices. Deep learning is among the promising methods for analyzing such data for healthcare applications and disease diagnosis. However, the conventional deep neural networks are computationally intensive and it is impractical to use them in real-time diagnosis with low-powered on-body devices. We propose Staged Inference using Conditional Deep Learning (SICDL), as an energy efficient approach for creating healthcare monitoring systems. For smart diagnostics, we observe that all diagnoses are not equally challenging. The proposed approach thus decomposes the diagnoses into preliminary analysis (such as healthy vs unhealthy) and detailed analysis (such as identifying the specific type of cardio disease). The preliminary diagnosis is conducted real-time with a low complexity neural network realized on the resource-constrained on-body device. The detailed diagnosis requires a larger network that is implemented remotely in cloud and is conditionally activated only for detailed diagnosis (unhealthy individuals). We evaluated the proposed approach using available physiological sensor data from Physionet databases, and achieved 38% energy reduction in comparison to the conventional deep learning approach.

Energy-efficient STDP-based learning circuits with memristor synapses

NASA Astrophysics Data System (ADS)

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

2014-05-01

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

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

PubMed

Schmitt, Michael

2004-09-01

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

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.

On the asymptotic equivalence between differential Hebbian and temporal difference learning.

PubMed

Kolodziejski, Christoph; Porr, Bernd; Wörgötter, Florentin

2009-04-01

In this theoretical contribution, we provide mathematical proof that two of the most important classes of network learning-correlation-based differential Hebbian learning and reward-based temporal difference learning-are asymptotically equivalent when timing the learning with a modulatory signal. This opens the opportunity to consistently reformulate most of the abstract reinforcement learning framework from a correlation-based perspective more closely related to the biophysics of neurons.

An Indoor Positioning Technique Based on a Feed-Forward Artificial Neural Network Using Levenberg-Marquardt Learning Method

NASA Astrophysics Data System (ADS)

Pahlavani, P.; Gholami, A.; Azimi, S.

2017-09-01

This paper presents an indoor positioning technique based on a multi-layer feed-forward (MLFF) artificial neural networks (ANN). Most of the indoor received signal strength (RSS)-based WLAN positioning systems use the fingerprinting technique that can be divided into two phases: the offline (calibration) phase and the online (estimation) phase. In this paper, RSSs were collected for all references points in four directions and two periods of time (Morning and Evening). Hence, RSS readings were sampled at a regular time interval and specific orientation at each reference point. The proposed ANN based model used Levenberg-Marquardt algorithm for learning and fitting the network to the training data. This RSS readings in all references points and the known position of these references points was prepared for training phase of the proposed MLFF neural network. Eventually, the average positioning error for this network using 30% check and validation data was computed approximately 2.20 meter.

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.

The Slothfulness Quotient.

ERIC Educational Resources Information Center

Joyce, Peter J.

2001-01-01

E-Learning eliminates time and distance barriers, creating universal learning-on-demand opportunities. Cisco Systems has invested over $50 million in the world's largest e-learning laboratory. Starting with 64 academies in 7 U.S. states in 1997, the Networking Academy program now serves 140,000 students in over 5,800 sites in 96 countries. (MLH)

Phonological Networks and New Word Learning

ERIC Educational Resources Information Center

Service, Elisabet

2006-01-01

The first report of a connection between vocabulary learning and phonological short-term memory was published in 1988 (Baddeley, Papagno, & Vallar, 1988). At that time, both Susan Gathercole and I were involved in longitudinal studies, investigating the relation between nonword repetition and language learning. We both found a connection. Now,…

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.

Application of machine learning methods for traffic signs recognition

NASA Astrophysics Data System (ADS)

Filatov, D. V.; Ignatev, K. V.; Deviatkin, A. V.; Serykh, E. V.

2018-02-01

This paper focuses on solving a relevant and pressing safety issue on intercity roads. Two approaches were considered for solving the problem of traffic signs recognition; the approaches involved neural networks to analyze images obtained from a camera in the real-time mode. The first approach is based on a sequential image processing. At the initial stage, with the help of color filters and morphological operations (dilatation and erosion), the area containing the traffic sign is located on the image, then the selected and scaled fragment of the image is analyzed using a feedforward neural network to determine the meaning of the found traffic sign. Learning of the neural network in this approach is carried out using a backpropagation method. The second approach involves convolution neural networks at both stages, i.e. when searching and selecting the area of the image containing the traffic sign, and when determining its meaning. Learning of the neural network in the second approach is carried out using the intersection over union function and a loss function. For neural networks to learn and the proposed algorithms to be tested, a series of videos from a dash cam were used that were shot under various weather and illumination conditions. As a result, the proposed approaches for traffic signs recognition were analyzed and compared by key indicators such as recognition rate percentage and the complexity of neural networks’ learning process.

Function approximation using combined unsupervised and supervised learning.

PubMed

Andras, Peter

2014-03-01

Function approximation is one of the core tasks that are solved using neural networks in the context of many engineering problems. However, good approximation results need good sampling of the data space, which usually requires exponentially increasing volume of data as the dimensionality of the data increases. At the same time, often the high-dimensional data is arranged around a much lower dimensional manifold. Here we propose the breaking of the function approximation task for high-dimensional data into two steps: (1) the mapping of the high-dimensional data onto a lower dimensional space corresponding to the manifold on which the data resides and (2) the approximation of the function using the mapped lower dimensional data. We use over-complete self-organizing maps (SOMs) for the mapping through unsupervised learning, and single hidden layer neural networks for the function approximation through supervised learning. We also extend the two-step procedure by considering support vector machines and Bayesian SOMs for the determination of the best parameters for the nonlinear neurons in the hidden layer of the neural networks used for the function approximation. We compare the approximation performance of the proposed neural networks using a set of functions and show that indeed the neural networks using combined unsupervised and supervised learning outperform in most cases the neural networks that learn the function approximation using the original high-dimensional data.

Road Network State Estimation Using Random Forest Ensemble Learning

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

Hou, Yi; Edara, Praveen; Chang, Yohan

Network-scale travel time prediction not only enables traffic management centers (TMC) to proactively implement traffic management strategies, but also allows travelers make informed decisions about route choices between various origins and destinations. In this paper, a random forest estimator was proposed to predict travel time in a network. The estimator was trained using two years of historical travel time data for a case study network in St. Louis, Missouri. Both temporal and spatial effects were considered in the modeling process. The random forest models predicted travel times accurately during both congested and uncongested traffic conditions. The computational times for themore » models were low, thus useful for real-time traffic management and traveler information applications.« less

Active learning of cortical connectivity from two-photon imaging data

PubMed Central

Wang, Ye; Dunson, David; Sapiro, Guillermo; Ringach, Dario

2018-01-01

Understanding how groups of neurons interact within a network is a fundamental question in system neuroscience. Instead of passively observing the ongoing activity of a network, we can typically perturb its activity, either by external sensory stimulation or directly via techniques such as two-photon optogenetics. A natural question is how to use such perturbations to identify the connectivity of the network efficiently. Here we introduce a method to infer sparse connectivity graphs from in-vivo, two-photon imaging of population activity in response to external stimuli. A novel aspect of the work is the introduction of a recommended distribution, incrementally learned from the data, to optimally refine the inferred network. Unlike existing system identification techniques, this “active learning” method automatically focuses its attention on key undiscovered areas of the network, instead of targeting global uncertainty indicators like parameter variance. We show how active learning leads to faster inference while, at the same time, provides confidence intervals for the network parameters. We present simulations on artificial small-world networks to validate the methods and apply the method to real data. Analysis of frequency of motifs recovered show that cortical networks are consistent with a small-world topology model. PMID:29718955

Reinforcement learning design-based adaptive tracking control with less learning parameters for nonlinear discrete-time MIMO systems.

PubMed

Liu, Yan-Jun; Tang, Li; Tong, Shaocheng; Chen, C L Philip; Li, Dong-Juan

2015-01-01

Based on the neural network (NN) approximator, an online reinforcement learning algorithm is proposed for a class of affine multiple input and multiple output (MIMO) nonlinear discrete-time systems with unknown functions and disturbances. In the design procedure, two networks are provided where one is an action network to generate an optimal control signal and the other is a critic network to approximate the cost function. An optimal control signal and adaptation laws can be generated based on two NNs. In the previous approaches, the weights of critic and action networks are updated based on the gradient descent rule and the estimations of optimal weight vectors are directly adjusted in the design. Consequently, compared with the existing results, the main contributions of this paper are: 1) only two parameters are needed to be adjusted, and thus the number of the adaptation laws is smaller than the previous results and 2) the updating parameters do not depend on the number of the subsystems for MIMO systems and the tuning rules are replaced by adjusting the norms on optimal weight vectors in both action and critic networks. It is proven that the tracking errors, the adaptation laws, and the control inputs are uniformly bounded using Lyapunov analysis method. The simulation examples are employed to illustrate the effectiveness of the proposed algorithm.

Validating the Use of Deep Learning Neural Networks for Correction of Large Hydrometric Datasets

NASA Astrophysics Data System (ADS)

Frazier, N.; Ogden, F. L.; Regina, J. A.; Cheng, Y.

2017-12-01

Collection and validation of Earth systems data can be time consuming and labor intensive. In particular, high resolution hydrometric data, including rainfall and streamflow measurements, are difficult to obtain due to a multitude of complicating factors. Measurement equipment is subject to clogs, environmental disturbances, and sensor drift. Manual intervention is typically required to identify, correct, and validate these data. Weirs can become clogged and the pressure transducer may float or drift over time. We typically employ a graphical tool called Time Series Editor to manually remove clogs and sensor drift from the data. However, this process is highly subjective and requires hydrological expertise. Two different people may produce two different data sets. To use this data for scientific discovery and model validation, a more consistent method is needed to processes this field data. Deep learning neural networks have proved to be excellent mechanisms for recognizing patterns in data. We explore the use of Recurrent Neural Networks (RNN) to capture the patterns in the data over time using various gating mechanisms (LSTM and GRU), network architectures, and hyper-parameters to build an automated data correction model. We also explore the required amount of manually corrected training data required to train the network for reasonable accuracy. The benefits of this approach are that the time to process a data set is significantly reduced, and the results are 100% reproducible after training is complete. Additionally, we train the RNN and calibrate a physically-based hydrological model against the same portion of data. Both the RNN and the model are applied to the remaining data using a split-sample methodology. Performance of the machine learning is evaluated for plausibility by comparing with the output of the hydrological model, and this analysis identifies potential periods where additional investigation is warranted.

Hybrid machine learning technique for forecasting Dhaka stock market timing decisions.

PubMed

Banik, Shipra; Khodadad Khan, A F M; Anwer, Mohammad

2014-01-01

Forecasting stock market has been a difficult job for applied researchers owing to nature of facts which is very noisy and time varying. However, this hypothesis has been featured by several empirical experiential studies and a number of researchers have efficiently applied machine learning techniques to forecast stock market. This paper studied stock prediction for the use of investors. It is always true that investors typically obtain loss because of uncertain investment purposes and unsighted assets. This paper proposes a rough set model, a neural network model, and a hybrid neural network and rough set model to find optimal buy and sell of a share on Dhaka stock exchange. Investigational findings demonstrate that our proposed hybrid model has higher precision than the single rough set model and the neural network model. We believe this paper findings will help stock investors to decide about optimal buy and/or sell time on Dhaka stock exchange.

Hybrid Machine Learning Technique for Forecasting Dhaka Stock Market Timing Decisions

PubMed Central

Banik, Shipra; Khodadad Khan, A. F. M.; Anwer, Mohammad

2014-01-01

Forecasting stock market has been a difficult job for applied researchers owing to nature of facts which is very noisy and time varying. However, this hypothesis has been featured by several empirical experiential studies and a number of researchers have efficiently applied machine learning techniques to forecast stock market. This paper studied stock prediction for the use of investors. It is always true that investors typically obtain loss because of uncertain investment purposes and unsighted assets. This paper proposes a rough set model, a neural network model, and a hybrid neural network and rough set model to find optimal buy and sell of a share on Dhaka stock exchange. Investigational findings demonstrate that our proposed hybrid model has higher precision than the single rough set model and the neural network model. We believe this paper findings will help stock investors to decide about optimal buy and/or sell time on Dhaka stock exchange. PMID:24701205

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

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

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

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

Online Distributed Learning Over Networks in RKH Spaces Using Random Fourier Features

NASA Astrophysics Data System (ADS)

Bouboulis, Pantelis; Chouvardas, Symeon; Theodoridis, Sergios

2018-04-01

We present a novel diffusion scheme for online kernel-based learning over networks. So far, a major drawback of any online learning algorithm, operating in a reproducing kernel Hilbert space (RKHS), is the need for updating a growing number of parameters as time iterations evolve. Besides complexity, this leads to an increased need of communication resources, in a distributed setting. In contrast, the proposed method approximates the solution as a fixed-size vector (of larger dimension than the input space) using Random Fourier Features. This paves the way to use standard linear combine-then-adapt techniques. To the best of our knowledge, this is the first time that a complete protocol for distributed online learning in RKHS is presented. Conditions for asymptotic convergence and boundness of the networkwise regret are also provided. The simulated tests illustrate the performance of the proposed scheme.

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.

Interarrival times of message propagation on directed networks.

PubMed

Mihaljev, Tamara; de Arcangelis, Lucilla; Herrmann, Hans J

2011-08-01

One of the challenges in fighting cybercrime is to understand the dynamics of message propagation on botnets, networks of infected computers used to send viruses, unsolicited commercial emails (SPAM) or denial of service attacks. We map this problem to the propagation of multiple random walkers on directed networks and we evaluate the interarrival time distribution between successive walkers arriving at a target. We show that the temporal organization of this process, which models information propagation on unstructured peer to peer networks, has the same features as SPAM reaching a single user. We study the behavior of the message interarrival time distribution on three different network topologies using two different rules for sending messages. In all networks the propagation is not a pure Poisson process. It shows universal features on Poissonian networks and a more complex behavior on scale free networks. Results open the possibility to indirectly learn about the process of sending messages on networks with unknown topologies, by studying interarrival times at any node of the network.

Interarrival times of message propagation on directed networks

NASA Astrophysics Data System (ADS)

Mihaljev, Tamara; de Arcangelis, Lucilla; Herrmann, Hans J.

2011-08-01

One of the challenges in fighting cybercrime is to understand the dynamics of message propagation on botnets, networks of infected computers used to send viruses, unsolicited commercial emails (SPAM) or denial of service attacks. We map this problem to the propagation of multiple random walkers on directed networks and we evaluate the interarrival time distribution between successive walkers arriving at a target. We show that the temporal organization of this process, which models information propagation on unstructured peer to peer networks, has the same features as SPAM reaching a single user. We study the behavior of the message interarrival time distribution on three different network topologies using two different rules for sending messages. In all networks the propagation is not a pure Poisson process. It shows universal features on Poissonian networks and a more complex behavior on scale free networks. Results open the possibility to indirectly learn about the process of sending messages on networks with unknown topologies, by studying interarrival times at any node of the network.

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.

Energy landscapes for a machine-learning prediction of patient discharge

NASA Astrophysics Data System (ADS)

Das, Ritankar; Wales, David J.

2016-06-01

The energy landscapes framework is applied to a configuration space generated by training the parameters of a neural network. In this study the input data consists of time series for a collection of vital signs monitored for hospital patients, and the outcomes are patient discharge or continued hospitalisation. Using machine learning as a predictive diagnostic tool to identify patterns in large quantities of electronic health record data in real time is a very attractive approach for supporting clinical decisions, which have the potential to improve patient outcomes and reduce waiting times for discharge. Here we report some preliminary analysis to show how machine learning might be applied. In particular, we visualize the fitting landscape in terms of locally optimal neural networks and the connections between them in parameter space. We anticipate that these results, and analogues of thermodynamic properties for molecular systems, may help in the future design of improved predictive tools.

Reducing weight precision of convolutional neural networks towards large-scale on-chip image recognition

NASA Astrophysics Data System (ADS)

Ji, Zhengping; Ovsiannikov, Ilia; Wang, Yibing; Shi, Lilong; Zhang, Qiang

2015-05-01

In this paper, we develop a server-client quantization scheme to reduce bit resolution of deep learning architecture, i.e., Convolutional Neural Networks, for image recognition tasks. Low bit resolution is an important factor in bringing the deep learning neural network into hardware implementation, which directly determines the cost and power consumption. We aim to reduce the bit resolution of the network without sacrificing its performance. To this end, we design a new quantization algorithm called supervised iterative quantization to reduce the bit resolution of learned network weights. In the training stage, the supervised iterative quantization is conducted via two steps on server - apply k-means based adaptive quantization on learned network weights and retrain the network based on quantized weights. These two steps are alternated until the convergence criterion is met. In this testing stage, the network configuration and low-bit weights are loaded to the client hardware device to recognize coming input in real time, where optimized but expensive quantization becomes infeasible. Considering this, we adopt a uniform quantization for the inputs and internal network responses (called feature maps) to maintain low on-chip expenses. The Convolutional Neural Network with reduced weight and input/response precision is demonstrated in recognizing two types of images: one is hand-written digit images and the other is real-life images in office scenarios. Both results show that the new network is able to achieve the performance of the neural network with full bit resolution, even though in the new network the bit resolution of both weight and input are significantly reduced, e.g., from 64 bits to 4-5 bits.

Real-time cerebellar neuroprosthetic system based on a spiking neural network model of motor learning

NASA Astrophysics Data System (ADS)

Xu, Tao; Xiao, Na; Zhai, Xiaolong; Chan, Pak Kwan; Tin, Chung

2018-02-01

Objective. Damage to the brain, as a result of various medical conditions, impacts the everyday life of patients and there is still no complete cure to neurological disorders. Neuroprostheses that can functionally replace the damaged neural circuit have recently emerged as a possible solution to these problems. Here we describe the development of a real-time cerebellar neuroprosthetic system to substitute neural function in cerebellar circuitry for learning delay eyeblink conditioning (DEC). Approach. The system was empowered by a biologically realistic spiking neural network (SNN) model of the cerebellar neural circuit, which considers the neuronal population and anatomical connectivity of the network. The model simulated synaptic plasticity critical for learning DEC. This SNN model was carefully implemented on a field programmable gate array (FPGA) platform for real-time simulation. This hardware system was interfaced in in vivo experiments with anesthetized rats and it used neural spikes recorded online from the animal to learn and trigger conditioned eyeblink in the animal during training. Main results. This rat-FPGA hybrid system was able to process neuronal spikes in real-time with an embedded cerebellum model of ~10 000 neurons and reproduce learning of DEC with different inter-stimulus intervals. Our results validated that the system performance is physiologically relevant at both the neural (firing pattern) and behavioral (eyeblink pattern) levels. Significance. This integrated system provides the sufficient computation power for mimicking the cerebellar circuit in real-time. The system interacts with the biological system naturally at the spike level and can be generalized for including other neural components (neuron types and plasticity) and neural functions for potential neuroprosthetic applications.

Indirect iterative learning control for a discrete visual servo without a camera-robot model.

PubMed

Jiang, Ping; Bamforth, Leon C A; Feng, Zuren; Baruch, John E F; Chen, YangQuan

2007-08-01

This paper presents a discrete learning controller for vision-guided robot trajectory imitation with no prior knowledge of the camera-robot model. A teacher demonstrates a desired movement in front of a camera, and then, the robot is tasked to replay it by repetitive tracking. The imitation procedure is considered as a discrete tracking control problem in the image plane, with an unknown and time-varying image Jacobian matrix. Instead of updating the control signal directly, as is usually done in iterative learning control (ILC), a series of neural networks are used to approximate the unknown Jacobian matrix around every sample point in the demonstrated trajectory, and the time-varying weights of local neural networks are identified through repetitive tracking, i.e., indirect ILC. This makes repetitive segmented training possible, and a segmented training strategy is presented to retain the training trajectories solely within the effective region for neural network approximation. However, a singularity problem may occur if an unmodified neural-network-based Jacobian estimation is used to calculate the robot end-effector velocity. A new weight modification algorithm is proposed which ensures invertibility of the estimation, thus circumventing the problem. Stability is further discussed, and the relationship between the approximation capability of the neural network and the tracking accuracy is obtained. Simulations and experiments are carried out to illustrate the validity of the proposed controller for trajectory imitation of robot manipulators with unknown time-varying Jacobian matrices.

Supervised machine learning on a network scale: application to seismic event classification and detection

NASA Astrophysics Data System (ADS)

Reynen, Andrew; Audet, Pascal

2017-09-01

A new method using a machine learning technique is applied to event classification and detection at seismic networks. This method is applicable to a variety of network sizes and settings. The algorithm makes use of a small catalogue of known observations across the entire network. Two attributes, the polarization and frequency content, are used as input to regression. These attributes are extracted at predicted arrival times for P and S waves using only an approximate velocity model, as attributes are calculated over large time spans. This method of waveform characterization is shown to be able to distinguish between blasts and earthquakes with 99 per cent accuracy using a network of 13 stations located in Southern California. The combination of machine learning with generalized waveform features is further applied to event detection in Oklahoma, United States. The event detection algorithm makes use of a pair of unique seismic phases to locate events, with a precision directly related to the sampling rate of the generalized waveform features. Over a week of data from 30 stations in Oklahoma, United States are used to automatically detect 25 times more events than the catalogue of the local geological survey, with a false detection rate of less than 2 per cent. This method provides a highly confident way of detecting and locating events. Furthermore, a large number of seismic events can be automatically detected with low false alarm, allowing for a larger automatic event catalogue with a high degree of trust.

Information recall using relative spike timing in a spiking neural network.

PubMed

Sterne, Philip

2012-08-01

We present a neural network that is capable of completing and correcting a spiking pattern given only a partial, noisy version. It operates in continuous time and represents information using the relative timing of individual spikes. The network is capable of correcting and recalling multiple patterns simultaneously. We analyze the network's performance in terms of information recall. We explore two measures of the capacity of the network: one that values the accurate recall of individual spike times and another that values only the presence or absence of complete patterns. Both measures of information are found to scale linearly in both the number of neurons and the period of the patterns, suggesting these are natural measures of network information. We show a smooth transition from encodings that provide precise spike times to flexible encodings that can encode many scenes. This makes it plausible that many diverse tasks could be learned with such an encoding.

Inferring causal molecular networks: empirical assessment through a community-based effort.

PubMed

Hill, Steven M; Heiser, Laura M; Cokelaer, Thomas; Unger, Michael; Nesser, Nicole K; Carlin, Daniel E; Zhang, Yang; Sokolov, Artem; Paull, Evan O; Wong, Chris K; Graim, Kiley; Bivol, Adrian; Wang, Haizhou; Zhu, Fan; Afsari, Bahman; Danilova, Ludmila V; Favorov, Alexander V; Lee, Wai Shing; Taylor, Dane; Hu, Chenyue W; Long, Byron L; Noren, David P; Bisberg, Alexander J; Mills, Gordon B; Gray, Joe W; Kellen, Michael; Norman, Thea; Friend, Stephen; Qutub, Amina A; Fertig, Elana J; Guan, Yuanfang; Song, Mingzhou; Stuart, Joshua M; Spellman, Paul T; Koeppl, Heinz; Stolovitzky, Gustavo; Saez-Rodriguez, Julio; Mukherjee, Sach

2016-04-01

It remains unclear whether causal, rather than merely correlational, relationships in molecular networks can be inferred in complex biological settings. Here we describe the HPN-DREAM network inference challenge, which focused on learning causal influences in signaling networks. We used phosphoprotein data from cancer cell lines as well as in silico data from a nonlinear dynamical model. Using the phosphoprotein data, we scored more than 2,000 networks submitted by challenge participants. The networks spanned 32 biological contexts and were scored in terms of causal validity with respect to unseen interventional data. A number of approaches were effective, and incorporating known biology was generally advantageous. Additional sub-challenges considered time-course prediction and visualization. Our results suggest that learning causal relationships may be feasible in complex settings such as disease states. Furthermore, our scoring approach provides a practical way to empirically assess inferred molecular networks in a causal sense.

Smart-Grid Backbone Network Real-Time Delay Reduction via Integer Programming.

PubMed

Pagadrai, Sasikanth; Yilmaz, Muhittin; Valluri, Pratyush

2016-08-01

This research investigates an optimal delay-based virtual topology design using integer linear programming (ILP), which is applied to the current backbone networks such as smart-grid real-time communication systems. A network traffic matrix is applied and the corresponding virtual topology problem is solved using the ILP formulations that include a network delay-dependent objective function and lightpath routing, wavelength assignment, wavelength continuity, flow routing, and traffic loss constraints. The proposed optimization approach provides an efficient deterministic integration of intelligent sensing and decision making, and network learning features for superior smart grid operations by adaptively responding the time-varying network traffic data as well as operational constraints to maintain optimal virtual topologies. A representative optical backbone network has been utilized to demonstrate the proposed optimization framework whose simulation results indicate that superior smart-grid network performance can be achieved using commercial networks and integer programming.

Real-time learning of predictive recognition categories that chunk sequences of items stored in working memory

PubMed Central

Kazerounian, Sohrob; Grossberg, Stephen

2014-01-01

How are sequences of events that are temporarily stored in a cognitive working memory unitized, or chunked, through learning? Such sequential learning is needed by the brain in order to enable language, spatial understanding, and motor skills to develop. In particular, how does the brain learn categories, or list chunks, that become selectively tuned to different temporal sequences of items in lists of variable length as they are stored in working memory, and how does this learning process occur in real time? The present article introduces a neural model that simulates learning of such list chunks. In this model, sequences of items are temporarily stored in an Item-and-Order, or competitive queuing, working memory before learning categorizes them using a categorization network, called a Masking Field, which is a self-similar, multiple-scale, recurrent on-center off-surround network that can weigh the evidence for variable-length sequences of items as they are stored in the working memory through time. A Masking Field hereby activates the learned list chunks that represent the most predictive item groupings at any time, while suppressing less predictive chunks. In a network with a given number of input items, all possible ordered sets of these item sequences, up to a fixed length, can be learned with unsupervised or supervised learning. The self-similar multiple-scale properties of Masking Fields interacting with an Item-and-Order working memory provide a natural explanation of George Miller's Magical Number Seven and Nelson Cowan's Magical Number Four. The article explains why linguistic, spatial, and action event sequences may all be stored by Item-and-Order working memories that obey similar design principles, and thus how the current results may apply across modalities. Item-and-Order properties may readily be extended to Item-Order-Rank working memories in which the same item can be stored in multiple list positions, or ranks, as in the list ABADBD. Comparisons with other models, including TRACE, MERGE, and TISK, are made. PMID:25339918

Backpropagation and ordered derivatives in the time scales calculus.

PubMed

Seiffertt, John; Wunsch, Donald C

2010-08-01

Backpropagation is the most widely used neural network learning technique. It is based on the mathematical notion of an ordered derivative. In this paper, we present a formulation of ordered derivatives and the backpropagation training algorithm using the important emerging area of mathematics known as the time scales calculus. This calculus, with its potential for application to a wide variety of inter-disciplinary problems, is becoming a key area of mathematics. It is capable of unifying continuous and discrete analysis within one coherent theoretical framework. Using this calculus, we present here a generalization of backpropagation which is appropriate for cases beyond the specifically continuous or discrete. We develop a new multivariate chain rule of this calculus, define ordered derivatives on time scales, prove a key theorem about them, and derive the backpropagation weight update equations for a feedforward multilayer neural network architecture. By drawing together the time scales calculus and the area of neural network learning, we present the first connection of two major fields of research.

Locomotion training of legged robots using hybrid machine learning techniques

NASA Technical Reports Server (NTRS)

Simon, William E.; Doerschuk, Peggy I.; Zhang, Wen-Ran; Li, Andrew L.

1995-01-01

In this study artificial neural networks and fuzzy logic are used to control the jumping behavior of a three-link uniped robot. The biped locomotion control problem is an increment of the uniped locomotion control. Study of legged locomotion dynamics indicates that a hierarchical controller is required to control the behavior of a legged robot. A structured control strategy is suggested which includes navigator, motion planner, biped coordinator and uniped controllers. A three-link uniped robot simulation is developed to be used as the plant. Neurocontrollers were trained both online and offline. In the case of on-line training, a reinforcement learning technique was used to train the neurocontroller to make the robot jump to a specified height. After several hundred iterations of training, the plant output achieved an accuracy of 7.4%. However, when jump distance and body angular momentum were also included in the control objectives, training time became impractically long. In the case of off-line training, a three-layered backpropagation (BP) network was first used with three inputs, three outputs and 15 to 40 hidden nodes. Pre-generated data were presented to the network with a learning rate as low as 0.003 in order to reach convergence. The low learning rate required for convergence resulted in a very slow training process which took weeks to learn 460 examples. After training, performance of the neurocontroller was rather poor. Consequently, the BP network was replaced by a Cerebeller Model Articulation Controller (CMAC) network. Subsequent experiments described in this document show that the CMAC network is more suitable to the solution of uniped locomotion control problems in terms of both learning efficiency and performance. A new approach is introduced in this report, viz., a self-organizing multiagent cerebeller model for fuzzy-neural control of uniped locomotion is suggested to improve training efficiency. This is currently being evaluated for a possible patent by NASA, Johnson Space Center. An alternative modular approach is also developed which uses separate controllers for each stage of the running stride. A self-organizing fuzzy-neural controller controls the height, distance and angular momentum of the stride. A CMAC-based controller controls the movement of the leg from the time the foot leaves the ground to the time of landing. Because the leg joints are controlled at each time step during flight, movement is smooth and obstacles can be avoided. Initial results indicate that this approach can yield fast, accurate results.

Mobile robots exploration through cnn-based reinforcement learning.

PubMed

Tai, Lei; Liu, Ming

2016-01-01

Exploration in an unknown environment is an elemental application for mobile robots. In this paper, we outlined a reinforcement learning method aiming for solving the exploration problem in a corridor environment. The learning model took the depth image from an RGB-D sensor as the only input. The feature representation of the depth image was extracted through a pre-trained convolutional-neural-networks model. Based on the recent success of deep Q-network on artificial intelligence, the robot controller achieved the exploration and obstacle avoidance abilities in several different simulated environments. It is the first time that the reinforcement learning is used to build an exploration strategy for mobile robots through raw sensor information.

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.

Modeling and Intervening across Time in Scientific Inquiry Exploratory Learning Environment

ERIC Educational Resources Information Center

Ting, Choo-Yee; Phon-Amnuaisuk, Somnuk; Chong, Yen-Kuan

2008-01-01

This article aims at discussing how Dynamic Decision Network (DDN) can be employed to tackle the challenges in modeling temporally variable scientific inquiry skills and provision of adaptive pedagogical interventions in INQPRO, a scientific inquiry exploratory learning environment for learning O'level Physics. We begin with an overview of INQPRO…

Recovering time-varying networks of dependencies in social and biological studies.

PubMed

Ahmed, Amr; Xing, Eric P

2009-07-21

A plausible representation of the relational information among entities in dynamic systems such as a living cell or a social community is a stochastic network that is topologically rewiring and semantically evolving over time. Although there is a rich literature in modeling static or temporally invariant networks, little has been done toward recovering the network structure when the networks are not observable in a dynamic context. In this article, we present a machine learning method called TESLA, which builds on a temporally smoothed l(1)-regularized logistic regression formalism that can be cast as a standard convex-optimization problem and solved efficiently by using generic solvers scalable to large networks. We report promising results on recovering simulated time-varying networks and on reverse engineering the latent sequence of temporally rewiring political and academic social networks from longitudinal data, and the evolving gene networks over >4,000 genes during the life cycle of Drosophila melanogaster from a microarray time course at a resolution limited only by sample frequency.

Providing Effective Learner Support for Part-Time Learners. Research Report

ERIC Educational Resources Information Center

Barker, Philip; Crawley, Jim

2005-01-01

Learner support, defined as the strategies which empower learners to establish and fulfill their learning, career and personal potential, continues to be a key issue in current thinking in the post-16 education sector. An earlier project report from the West Country Learning and Skills Research Network (WCLSRN) showed that part-time learners were…

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

PubMed Central

Yang, Xinyi

2016-01-01

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

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

PubMed

Pang, Shan; Yang, Xinyi

2016-01-01

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

Implementing Role-Changing Versus Time-Changing Innovations in Health Care: Differences in Helpfulness of Staff Improvement Teams, Management, and Network for Learning.

PubMed

Nembhard, Ingrid M; Morrow, Christopher T; Bradley, Elizabeth H

2015-12-01

Health care organizations often fail in their effort to implement care-improving innovations. This article differentiates role-changing innovations, altering what workers do, from time-changing innovations, altering when tasks are performed or for how long. We examine our hypothesis that the degree to which access to groups that can alter organizational learning--staff, management, and external network--facilitates implementation depends on innovation type. Our longitudinal study using ordinal logistic regression and survey data on 517 hospitals' implementation of evidence-based practices for treating heart attack confirmed our thesis for factors granting access to each group: improvement team's representativeness (of affected staff), senior management engagement, and network membership. Although team representativeness and network membership were positively associated with implementing role-changing practices, senior management engagement was not. In contrast, senior management engagement was positively associated with implementing time-changing practices, whereas team representativeness was not, and network membership was not unless there was limited management engagement. These findings advance implementation science by explaining mixed results across past studies: Nature of change for workers alters potential facilitators' effects on implementation. © The Author(s) 2015.

Smoothing of cost function leads to faster convergence of neural network learning

NASA Astrophysics Data System (ADS)

Xu, Li-Qun; Hall, Trevor J.

1994-03-01

One of the major problems in supervised learning of neural networks is the inevitable local minima inherent in the cost function f(W,D). This often makes classic gradient-descent-based learning algorithms that calculate the weight updates for each iteration according to (Delta) W(t) equals -(eta) (DOT)$DELwf(W,D) powerless. In this paper we describe a new strategy to solve this problem, which, adaptively, changes the learning rate and manipulates the gradient estimator simultaneously. The idea is to implicitly convert the local- minima-laden cost function f((DOT)) into a sequence of its smoothed versions {f(beta t)}Ttequals1, which, subject to the parameter (beta) t, bears less details at time t equals 1 and gradually more later on, the learning is actually performed on this sequence of functionals. The corresponding smoothed global minima obtained in this way, {Wt}Ttequals1, thus progressively approximate W-the desired global minimum. Experimental results on a nonconvex function minimization problem and a typical neural network learning task are given, analyses and discussions of some important issues are provided.

Neuromodulated Synaptic Plasticity on the SpiNNaker Neuromorphic System

PubMed Central

Mikaitis, Mantas; Pineda García, Garibaldi; Knight, James C.; Furber, Steve B.

2018-01-01

SpiNNaker is a digital neuromorphic architecture, designed specifically for the low power simulation of large-scale spiking neural networks at speeds close to biological real-time. Unlike other neuromorphic systems, SpiNNaker allows users to develop their own neuron and synapse models as well as specify arbitrary connectivity. As a result SpiNNaker has proved to be a powerful tool for studying different neuron models as well as synaptic plasticity—believed to be one of the main mechanisms behind learning and memory in the brain. A number of Spike-Timing-Dependent-Plasticity(STDP) rules have already been implemented on SpiNNaker and have been shown to be capable of solving various learning tasks in real-time. However, while STDP is an important biological theory of learning, it is a form of Hebbian or unsupervised learning and therefore does not explain behaviors that depend on feedback from the environment. Instead, learning rules based on neuromodulated STDP (three-factor learning rules) have been shown to be capable of solving reinforcement learning tasks in a biologically plausible manner. In this paper we demonstrate for the first time how a model of three-factor STDP, with the third-factor representing spikes from dopaminergic neurons, can be implemented on the SpiNNaker neuromorphic system. Using this learning rule we first show how reward and punishment signals can be delivered to a single synapse before going on to demonstrate it in a larger network which solves the credit assignment problem in a Pavlovian conditioning experiment. Because of its extra complexity, we find that our three-factor learning rule requires approximately 2× as much processing time as the existing SpiNNaker STDP learning rules. However, we show that it is still possible to run our Pavlovian conditioning model with up to 1 × 104 neurons in real-time, opening up new research opportunities for modeling behavioral learning on SpiNNaker. PMID:29535600

Online learning algorithm for time series forecasting suitable for low cost wireless sensor networks nodes.

PubMed

Pardo, Juan; Zamora-Martínez, Francisco; Botella-Rocamora, Paloma

2015-04-21

Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning) systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN) algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN) to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP) algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources.

Online Learning Algorithm for Time Series Forecasting Suitable for Low Cost Wireless Sensor Networks Nodes

PubMed Central

Pardo, Juan; Zamora-Martínez, Francisco; Botella-Rocamora, Paloma

2015-01-01

Time series forecasting is an important predictive methodology which can be applied to a wide range of problems. Particularly, forecasting the indoor temperature permits an improved utilization of the HVAC (Heating, Ventilating and Air Conditioning) systems in a home and thus a better energy efficiency. With such purpose the paper describes how to implement an Artificial Neural Network (ANN) algorithm in a low cost system-on-chip to develop an autonomous intelligent wireless sensor network. The present paper uses a Wireless Sensor Networks (WSN) to monitor and forecast the indoor temperature in a smart home, based on low resources and cost microcontroller technology as the 8051MCU. An on-line learning approach, based on Back-Propagation (BP) algorithm for ANNs, has been developed for real-time time series learning. It performs the model training with every new data that arrive to the system, without saving enormous quantities of data to create a historical database as usual, i.e., without previous knowledge. Consequently to validate the approach a simulation study through a Bayesian baseline model have been tested in order to compare with a database of a real application aiming to see the performance and accuracy. The core of the paper is a new algorithm, based on the BP one, which has been described in detail, and the challenge was how to implement a computational demanding algorithm in a simple architecture with very few hardware resources. PMID:25905698

Teachers Beware! The Dark Side of Social Networking

ERIC Educational Resources Information Center

Belch, Harry Ess

2012-01-01

Think teachers can post what they want on their own time? Think again. Many have lost their jobs over social networking gaffes in recent years. In this article, the author shares what he has learned about how school districts cope with teachers and online social networking sites, and offers recommendations to teachers who want to have an online…

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

Tracking Plasticity: Effects of Long-Term Rehearsal in Expert Dancers Encoding Music to Movement

PubMed Central

Bar, Rachel J.; DeSouza, Joseph F. X.

2016-01-01

Our knowledge of neural plasticity suggests that neural networks show adaptation to environmental and intrinsic change. In particular, studies investigating the neuroplastic changes associated with learning and practicing motor tasks have shown that practicing such tasks results in an increase in neural activation in several specific brain regions. However, studies comparing experts and non-experts suggest that experts employ less neuronal activation than non-experts when performing a familiar motor task. Here, we aimed to determine the long-term changes in neural networks associated with learning a new dance in professional ballet dancers over 34 weeks. Subjects visualized dance movements to music while undergoing fMRI scanning at four time points over 34-weeks. Results demonstrated that initial learning and performance at seven weeks led to increases in activation in cortical regions during visualization compared to the first week. However, at 34 weeks, the cortical networks showed reduced activation compared to week seven. Specifically, motor learning and performance over the 34 weeks showed the typical inverted-U-shaped function of learning. Further, our result demonstrate that learning of a motor sequence of dance movements to music in the real world can be visualized by expert dancers using fMRI and capture highly significant modeled fits of the brain network variance of BOLD signals from early learning to expert level performance. PMID:26824475

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.

Protein complexes, big data, machine learning and integrative proteomics: lessons learned over a decade of systematic analysis of protein interaction networks.

PubMed

Havugimana, Pierre C; Hu, Pingzhao; Emili, Andrew

2017-10-01

Elucidation of the networks of physical (functional) interactions present in cells and tissues is fundamental for understanding the molecular organization of biological systems, the mechanistic basis of essential and disease-related processes, and for functional annotation of previously uncharacterized proteins (via guilt-by-association or -correlation). After a decade in the field, we felt it timely to document our own experiences in the systematic analysis of protein interaction networks. Areas covered: Researchers worldwide have contributed innovative experimental and computational approaches that have driven the rapidly evolving field of 'functional proteomics'. These include mass spectrometry-based methods to characterize macromolecular complexes on a global-scale and sophisticated data analysis tools - most notably machine learning - that allow for the generation of high-quality protein association maps. Expert commentary: Here, we recount some key lessons learned, with an emphasis on successful workflows, and challenges, arising from our own and other groups' ongoing efforts to generate, interpret and report proteome-scale interaction networks in increasingly diverse biological contexts.

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.

Extraction of temporally correlated features from dynamic vision sensors with spike-timing-dependent plasticity.

PubMed

Bichler, Olivier; Querlioz, Damien; Thorpe, Simon J; Bourgoin, Jean-Philippe; Gamrat, Christian

2012-08-01

A biologically inspired approach to learning temporally correlated patterns from a spiking silicon retina is presented. Spikes are generated from the retina in response to relative changes in illumination at the pixel level and transmitted to a feed-forward spiking neural network. Neurons become sensitive to patterns of pixels with correlated activation times, in a fully unsupervised scheme. This is achieved using a special form of Spike-Timing-Dependent Plasticity which depresses synapses that did not recently contribute to the post-synaptic spike activation, regardless of their activation time. Competitive learning is implemented with lateral inhibition. When tested with real-life data, the system is able to extract complex and overlapping temporally correlated features such as car trajectories on a freeway, after only 10 min of traffic learning. Complete trajectories can be learned with a 98% detection rate using a second layer, still with unsupervised learning, and the system may be used as a car counter. The proposed neural network is extremely robust to noise and it can tolerate a high degree of synaptic and neuronal variability with little impact on performance. Such results show that a simple biologically inspired unsupervised learning scheme is capable of generating selectivity to complex meaningful events on the basis of relatively little sensory experience. Copyright © 2012 Elsevier Ltd. All rights reserved.

Slave to the Rhythm: Experimental Tests of a Model for Verbal Short-Term Memory and Long-Term Sequence Learning

ERIC Educational Resources Information Center

Hitch, Graham J.; Flude, Brenda; Burgess, Neil

2009-01-01

Three experiments tested predictions of a neural network model of phonological short-term memory that assumes separate representations for order and item information, order being coded via a context-timing signal [Burgess, N., & Hitch, G. J. (1999). Memory for serial order: A network model of the phonological loop and its timing. "Psychological…

Simulation of noisy dynamical system by Deep Learning

NASA Astrophysics Data System (ADS)

Yeo, Kyongmin

2017-11-01

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

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.

Reinforced two-step-ahead weight adjustment technique for online training of recurrent neural networks.

PubMed

Chang, Li-Chiu; Chen, Pin-An; Chang, Fi-John

2012-08-01

A reliable forecast of future events possesses great value. The main purpose of this paper is to propose an innovative learning technique for reinforcing the accuracy of two-step-ahead (2SA) forecasts. The real-time recurrent learning (RTRL) algorithm for recurrent neural networks (RNNs) can effectively model the dynamics of complex processes and has been used successfully in one-step-ahead forecasts for various time series. A reinforced RTRL algorithm for 2SA forecasts using RNNs is proposed in this paper, and its performance is investigated by two famous benchmark time series and a streamflow during flood events in Taiwan. Results demonstrate that the proposed reinforced 2SA RTRL algorithm for RNNs can adequately forecast the benchmark (theoretical) time series, significantly improve the accuracy of flood forecasts, and effectively reduce time-lag effects.

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

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.

From struggles to resource gains in interprofessional service networks: Key findings from a multiple case study.

PubMed

Toiviainen, Hanna; Kira, Mari

2017-07-01

In interprofessional service networks, employees cross professional boundaries to collaborate with colleagues and clients with expertise and values different from their own. It can be a struggle to adopt shared work practices and deal with "multivoicedness." At the same time, networks allow members to engage in meaningful service provision, gain a broader understanding of the service provided, and obtain social support. Intertwined network struggles and resource gains have received limited attention in the interprofessional care literature to date. The aim of the study was to investigate the learning potential of the co-existing struggles and resource gains. This article reports findings from two interprofessional networks. Interviews were conducted with 19 employees and thematically analysed. Three types of struggles and six types of resource gains of networking were identified. The struggles relate, first, to the assumptions of networking following similar practices to those in a home organisation; second, to the challenges of dealing with the multivoicedness of networking; and, third, to the experienced gap between the networking ideals and the reality of cooperation. At the same time, the network members experience gains in emotional resources (e.g., stronger sense of meaningfulness at work), cognitive resources (e.g., understanding the customer needs from alternative perspectives), and social resources (e.g., being able to rely on other professionals' competence). Learning potential emerged from the dynamics between coexisting struggles and resource gains.

Background rejection in NEXT using deep neural networks

DOE PAGES

Renner, J.; Farbin, A.; Vidal, J. Muñoz; ...

2017-01-16

Here, we investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of detailed track reconstruction. The differences in the topological signatures of background and signal events can be learned by deep neural networks via training over many thousands of events. These networks can then be used to classify further events as signal or background, providing an additional background rejection factor at an acceptable loss of efficiency. The networks trained in this study performed better than previous methods developed based on the usemore » of the same topological signatures by a factor of 1.2 to 1.6, and there is potential for further improvement.« less

Supervised Learning Applied to Air Traffic Trajectory Classification

NASA Technical Reports Server (NTRS)

Bosson, Christabelle S.; Nikoleris, Tasos

2018-01-01

Given the recent increase of interest in introducing new vehicle types and missions into the National Airspace System, a transition towards a more autonomous air traffic control system is required in order to enable and handle increased density and complexity. This paper presents an exploratory effort of the needed autonomous capabilities by exploring supervised learning techniques in the context of aircraft trajectories. In particular, it focuses on the application of machine learning algorithms and neural network models to a runway recognition trajectory-classification study. It investigates the applicability and effectiveness of various classifiers using datasets containing trajectory records for a month of air traffic. A feature importance and sensitivity analysis are conducted to challenge the chosen time-based datasets and the ten selected features. The study demonstrates that classification accuracy levels of 90% and above can be reached in less than 40 seconds of training for most machine learning classifiers when one track data point, described by the ten selected features at a particular time step, per trajectory is used as input. It also shows that neural network models can achieve similar accuracy levels but at higher training time costs.

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.

Boosting compound-protein interaction prediction by deep learning.

PubMed

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

2016-11-01

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

A 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.

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

PubMed

Benton, D C; Ferguson, S L

2017-03-01

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

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.

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

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

ERIC Educational Resources Information Center

Sorensen, Elsebeth Korsgaard

2007-01-01

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

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

ERIC Educational Resources Information Center

Ahmed, Iftikhar; Sadeq, Muhammad Jafar

2006-01-01

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

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…

Face to Facebook: Social Media and the Learning and Teaching Potential of Symmetrical, Synchronous Communication

ERIC Educational Resources Information Center

VanDoorn, George; Eklund, Antoinette A.

2013-01-01

Social networking offers teachers and learners exciting opportunities to communicate. Web 2.0 and its synchronous communications platforms provide new avenues for teachers to deliver curriculum and facilitate learning. Further, they provide new avenues for students to engage and intensify their own learning. Being able to chat in real-time with a…

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.).

On the Effectiveness of a Neural Network for Adaptive External Pacing.

ERIC Educational Resources Information Center

Montazemi, Ali R.; Wang, Feng

1995-01-01

Proposes a neural network model for an intelligent tutoring system featuring adaptive external control of student pacing. An experiment was conducted, and students using adaptive external pacing experienced improved mastery learning and increased motivation for time management. Contains 66 references. (JKP)

Deep neural networks to enable real-time multimessenger astrophysics

NASA Astrophysics Data System (ADS)

George, Daniel; Huerta, E. A.

2018-02-01

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

Unsupervised learning in probabilistic neural networks with multi-state metal-oxide memristive synapses

NASA Astrophysics Data System (ADS)

Serb, Alexander; Bill, Johannes; Khiat, Ali; Berdan, Radu; Legenstein, Robert; Prodromakis, Themis

2016-09-01

In an increasingly data-rich world the need for developing computing systems that cannot only process, but ideally also interpret big data is becoming continuously more pressing. Brain-inspired concepts have shown great promise towards addressing this need. Here we demonstrate unsupervised learning in a probabilistic neural network that utilizes metal-oxide memristive devices as multi-state synapses. Our approach can be exploited for processing unlabelled data and can adapt to time-varying clusters that underlie incoming data by supporting the capability of reversible unsupervised learning. The potential of this work is showcased through the demonstration of successful learning in the presence of corrupted input data and probabilistic neurons, thus paving the way towards robust big-data processors.

Wavelets and Elman Neural Networks for monitoring environmental variables

NASA Astrophysics Data System (ADS)

Ciarlini, Patrizia; Maniscalco, Umberto

2008-11-01

An application in cultural heritage is introduced. Wavelet decomposition and Neural Networks like virtual sensors are jointly used to simulate physical and chemical measurements in specific locations of a monument. Virtual sensors, suitably trained and tested, can substitute real sensors in monitoring the monument surface quality, while the real ones should be installed for a long time and at high costs. The application of the wavelet decomposition to the environmental data series allows getting the treatment of underlying temporal structure at low frequencies. Consequently a separate training of suitable Elman Neural Networks for high/low components can be performed, thus improving the networks convergence in learning time and measurement accuracy in working time.

Neural Correlates of Morphology Acquisition through a Statistical Learning Paradigm.

PubMed

Sandoval, Michelle; Patterson, Dianne; Dai, Huanping; Vance, Christopher J; Plante, Elena

2017-01-01

The neural basis of statistical learning as it occurs over time was explored with stimuli drawn from a natural language (Russian nouns). The input reflected the "rules" for marking categories of gendered nouns, without making participants explicitly aware of the nature of what they were to learn. Participants were scanned while listening to a series of gender-marked nouns during four sequential scans, and were tested for their learning immediately after each scan. Although participants were not told the nature of the learning task, they exhibited learning after their initial exposure to the stimuli. Independent component analysis of the brain data revealed five task-related sub-networks. Unlike prior statistical learning studies of word segmentation, this morphological learning task robustly activated the inferior frontal gyrus during the learning period. This region was represented in multiple independent components, suggesting it functions as a network hub for this type of learning. Moreover, the results suggest that subnetworks activated by statistical learning are driven by the nature of the input, rather than reflecting a general statistical learning system.

Neural Correlates of Morphology Acquisition through a Statistical Learning Paradigm

PubMed Central

Sandoval, Michelle; Patterson, Dianne; Dai, Huanping; Vance, Christopher J.; Plante, Elena

2017-01-01

The neural basis of statistical learning as it occurs over time was explored with stimuli drawn from a natural language (Russian nouns). The input reflected the “rules” for marking categories of gendered nouns, without making participants explicitly aware of the nature of what they were to learn. Participants were scanned while listening to a series of gender-marked nouns during four sequential scans, and were tested for their learning immediately after each scan. Although participants were not told the nature of the learning task, they exhibited learning after their initial exposure to the stimuli. Independent component analysis of the brain data revealed five task-related sub-networks. Unlike prior statistical learning studies of word segmentation, this morphological learning task robustly activated the inferior frontal gyrus during the learning period. This region was represented in multiple independent components, suggesting it functions as a network hub for this type of learning. Moreover, the results suggest that subnetworks activated by statistical learning are driven by the nature of the input, rather than reflecting a general statistical learning system. PMID:28798703

A Circuit-Based Neural Network with Hybrid Learning of Backpropagation and Random Weight Change Algorithms

PubMed Central

Yang, Changju; Kim, Hyongsuk; Adhikari, Shyam Prasad; Chua, Leon O.

2016-01-01

A hybrid learning method of a software-based backpropagation learning and a hardware-based RWC learning is proposed for the development of circuit-based neural networks. The backpropagation is known as one of the most efficient learning algorithms. A weak point is that its hardware implementation is extremely difficult. The RWC algorithm, which is very easy to implement with respect to its hardware circuits, takes too many iterations for learning. The proposed learning algorithm is a hybrid one of these two. The main learning is performed with a software version of the BP algorithm, firstly, and then, learned weights are transplanted on a hardware version of a neural circuit. At the time of the weight transplantation, a significant amount of output error would occur due to the characteristic difference between the software and the hardware. In the proposed method, such error is reduced via a complementary learning of the RWC algorithm, which is implemented in a simple hardware. The usefulness of the proposed hybrid learning system is verified via simulations upon several classical learning problems. PMID:28025566

Deep Constrained Siamese Hash Coding Network and Load-Balanced Locality-Sensitive Hashing for Near Duplicate Image Detection.

PubMed

Hu, Weiming; Fan, Yabo; Xing, Junliang; Sun, Liang; Cai, Zhaoquan; Maybank, Stephen

2018-09-01

We construct a new efficient near duplicate image detection method using a hierarchical hash code learning neural network and load-balanced locality-sensitive hashing (LSH) indexing. We propose a deep constrained siamese hash coding neural network combined with deep feature learning. Our neural network is able to extract effective features for near duplicate image detection. The extracted features are used to construct a LSH-based index. We propose a load-balanced LSH method to produce load-balanced buckets in the hashing process. The load-balanced LSH significantly reduces the query time. Based on the proposed load-balanced LSH, we design an effective and feasible algorithm for near duplicate image detection. Extensive experiments on three benchmark data sets demonstrate the effectiveness of our deep siamese hash encoding network and load-balanced LSH.

Signalling chains with probe and adjust learning

NASA Astrophysics Data System (ADS)

Gosti, Giorgio

2018-04-01

Many models explain the evolution of signalling in repeated stage games on social networks, differently in this study each signalling game evolves a communication strategy to transmit information across the network. Specifically, I formalise signalling chain games as a generalisation of Lewis' signalling games, where a number of players are placed on a chain network and play a signalling game in which they have to propagate information across the network. I show that probe and adjust learning allows the system to develop communication conventions, but it may temporarily perturb the system out of conventions. Through simulations, I evaluate how long the system takes to evolve a signalling convention and the amount of time it stays in it. This discussion presents a mechanism in which simple players can evolve signalling across a social network without necessarily understanding the entire system.

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.

Evaluating the Generalization Value of Process-based Models in a Deep-in-time Machine Learning framework

NASA Astrophysics Data System (ADS)

Shen, C.; Fang, K.

2017-12-01

Deep Learning (DL) methods have made revolutionary strides in recent years. A core value proposition of DL is that abstract notions and patterns can be extracted purely from data, without the need for domain expertise. Process-based models (PBM), on the other hand, can be regarded as repositories of human knowledge or hypotheses about how systems function. Here, through computational examples, we argue that there is merit in integrating PBMs with DL due to the imbalance and lack of data in many situations, especially in hydrology. We trained a deep-in-time neural network, the Long Short-Term Memory (LSTM), to learn soil moisture dynamics from Soil Moisture Active Passive (SMAP) Level 3 product. We show that when PBM solutions are integrated into LSTM, the network is able to better generalize across regions. LSTM is able to better utilize PBM solutions than simpler statistical methods. Our results suggest PBMs have generalization value which should be carefully assessed and utilized. We also emphasize that when properly regularized, the deep network is robust and is of superior testing performance compared to simpler methods.

IPY Education, Outreach and Communication - Some Lessons Learned (Invited)

NASA Astrophysics Data System (ADS)

Carlson, D. J.; Salmon, R.; Munro, N.

2009-12-01

IPY Education, Outreach and Communications planning and implementation occurred with a minimum of staff and resources and a maximum of international volunteer enthusiasm and energy. Although many relatively well-funded and remarkable national activities occurred, sharing and promoting these internationally depended entirely on the volunteer networks of individuals and institutions. Through these partnerships we have learned valuable lessons about impact and distribution, and challenged several assumptions about educational partnerships. For example, we learned the importance of regular pre-scheduled events, and how to use networks of volunteer translators and free geobrowser tools. We have learned how best to conduct planning meetings and live events across time zones and hemispheres, and shown how the best concepts and ideas of science education can propagate across age groups and among languages. We have learned the optimal times of year for international events, and the most effective means for international distribution and communication. We have established a rapid-response help desk without home or staff, and sustained active and high-impact interactions with journalists largely without press releases. We have shown that, in general, wide-spread distribution of freely accessible materials produces a better impact than embargoes and restrictions. Most fundamentally, we have exposed a pervasive interest in polar science and a hunger for climate information, and responded with an active, flexible, and efficient network of partners and products.

Saliency detection by conditional generative adversarial network

NASA Astrophysics Data System (ADS)

Cai, Xiaoxu; Yu, Hui

2018-04-01

Detecting salient objects in images has been a fundamental problem in computer vision. In recent years, deep learning has shown its impressive performance in dealing with many kinds of vision tasks. In this paper, we propose a new method to detect salient objects by using Conditional Generative Adversarial Network (GAN). This type of network not only learns the mapping from RGB images to salient regions, but also learns a loss function for training the mapping. To the best of our knowledge, this is the first time that Conditional GAN has been used in salient object detection. We evaluate our saliency detection method on 2 large publicly available datasets with pixel accurate annotations. The experimental results have shown the significant and consistent improvements over the state-of-the-art method on a challenging dataset, and the testing speed is much faster.

Is Multitask Deep Learning Practical for Pharma?

PubMed

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

2017-08-28

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

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…

Machine learning topological states

NASA Astrophysics Data System (ADS)

Deng, Dong-Ling; Li, Xiaopeng; Das Sarma, S.

2017-11-01

Artificial neural networks and machine learning have now reached a new era after several decades of improvement where applications are to explode in many fields of science, industry, and technology. Here, we use artificial neural networks to study an intriguing phenomenon in quantum physics—the topological phases of matter. We find that certain topological states, either symmetry-protected or with intrinsic topological order, can be represented with classical artificial neural networks. This is demonstrated by using three concrete spin systems, the one-dimensional (1D) symmetry-protected topological cluster state and the 2D and 3D toric code states with intrinsic topological orders. For all three cases, we show rigorously that the topological ground states can be represented by short-range neural networks in an exact and efficient fashion—the required number of hidden neurons is as small as the number of physical spins and the number of parameters scales only linearly with the system size. For the 2D toric-code model, we find that the proposed short-range neural networks can describe the excited states with Abelian anyons and their nontrivial mutual statistics as well. In addition, by using reinforcement learning we show that neural networks are capable of finding the topological ground states of nonintegrable Hamiltonians with strong interactions and studying their topological phase transitions. Our results demonstrate explicitly the exceptional power of neural networks in describing topological quantum states, and at the same time provide valuable guidance to machine learning of topological phases in generic lattice models.

A Model of Self-Organizing Head-Centered Visual Responses in Primate Parietal Areas

PubMed Central

Mender, Bedeho M. W.; Stringer, Simon M.

2013-01-01

We present a hypothesis for how head-centered visual representations in primate parietal areas could self-organize through visually-guided learning, and test this hypothesis using a neural network model. The model consists of a competitive output layer of neurons that receives afferent synaptic connections from a population of input neurons with eye position gain modulated retinal receptive fields. The synaptic connections in the model are trained with an associative trace learning rule which has the effect of encouraging output neurons to learn to respond to subsets of input patterns that tend to occur close together in time. This network architecture and synaptic learning rule is hypothesized to promote the development of head-centered output neurons during periods of time when the head remains fixed while the eyes move. This hypothesis is demonstrated to be feasible, and each of the core model components described is tested and found to be individually necessary for successful self-organization. PMID:24349064

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.

A lightweight network anomaly detection technique

DOE PAGES

Kim, Jinoh; Yoo, Wucherl; Sim, Alex; ...

2017-03-13

While the network anomaly detection is essential in network operations and management, it becomes further challenging to perform the first line of detection against the exponentially increasing volume of network traffic. In this paper, we develop a technique for the first line of online anomaly detection with two important considerations: (i) availability of traffic attributes during the monitoring time, and (ii) computational scalability for streaming data. The presented learning technique is lightweight and highly scalable with the beauty of approximation based on the grid partitioning of the given dimensional space. With the public traffic traces of KDD Cup 1999 andmore » NSL-KDD, we show that our technique yields 98.5% and 83% of detection accuracy, respectively, only with a couple of readily available traffic attributes that can be obtained without the help of post-processing. Finally, the results are at least comparable with the classical learning methods including decision tree and random forest, with approximately two orders of magnitude faster learning performance.« less

A lightweight network anomaly detection technique

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

Kim, Jinoh; Yoo, Wucherl; Sim, Alex

While the network anomaly detection is essential in network operations and management, it becomes further challenging to perform the first line of detection against the exponentially increasing volume of network traffic. In this paper, we develop a technique for the first line of online anomaly detection with two important considerations: (i) availability of traffic attributes during the monitoring time, and (ii) computational scalability for streaming data. The presented learning technique is lightweight and highly scalable with the beauty of approximation based on the grid partitioning of the given dimensional space. With the public traffic traces of KDD Cup 1999 andmore » NSL-KDD, we show that our technique yields 98.5% and 83% of detection accuracy, respectively, only with a couple of readily available traffic attributes that can be obtained without the help of post-processing. Finally, the results are at least comparable with the classical learning methods including decision tree and random forest, with approximately two orders of magnitude faster learning performance.« less

Convolutional neural network with transfer learning for rice type classification

NASA Astrophysics Data System (ADS)

Patel, Vaibhav Amit; Joshi, Manjunath V.

2018-04-01

Presently, rice type is identified manually by humans, which is time consuming and error prone. Therefore, there is a need to do this by machine which makes it faster with greater accuracy. This paper proposes a deep learning based method for classification of rice types. We propose two methods to classify the rice types. In the first method, we train a deep convolutional neural network (CNN) using the given segmented rice images. In the second method, we train a combination of a pretrained VGG16 network and the proposed method, while using transfer learning in which the weights of a pretrained network are used to achieve better accuracy. Our approach can also be used for classification of rice grain as broken or fine. We train a 5-class model for classifying rice types using 4000 training images and another 2- class model for the classification of broken and normal rice using 1600 training images. We observe that despite having distinct rice images, our architecture, pretrained on ImageNet data boosts classification accuracy significantly.

A classifier neural network for rotordynamic systems

NASA Astrophysics Data System (ADS)

Ganesan, R.; Jionghua, Jin; Sankar, T. S.

1995-07-01

A feedforward backpropagation neural network is formed to identify the stability characteristic of a high speed rotordynamic system. The principal focus resides in accounting for the instability due to the bearing clearance effects. The abnormal operating condition of 'normal-loose' Coulomb rub, that arises in units supported by hydrodynamic bearings or rolling element bearings, is analysed in detail. The multiple-parameter stability problem is formulated and converted to a set of three-parameter algebraic inequality equations. These three parameters map the wider range of physical parameters of commonly-used rotordynamic systems into a narrow closed region, that is used in the supervised learning of the neural network. A binary-type state of the system is expressed through these inequalities that are deduced from the analytical simulation of the rotor system. Both the hidden layer as well as functional-link networks are formed and the superiority of the functional-link network is established. Considering the real time interpretation and control of the rotordynamic system, the network reliability and the learning time are used as the evaluation criteria to assess the superiority of the functional-link network. This functional-link network is further trained using the parameter values of selected rotor systems, and the classifier network is formed. The success rate of stability status identification is obtained to assess the potentials of this classifier network. The classifier network is shown that it can also be used, for control purposes, as an 'advisory' system that suggests the optimum way of parameter adjustment.

Detecting and preventing error propagation via competitive learning.

PubMed

Silva, Thiago Christiano; Zhao, Liang

2013-05-01

Semisupervised learning is a machine learning approach which is able to employ both labeled and unlabeled samples in the training process. It is an important mechanism for autonomous systems due to the ability of exploiting the already acquired information and for exploring the new knowledge in the learning space at the same time. In these cases, the reliability of the labels is a crucial factor, because mislabeled samples may propagate wrong labels to a portion of or even the entire data set. This paper has the objective of addressing the error propagation problem originated by these mislabeled samples by presenting a mechanism embedded in a network-based (graph-based) semisupervised learning method. Such a procedure is based on a combined random-preferential walk of particles in a network constructed from the input data set. The particles of the same class cooperate among them, while the particles of different classes compete with each other to propagate class labels to the whole network. Computer simulations conducted on synthetic and real-world data sets reveal the effectiveness of the model. Copyright © 2012 Elsevier Ltd. All rights reserved.

Modeling somatic and dendritic spike mediated plasticity at the single neuron and network level.

PubMed

Bono, Jacopo; Clopath, Claudia

2017-09-26

Synaptic plasticity is thought to be the principal neuronal mechanism underlying learning. Models of plastic networks typically combine point neurons with spike-timing-dependent plasticity (STDP) as the learning rule. However, a point neuron does not capture the local non-linear processing of synaptic inputs allowed for by dendrites. Furthermore, experimental evidence suggests that STDP is not the only learning rule available to neurons. By implementing biophysically realistic neuron models, we study how dendrites enable multiple synaptic plasticity mechanisms to coexist in a single cell. In these models, we compare the conditions for STDP and for synaptic strengthening by local dendritic spikes. We also explore how the connectivity between two cells is affected by these plasticity rules and by different synaptic distributions. Finally, we show that how memory retention during associative learning can be prolonged in networks of neurons by including dendrites.Synaptic plasticity is the neuronal mechanism underlying learning. Here the authors construct biophysical models of pyramidal neurons that reproduce observed plasticity gradients along the dendrite and show that dendritic spike dependent LTP which is predominant in distal sections can prolong memory retention.

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

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

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.

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.

Cognitive Neurostimulation: Learning to Volitionally Sustain Ventral Tegmental Area Activation

PubMed Central

MacInnes, Jeff J.; Dickerson, Kathryn C.; Chen, Nan-kuei; Adcock, R. Alison

2016-01-01

SUMMARY Activation of the ventral tegmental area (VTA) and mesolimbic networks is essential to motivation, performance, and learning. Humans routinely attempt to motivate themselves, with unclear efficacy or impact on VTA networks. Using fMRI, we found untrained participants’ motivational strategies failed to consistently activate VTA. After real-time VTA neurofeedback training, however, participants volitionally induced VTA activation without external aids, relative to baseline, Pre-Test, and control groups. VTA self-activation was accompanied by increased mesolimbic network connectivity. Among two comparison groups (no neurofeedback, false neurofeedback) and an alternate neurofeedback group (nucleus accumbens), none sustained activation in target regions of interest nor increased VTA functional connectivity. The results comprise two novel demonstrations: learning and generalization after VTA neurofeedback training and the ability to sustain VTA activation without external reward or reward cues. These findings suggest theoretical alignment of ideas about motivation and midbrain physiology and the potential for generalizable interventions to improve performance and learning. PMID:26948894

Cognitive Neurostimulation: Learning to Volitionally Sustain Ventral Tegmental Area Activation.

PubMed

MacInnes, Jeff J; Dickerson, Kathryn C; Chen, Nan-Kuei; Adcock, R Alison

2016-03-16

Activation of the ventral tegmental area (VTA) and mesolimbic networks is essential to motivation, performance, and learning. Humans routinely attempt to motivate themselves, with unclear efficacy or impact on VTA networks. Using fMRI, we found untrained participants' motivational strategies failed to consistently activate VTA. After real-time VTA neurofeedback training, however, participants volitionally induced VTA activation without external aids, relative to baseline, Pre-test, and control groups. VTA self-activation was accompanied by increased mesolimbic network connectivity. Among two comparison groups (no neurofeedback, false neurofeedback) and an alternate neurofeedback group (nucleus accumbens), none sustained activation in target regions of interest nor increased VTA functional connectivity. The results comprise two novel demonstrations: learning and generalization after VTA neurofeedback training and the ability to sustain VTA activation without external reward or reward cues. These findings suggest theoretical alignment of ideas about motivation and midbrain physiology and the potential for generalizable interventions to improve performance and learning. Copyright © 2016 Elsevier Inc. All rights reserved.

Finding Influential Users in Social Media Using Association Rule Learning

NASA Astrophysics Data System (ADS)

Erlandsson, Fredrik; Bródka, Piotr; Borg, Anton; Johnson, Henric

2016-04-01

Influential users play an important role in online social networks since users tend to have an impact on one other. Therefore, the proposed work analyzes users and their behavior in order to identify influential users and predict user participation. Normally, the success of a social media site is dependent on the activity level of the participating users. For both online social networking sites and individual users, it is of interest to find out if a topic will be interesting or not. In this article, we propose association learning to detect relationships between users. In order to verify the findings, several experiments were executed based on social network analysis, in which the most influential users identified from association rule learning were compared to the results from Degree Centrality and Page Rank Centrality. The results clearly indicate that it is possible to identify the most influential users using association rule learning. In addition, the results also indicate a lower execution time compared to state-of-the-art methods.

A Learning Theory for Reward-Modulated Spike-Timing-Dependent Plasticity with Application to Biofeedback

PubMed Central

Maass, Wolfgang

2008-01-01

Reward-modulated spike-timing-dependent plasticity (STDP) has recently emerged as a candidate for a learning rule that could explain how behaviorally relevant adaptive changes in complex networks of spiking neurons could be achieved in a self-organizing manner through local synaptic plasticity. However, the capabilities and limitations of this learning rule could so far only be tested through computer simulations. This article provides tools for an analytic treatment of reward-modulated STDP, which allows us to predict under which conditions reward-modulated STDP will achieve a desired learning effect. These analytical results imply that neurons can learn through reward-modulated STDP to classify not only spatial but also temporal firing patterns of presynaptic neurons. They also can learn to respond to specific presynaptic firing patterns with particular spike patterns. Finally, the resulting learning theory predicts that even difficult credit-assignment problems, where it is very hard to tell which synaptic weights should be modified in order to increase the global reward for the system, can be solved in a self-organizing manner through reward-modulated STDP. This yields an explanation for a fundamental experimental result on biofeedback in monkeys by Fetz and Baker. In this experiment monkeys were rewarded for increasing the firing rate of a particular neuron in the cortex and were able to solve this extremely difficult credit assignment problem. Our model for this experiment relies on a combination of reward-modulated STDP with variable spontaneous firing activity. Hence it also provides a possible functional explanation for trial-to-trial variability, which is characteristic for cortical networks of neurons but has no analogue in currently existing artificial computing systems. In addition our model demonstrates that reward-modulated STDP can be applied to all synapses in a large recurrent neural network without endangering the stability of the network dynamics. PMID:18846203

Spike-Based Bayesian-Hebbian Learning of Temporal Sequences

PubMed Central

Lindén, Henrik; Lansner, Anders

2016-01-01

Many cognitive and motor functions are enabled by the temporal representation and processing of stimuli, but it remains an open issue how neocortical microcircuits can reliably encode and replay such sequences of information. To better understand this, a modular attractor memory network is proposed in which meta-stable sequential attractor transitions are learned through changes to synaptic weights and intrinsic excitabilities via the spike-based Bayesian Confidence Propagation Neural Network (BCPNN) learning rule. We find that the formation of distributed memories, embodied by increased periods of firing in pools of excitatory neurons, together with asymmetrical associations between these distinct network states, can be acquired through plasticity. The model’s feasibility is demonstrated using simulations of adaptive exponential integrate-and-fire model neurons (AdEx). We show that the learning and speed of sequence replay depends on a confluence of biophysically relevant parameters including stimulus duration, level of background noise, ratio of synaptic currents, and strengths of short-term depression and adaptation. Moreover, sequence elements are shown to flexibly participate multiple times in the sequence, suggesting that spiking attractor networks of this type can support an efficient combinatorial code. The model provides a principled approach towards understanding how multiple interacting plasticity mechanisms can coordinate hetero-associative learning in unison. PMID:27213810

LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices.

PubMed

He, Ziyang; Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

2018-04-17

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices.

LiteNet: Lightweight Neural Network for Detecting Arrhythmias at Resource-Constrained Mobile Devices

PubMed Central

Zhang, Xiaoqing; Cao, Yangjie; Liu, Zhi; Zhang, Bo; Wang, Xiaoyan

2018-01-01

By running applications and services closer to the user, edge processing provides many advantages, such as short response time and reduced network traffic. Deep-learning based algorithms provide significantly better performances than traditional algorithms in many fields but demand more resources, such as higher computational power and more memory. Hence, designing deep learning algorithms that are more suitable for resource-constrained mobile devices is vital. In this paper, we build a lightweight neural network, termed LiteNet which uses a deep learning algorithm design to diagnose arrhythmias, as an example to show how we design deep learning schemes for resource-constrained mobile devices. Compare to other deep learning models with an equivalent accuracy, LiteNet has several advantages. It requires less memory, incurs lower computational cost, and is more feasible for deployment on resource-constrained mobile devices. It can be trained faster than other neural network algorithms and requires less communication across different processing units during distributed training. It uses filters of heterogeneous size in a convolutional layer, which contributes to the generation of various feature maps. The algorithm was tested using the MIT-BIH electrocardiogram (ECG) arrhythmia database; the results showed that LiteNet outperforms comparable schemes in diagnosing arrhythmias, and in its feasibility for use at the mobile devices. PMID:29673171

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.

Machine learning molecular dynamics for the simulation of infrared spectra.

PubMed

Gastegger, Michael; Behler, Jörg; Marquetand, Philipp

2017-10-01

Machine learning has emerged as an invaluable tool in many research areas. In the present work, we harness this power to predict highly accurate molecular infrared spectra with unprecedented computational efficiency. To account for vibrational anharmonic and dynamical effects - typically neglected by conventional quantum chemistry approaches - we base our machine learning strategy on ab initio molecular dynamics simulations. While these simulations are usually extremely time consuming even for small molecules, we overcome these limitations by leveraging the power of a variety of machine learning techniques, not only accelerating simulations by several orders of magnitude, but also greatly extending the size of systems that can be treated. To this end, we develop a molecular dipole moment model based on environment dependent neural network charges and combine it with the neural network potential approach of Behler and Parrinello. Contrary to the prevalent big data philosophy, we are able to obtain very accurate machine learning models for the prediction of infrared spectra based on only a few hundreds of electronic structure reference points. This is made possible through the use of molecular forces during neural network potential training and the introduction of a fully automated sampling scheme. We demonstrate the power of our machine learning approach by applying it to model the infrared spectra of a methanol molecule, n -alkanes containing up to 200 atoms and the protonated alanine tripeptide, which at the same time represents the first application of machine learning techniques to simulate the dynamics of a peptide. In all of these case studies we find an excellent agreement between the infrared spectra predicted via machine learning models and the respective theoretical and experimental spectra.

Different propagation speeds of recalled sequences in plastic spiking neural networks

NASA Astrophysics Data System (ADS)

Huang, Xuhui; Zheng, Zhigang; Hu, Gang; Wu, Si; Rasch, Malte J.

2015-03-01

Neural networks can generate spatiotemporal patterns of spike activity. Sequential activity learning and retrieval have been observed in many brain areas, and e.g. is crucial for coding of episodic memory in the hippocampus or generating temporal patterns during song production in birds. In a recent study, a sequential activity pattern was directly entrained onto the neural activity of the primary visual cortex (V1) of rats and subsequently successfully recalled by a local and transient trigger. It was observed that the speed of activity propagation in coordinates of the retinotopically organized neural tissue was constant during retrieval regardless how the speed of light stimulation sweeping across the visual field during training was varied. It is well known that spike-timing dependent plasticity (STDP) is a potential mechanism for embedding temporal sequences into neural network activity. How training and retrieval speeds relate to each other and how network and learning parameters influence retrieval speeds, however, is not well described. We here theoretically analyze sequential activity learning and retrieval in a recurrent neural network with realistic synaptic short-term dynamics and STDP. Testing multiple STDP rules, we confirm that sequence learning can be achieved by STDP. However, we found that a multiplicative nearest-neighbor (NN) weight update rule generated weight distributions and recall activities that best matched the experiments in V1. Using network simulations and mean-field analysis, we further investigated the learning mechanisms and the influence of network parameters on recall speeds. Our analysis suggests that a multiplicative STDP rule with dominant NN spike interaction might be implemented in V1 since recall speed was almost constant in an NMDA-dominant regime. Interestingly, in an AMPA-dominant regime, neural circuits might exhibit recall speeds that instead follow the change in stimulus speeds. This prediction could be tested in experiments.

Self-Learning Intelligent Agents for Dynamic Traffic Routing on Transportation Networks

NASA Astrophysics Data System (ADS)

Sadek, Add; Basha, Nagi

Intelligent Transportation Systems (ITS) are designed to take advantage of recent advances in communications, electronics, and Information Technology in improving the efficiency and safety of transportation systems. Among the several ITS applications is the notion of Dynamic Traffic Routing (DTR), which involves generating "optimal" routing recommendations to drivers with the aim of maximizing network utilizing. In this paper, we demonstrate the feasibility of using a self-learning intelligent agent to solve the DTR problem to achieve traffic user equilibrium in a transportation network. The core idea is to deploy an agent to a simulation model of a highway. The agent then learns by itself by interacting with the simulation model. Once the agent reaches a satisfactory level of performance, it can then be deployed to the real-world, where it would continue to learn how to refine its control policies over time. To test this concept in this paper, the Cell Transmission Model (CTM) developed by Carlos Daganzo of the University of California at Berkeley is used to simulate a simple highway with two main alternative routes. With the model developed, a Reinforcement Learning Agent (RLA) is developed to learn how to best dynamically route traffic, so as to maximize the utilization of existing capacity. Preliminary results obtained from our experiments are promising. RL, being an adaptive online learning technique, appears to have a great potential for controlling a stochastic dynamic systems such as a transportation system. Furthermore, the approach is highly scalable and applicable to a variety of networks and roadways.

Engaging Employers to Drive up Skills: The Realities of Effective Employer Engagement--Current Opportunities and Challenges

ERIC Educational Resources Information Center

Learning and Skills Network (NJ3), 2010

2010-01-01

The Learning and Skills Network's (LSN's) think tank, the Centre for Innovation in Learning, in association with the 157 Group, the Association of Learning Providers (ALP) and the Association of Colleges (AoC), has undertaken timely and important research into how to support and improve employer engagement in the further education (FE) and skills…

Effectiveness and Obstacle of Using Facebook as a Tool to Facilitate Student-Centred Learning in Higher Education

ERIC Educational Resources Information Center

Cheng, Irene Nga Yee; Chan, Janet Kit Yan; Kong, Suria Suet Yee; Leung, Kenneth Mei Yee

2016-01-01

Blended learning which combines face-to-face and online experiences of students by integrating technology into the curriculum is increasingly prevalent in university education. In a context of long time arguments on the educational value of using social networking websites on teaching and learning, this study was conducted in two higher education…

Learning Leaders Leading for Learning: A Cross-Case Analysis of How Participation in an Instructional Rounds Network Shapes Superintendents' Instructional Leadership Practices

ERIC Educational Resources Information Center

Schiavino-Narvaez, Beth

2012-01-01

The leadership practice of superintendents spans three domains: instructional, managerial, and political (Johnson, 1996; Cuban, 1998; Nestor-Baker and Hoy, 2001; Lashaway, 2002). Despite the fact that superintendents lead organizations whose main business is teaching and learning, they spend most of their time in the political and managerial…

On the fusion of tuning parameters of fuzzy rules and neural network

NASA Astrophysics Data System (ADS)

Mamuda, Mamman; Sathasivam, Saratha

2017-08-01

Learning fuzzy rule-based system with neural network can lead to a precise valuable empathy of several problems. Fuzzy logic offers a simple way to reach at a definite conclusion based upon its vague, ambiguous, imprecise, noisy or missing input information. Conventional learning algorithm for tuning parameters of fuzzy rules using training input-output data usually end in a weak firing state, this certainly powers the fuzzy rule and makes it insecure for a multiple-input fuzzy system. In this paper, we introduce a new learning algorithm for tuning the parameters of the fuzzy rules alongside with radial basis function neural network (RBFNN) in training input-output data based on the gradient descent method. By the new learning algorithm, the problem of weak firing using the conventional method was addressed. We illustrated the efficiency of our new learning algorithm by means of numerical examples. MATLAB R2014(a) software was used in simulating our result The result shows that the new learning method has the best advantage of training the fuzzy rules without tempering with the fuzzy rule table which allowed a membership function of the rule to be used more than one time in the fuzzy rule base.

Evolution of co-management: role of knowledge generation, bridging organizations and social learning.

PubMed

Berkes, Fikret

2009-04-01

Over a period of some 20 years, different aspects of co-management (the sharing of power and responsibility between the government and local resource users) have come to the forefront. The paper focuses on a selection of these: knowledge generation, bridging organizations, social learning, and the emergence of adaptive co-management. Co-management can be considered a knowledge partnership. Different levels of organization, from local to international, have comparative advantages in the generation and mobilization of knowledge acquired at different scales. Bridging organizations provide a forum for the interaction of these different kinds of knowledge, and the coordination of other tasks that enable co-operation: accessing resources, bringing together different actors, building trust, resolving conflict, and networking. Social learning is one of these tasks, essential both for the co-operation of partners and an outcome of the co-operation of partners. It occurs most efficiently through joint problem solving and reflection within learning networks. Through successive rounds of learning and problem solving, learning networks can incorporate new knowledge to deal with problems at increasingly larger scales, with the result that maturing co-management arrangements become adaptive co-management in time.

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.

A smart-pixel holographic competitive learning network

NASA Astrophysics Data System (ADS)

Slagle, Timothy Michael

Neural networks are adaptive classifiers which modify their decision boundaries based on feedback from externally- or internally-generated error signals. Optics is an attractive technology for neural network implementation because it offers the possibility of parallel, nearly instantaneous computation of the weighted neuron inputs by the propagation of light through the optical system. Using current optical device technology, system performance levels of 3 × 1011 connection updates per second can be achieved. This thesis presents an architecture for an optical competitive learning network which offers advantages over previous optical implementations, including smart-pixel-based optical neurons, phase- conjugate self-alignment of a single neuron plane, and high-density, parallel-access weight storage, interconnection, and learning in a volume hologram. The competitive learning algorithm with modifications for optical implementation is described, and algorithm simulations are performed for an example problem. The optical competitive learning architecture is then introduced. The optical system is simulated using the ``beamprop'' algorithm at the level of light propagating through the system components, and results showing competitive learning operation in agreement with the algorithm simulations are presented. The optical competitive learning requires a non-linear, non-local ``winner-take-all'' (WTA) neuron function. Custom-designed smart-pixel WTA neuron arrays were fabricated using CMOS VLSI/liquid crystal technology. Results of laboratory tests of the WTA arrays' switching characteristics, time response, and uniformity are then presented. The system uses a phase-conjugate mirror to write the self-aligning interconnection weight holograms, and energy gain is required from the reflection to minimize erasure of the existing weights. An experimental system for characterizing the PCM response is described. Useful gains of 20 were obtained with a polarization-multiplexed PCM readout, and gains of up to 60 were observed when a time-sequential read-out technique was used. Finally, the optical competitive learning laboratory system is described, including some necessary modifications to the previous architectures, and the data acquisition and control system developed for the system. Experimental results showing phase conjugation of the WTA outputs, holographic interconnect storage, associative storage between input images and WTA neuron outputs, and WTA array switching are presented, demonstrating the functions necessary for the operation of the optical learning system.

Path integration of head direction: updating a packet of neural activity at the correct speed using axonal conduction delays.

PubMed

Walters, Daniel; Stringer, Simon; Rolls, Edmund

2013-01-01

The head direction cell system is capable of accurately updating its current representation of head direction in the absence of visual input. This is known as the path integration of head direction. An important question is how the head direction cell system learns to perform accurate path integration of head direction. In this paper we propose a model of velocity path integration of head direction in which the natural time delay of axonal transmission between a linked continuous attractor network and competitive network acts as a timing mechanism to facilitate the correct speed of path integration. The model effectively learns a "look-up" table for the correct speed of path integration. In simulation, we show that the model is able to successfully learn two different speeds of path integration across two different axonal conduction delays, and without the need to alter any other model parameters. An implication of this model is that, by learning look-up tables for each speed of path integration, the model should exhibit a degree of robustness to damage. In simulations, we show that the speed of path integration is not significantly affected by degrading the network through removing a proportion of the cells that signal rotational velocity.

Path Integration of Head Direction: Updating a Packet of Neural Activity at the Correct Speed Using Axonal Conduction Delays

PubMed Central

Walters, Daniel; Stringer, Simon; Rolls, Edmund

2013-01-01

The head direction cell system is capable of accurately updating its current representation of head direction in the absence of visual input. This is known as the path integration of head direction. An important question is how the head direction cell system learns to perform accurate path integration of head direction. In this paper we propose a model of velocity path integration of head direction in which the natural time delay of axonal transmission between a linked continuous attractor network and competitive network acts as a timing mechanism to facilitate the correct speed of path integration. The model effectively learns a “look-up” table for the correct speed of path integration. In simulation, we show that the model is able to successfully learn two different speeds of path integration across two different axonal conduction delays, and without the need to alter any other model parameters. An implication of this model is that, by learning look-up tables for each speed of path integration, the model should exhibit a degree of robustness to damage. In simulations, we show that the speed of path integration is not significantly affected by degrading the network through removing a proportion of the cells that signal rotational velocity. PMID:23526976

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.

Object recognition using deep convolutional neural networks with complete transfer and partial frozen layers

NASA Astrophysics Data System (ADS)

Kruithof, Maarten C.; Bouma, Henri; Fischer, Noëlle M.; Schutte, Klamer

2016-10-01

Object recognition is important to understand the content of video and allow flexible querying in a large number of cameras, especially for security applications. Recent benchmarks show that deep convolutional neural networks are excellent approaches for object recognition. This paper describes an approach of domain transfer, where features learned from a large annotated dataset are transferred to a target domain where less annotated examples are available as is typical for the security and defense domain. Many of these networks trained on natural images appear to learn features similar to Gabor filters and color blobs in the first layer. These first-layer features appear to be generic for many datasets and tasks while the last layer is specific. In this paper, we study the effect of copying all layers and fine-tuning a variable number. We performed an experiment with a Caffe-based network on 1000 ImageNet classes that are randomly divided in two equal subgroups for the transfer from one to the other. We copy all layers and vary the number of layers that is fine-tuned and the size of the target dataset. We performed additional experiments with the Keras platform on CIFAR-10 dataset to validate general applicability. We show with both platforms and both datasets that the accuracy on the target dataset improves when more target data is used. When the target dataset is large, it is beneficial to freeze only a few layers. For a large target dataset, the network without transfer learning performs better than the transfer network, especially if many layers are frozen. When the target dataset is small, it is beneficial to transfer (and freeze) many layers. For a small target dataset, the transfer network boosts generalization and it performs much better than the network without transfer learning. Learning time can be reduced by freezing many layers in a network.

Unsupervised learning of temporal features for word categorization in a spiking neural network model of the auditory brain.

PubMed

Higgins, Irina; Stringer, Simon; Schnupp, Jan

2017-01-01

The nature of the code used in the auditory cortex to represent complex auditory stimuli, such as naturally spoken words, remains a matter of debate. Here we argue that such representations are encoded by stable spatio-temporal patterns of firing within cell assemblies known as polychronous groups, or PGs. We develop a physiologically grounded, unsupervised spiking neural network model of the auditory brain with local, biologically realistic, spike-time dependent plasticity (STDP) learning, and show that the plastic cortical layers of the network develop PGs which convey substantially more information about the speaker independent identity of two naturally spoken word stimuli than does rate encoding that ignores the precise spike timings. We furthermore demonstrate that such informative PGs can only develop if the input spatio-temporal spike patterns to the plastic cortical areas of the model are relatively stable.

Unsupervised learning of temporal features for word categorization in a spiking neural network model of the auditory brain

PubMed Central

Stringer, Simon

2017-01-01

The nature of the code used in the auditory cortex to represent complex auditory stimuli, such as naturally spoken words, remains a matter of debate. Here we argue that such representations are encoded by stable spatio-temporal patterns of firing within cell assemblies known as polychronous groups, or PGs. We develop a physiologically grounded, unsupervised spiking neural network model of the auditory brain with local, biologically realistic, spike-time dependent plasticity (STDP) learning, and show that the plastic cortical layers of the network develop PGs which convey substantially more information about the speaker independent identity of two naturally spoken word stimuli than does rate encoding that ignores the precise spike timings. We furthermore demonstrate that such informative PGs can only develop if the input spatio-temporal spike patterns to the plastic cortical areas of the model are relatively stable. PMID:28797034

Robust Learning of High-dimensional Biological Networks with Bayesian Networks

NASA Astrophysics Data System (ADS)

Nägele, Andreas; Dejori, Mathäus; Stetter, Martin

Structure learning of Bayesian networks applied to gene expression data has become a potentially useful method to estimate interactions between genes. However, the NP-hardness of Bayesian network structure learning renders the reconstruction of the full genetic network with thousands of genes unfeasible. Consequently, the maximal network size is usually restricted dramatically to a small set of genes (corresponding with variables in the Bayesian network). Although this feature reduction step makes structure learning computationally tractable, on the downside, the learned structure might be adversely affected due to the introduction of missing genes. Additionally, gene expression data are usually very sparse with respect to the number of samples, i.e., the number of genes is much greater than the number of different observations. Given these problems, learning robust network features from microarray data is a challenging task. This chapter presents several approaches tackling the robustness issue in order to obtain a more reliable estimation of learned network features.

Web-Based Learning in the Computer-Aided Design Curriculum.

ERIC Educational Resources Information Center

Sung, Wen-Tsai; Ou, S. C.

2002-01-01

Applies principles of constructivism and virtual reality (VR) to computer-aided design (CAD) curriculum, particularly engineering, by integrating network, VR and CAD technologies into a Web-based learning environment that expands traditional two-dimensional computer graphics into a three-dimensional real-time simulation that enhances user…

Learning to Estimate Dynamical State with Probabilistic Population Codes.

PubMed

Makin, Joseph G; Dichter, Benjamin K; Sabes, Philip N

2015-11-01

Tracking moving objects, including one's own body, is a fundamental ability of higher organisms, playing a central role in many perceptual and motor tasks. While it is unknown how the brain learns to follow and predict the dynamics of objects, it is known that this process of state estimation can be learned purely from the statistics of noisy observations. When the dynamics are simply linear with additive Gaussian noise, the optimal solution is the well known Kalman filter (KF), the parameters of which can be learned via latent-variable density estimation (the EM algorithm). The brain does not, however, directly manipulate matrices and vectors, but instead appears to represent probability distributions with the firing rates of population of neurons, "probabilistic population codes." We show that a recurrent neural network-a modified form of an exponential family harmonium (EFH)-that takes a linear probabilistic population code as input can learn, without supervision, to estimate the state of a linear dynamical system. After observing a series of population responses (spike counts) to the position of a moving object, the network learns to represent the velocity of the object and forms nearly optimal predictions about the position at the next time-step. This result builds on our previous work showing that a similar network can learn to perform multisensory integration and coordinate transformations for static stimuli. The receptive fields of the trained network also make qualitative predictions about the developing and learning brain: tuning gradually emerges for higher-order dynamical states not explicitly present in the inputs, appearing as delayed tuning for the lower-order states.

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,…

Approximate, computationally efficient online learning in Bayesian spiking neurons.

PubMed

Kuhlmann, Levin; Hauser-Raspe, Michael; Manton, Jonathan H; Grayden, David B; Tapson, Jonathan; van Schaik, André

2014-03-01

Bayesian spiking neurons (BSNs) provide a probabilistic interpretation of how neurons perform inference and learning. Online learning in BSNs typically involves parameter estimation based on maximum-likelihood expectation-maximization (ML-EM) which is computationally slow and limits the potential of studying networks of BSNs. An online learning algorithm, fast learning (FL), is presented that is more computationally efficient than the benchmark ML-EM for a fixed number of time steps as the number of inputs to a BSN increases (e.g., 16.5 times faster run times for 20 inputs). Although ML-EM appears to converge 2.0 to 3.6 times faster than FL, the computational cost of ML-EM means that ML-EM takes longer to simulate to convergence than FL. FL also provides reasonable convergence performance that is robust to initialization of parameter estimates that are far from the true parameter values. However, parameter estimation depends on the range of true parameter values. Nevertheless, for a physiologically meaningful range of parameter values, FL gives very good average estimation accuracy, despite its approximate nature. The FL algorithm therefore provides an efficient tool, complementary to ML-EM, for exploring BSN networks in more detail in order to better understand their biological relevance. Moreover, the simplicity of the FL algorithm means it can be easily implemented in neuromorphic VLSI such that one can take advantage of the energy-efficient spike coding of BSNs.

Autonomous learning by simple dynamical systems with a discrete-time formulation

NASA Astrophysics Data System (ADS)

Bilen, Agustín M.; Kaluza, Pablo

2017-05-01

We present a discrete-time formulation for the autonomous learning conjecture. The main feature of this formulation is the possibility to apply the autonomous learning scheme to systems in which the errors with respect to target functions are not well-defined for all times. This restriction for the evaluation of functionality is a typical feature in systems that need a finite time interval to process a unit piece of information. We illustrate its application on an artificial neural network with feed-forward architecture for classification and a phase oscillator system with synchronization properties. The main characteristics of the discrete-time formulation are shown by constructing these systems with predefined functions.

Performance Evaluation of Machine Learning Methods for Leaf Area Index Retrieval from Time-Series MODIS Reflectance Data

PubMed Central

Wang, Tongtong; Xiao, Zhiqiang; Liu, Zhigang

2017-01-01

Leaf area index (LAI) is an important biophysical parameter and the retrieval of LAI from remote sensing data is the only feasible method for generating LAI products at regional and global scales. However, most LAI retrieval methods use satellite observations at a specific time to retrieve LAI. Because of the impacts of clouds and aerosols, the LAI products generated by these methods are spatially incomplete and temporally discontinuous, and thus they cannot meet the needs of practical applications. To generate high-quality LAI products, four machine learning algorithms, including back-propagation neutral network (BPNN), radial basis function networks (RBFNs), general regression neutral networks (GRNNs), and multi-output support vector regression (MSVR) are proposed to retrieve LAI from time-series Moderate Resolution Imaging Spectroradiometer (MODIS) reflectance data in this study and performance of these machine learning algorithms is evaluated. The results demonstrated that GRNNs, RBFNs, and MSVR exhibited low sensitivity to training sample size, whereas BPNN had high sensitivity. The four algorithms performed slightly better with red, near infrared (NIR), and short wave infrared (SWIR) bands than red and NIR bands, and the results were significantly better than those obtained using single band reflectance data (red or NIR). Regardless of band composition, GRNNs performed better than the other three methods. Among the four algorithms, BPNN required the least training time, whereas MSVR needed the most for any sample size. PMID:28045443

Performance Evaluation of Machine Learning Methods for Leaf Area Index Retrieval from Time-Series MODIS Reflectance Data.

PubMed

Wang, Tongtong; Xiao, Zhiqiang; Liu, Zhigang

2017-01-01

Leaf area index (LAI) is an important biophysical parameter and the retrieval of LAI from remote sensing data is the only feasible method for generating LAI products at regional and global scales. However, most LAI retrieval methods use satellite observations at a specific time to retrieve LAI. Because of the impacts of clouds and aerosols, the LAI products generated by these methods are spatially incomplete and temporally discontinuous, and thus they cannot meet the needs of practical applications. To generate high-quality LAI products, four machine learning algorithms, including back-propagation neutral network (BPNN), radial basis function networks (RBFNs), general regression neutral networks (GRNNs), and multi-output support vector regression (MSVR) are proposed to retrieve LAI from time-series Moderate Resolution Imaging Spectroradiometer (MODIS) reflectance data in this study and performance of these machine learning algorithms is evaluated. The results demonstrated that GRNNs, RBFNs, and MSVR exhibited low sensitivity to training sample size, whereas BPNN had high sensitivity. The four algorithms performed slightly better with red, near infrared (NIR), and short wave infrared (SWIR) bands than red and NIR bands, and the results were significantly better than those obtained using single band reflectance data (red or NIR). Regardless of band composition, GRNNs performed better than the other three methods. Among the four algorithms, BPNN required the least training time, whereas MSVR needed the most for any sample size.

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…

Learning Perfectly Secure Cryptography to Protect Communications with Adversarial Neural Cryptography

PubMed Central

2018-01-01

Researches in Artificial Intelligence (AI) have achieved many important breakthroughs, especially in recent years. In some cases, AI learns alone from scratch and performs human tasks faster and better than humans. With the recent advances in AI, it is natural to wonder whether Artificial Neural Networks will be used to successfully create or break cryptographic algorithms. Bibliographic review shows the main approach to this problem have been addressed throughout complex Neural Networks, but without understanding or proving the security of the generated model. This paper presents an analysis of the security of cryptographic algorithms generated by a new technique called Adversarial Neural Cryptography (ANC). Using the proposed network, we show limitations and directions to improve the current approach of ANC. Training the proposed Artificial Neural Network with the improved model of ANC, we show that artificially intelligent agents can learn the unbreakable One-Time Pad (OTP) algorithm, without human knowledge, to communicate securely through an insecure communication channel. This paper shows in which conditions an AI agent can learn a secure encryption scheme. However, it also shows that, without a stronger adversary, it is more likely to obtain an insecure one. PMID:29695066

Learning Perfectly Secure Cryptography to Protect Communications with Adversarial Neural Cryptography.

PubMed

Coutinho, Murilo; de Oliveira Albuquerque, Robson; Borges, Fábio; García Villalba, Luis Javier; Kim, Tai-Hoon

2018-04-24

Researches in Artificial Intelligence (AI) have achieved many important breakthroughs, especially in recent years. In some cases, AI learns alone from scratch and performs human tasks faster and better than humans. With the recent advances in AI, it is natural to wonder whether Artificial Neural Networks will be used to successfully create or break cryptographic algorithms. Bibliographic review shows the main approach to this problem have been addressed throughout complex Neural Networks, but without understanding or proving the security of the generated model. This paper presents an analysis of the security of cryptographic algorithms generated by a new technique called Adversarial Neural Cryptography (ANC). Using the proposed network, we show limitations and directions to improve the current approach of ANC. Training the proposed Artificial Neural Network with the improved model of ANC, we show that artificially intelligent agents can learn the unbreakable One-Time Pad (OTP) algorithm, without human knowledge, to communicate securely through an insecure communication channel. This paper shows in which conditions an AI agent can learn a secure encryption scheme. However, it also shows that, without a stronger adversary, it is more likely to obtain an insecure one.

Uncovering and Managing the Impact of Methodological Choices for the Computational Construction of Socio-Technical Networks from Texts

DTIC Science & Technology

2012-01-01

networks has become fast , cheap, and easy (Shapiro, 1971; Trigg & Weiser, 1986). Modern information and communication technologies, such as the internet...However, once the model is learned, inference time is not subject to this constraint. Therefore, applying the model in end-user applications is fast ...products that facilitate the fast collection and assessment of these networks. For the purpose of analyzing socio-technical networks of geopolitical

A Spatiotemporal Prediction Framework for Air Pollution Based on Deep RNN

NASA Astrophysics Data System (ADS)

Fan, J.; Li, Q.; Hou, J.; Feng, X.; Karimian, H.; Lin, S.

2017-10-01

Time series data in practical applications always contain missing values due to sensor malfunction, network failure, outliers etc. In order to handle missing values in time series, as well as the lack of considering temporal properties in machine learning models, we propose a spatiotemporal prediction framework based on missing value processing algorithms and deep recurrent neural network (DRNN). By using missing tag and missing interval to represent time series patterns, we implement three different missing value fixing algorithms, which are further incorporated into deep neural network that consists of LSTM (Long Short-term Memory) layers and fully connected layers. Real-world air quality and meteorological datasets (Jingjinji area, China) are used for model training and testing. Deep feed forward neural networks (DFNN) and gradient boosting decision trees (GBDT) are trained as baseline models against the proposed DRNN. Performances of three missing value fixing algorithms, as well as different machine learning models are evaluated and analysed. Experiments show that the proposed DRNN framework outperforms both DFNN and GBDT, therefore validating the capacity of the proposed framework. Our results also provides useful insights for better understanding of different strategies that handle missing values.

Hexacopter trajectory control using a neural network

NASA Astrophysics Data System (ADS)

Artale, V.; Collotta, M.; Pau, G.; Ricciardello, A.

2013-10-01

The modern flight control systems are complex due to their non-linear nature. In fact, modern aerospace vehicles are expected to have non-conventional flight envelopes and, then, they must guarantee a high level of robustness and adaptability in order to operate in uncertain environments. Neural Networks (NN), with real-time learning capability, for flight control can be used in applications with manned or unmanned aerial vehicles. Indeed, using proven lower level control algorithms with adaptive elements that exhibit long term learning could help in achieving better adaptation performance while performing aggressive maneuvers. In this paper we show a mathematical modeling and a Neural Network for a hexacopter dynamics in order to develop proper methods for stabilization and trajectory control.

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

Renner, J.; Farbin, A.; Vidal, J. Muñoz

Here, we investigate the potential of using deep learning techniques to reject background events in searches for neutrinoless double beta decay with high pressure xenon time projection chambers capable of detailed track reconstruction. The differences in the topological signatures of background and signal events can be learned by deep neural networks via training over many thousands of events. These networks can then be used to classify further events as signal or background, providing an additional background rejection factor at an acceptable loss of efficiency. The networks trained in this study performed better than previous methods developed based on the usemore » of the same topological signatures by a factor of 1.2 to 1.6, and there is potential for further improvement.« less

Learning alters theta amplitude, theta-gamma coupling and neuronal synchronization in inferotemporal cortex.

PubMed

Kendrick, Keith M; Zhan, Yang; Fischer, Hanno; Nicol, Alister U; Zhang, Xuejuan; Feng, Jianfeng

2011-06-09

How oscillatory brain rhythms alone, or in combination, influence cortical information processing to support learning has yet to be fully established. Local field potential and multi-unit neuronal activity recordings were made from 64-electrode arrays in the inferotemporal cortex of conscious sheep during and after visual discrimination learning of face or object pairs. A neural network model has been developed to simulate and aid functional interpretation of learning-evoked changes. Following learning the amplitude of theta (4-8 Hz), but not gamma (30-70 Hz) oscillations was increased, as was the ratio of theta to gamma. Over 75% of electrodes showed significant coupling between theta phase and gamma amplitude (theta-nested gamma). The strength of this coupling was also increased following learning and this was not simply a consequence of increased theta amplitude. Actual discrimination performance was significantly correlated with theta and theta-gamma coupling changes. Neuronal activity was phase-locked with theta but learning had no effect on firing rates or the magnitude or latencies of visual evoked potentials during stimuli. The neural network model developed showed that a combination of fast and slow inhibitory interneurons could generate theta-nested gamma. By increasing N-methyl-D-aspartate receptor sensitivity in the model similar changes were produced as in inferotemporal cortex after learning. The model showed that these changes could potentiate the firing of downstream neurons by a temporal desynchronization of excitatory neuron output without increasing the firing frequencies of the latter. This desynchronization effect was confirmed in IT neuronal activity following learning and its magnitude was correlated with discrimination performance. Face discrimination learning produces significant increases in both theta amplitude and the strength of theta-gamma coupling in the inferotemporal cortex which are correlated with behavioral performance. A network model which can reproduce these changes suggests that a key function of such learning-evoked alterations in theta and theta-nested gamma activity may be increased temporal desynchronization in neuronal firing leading to optimal timing of inputs to downstream neural networks potentiating their responses. In this way learning can produce potentiation in neural networks simply through altering the temporal pattern of their inputs.

Learning alters theta amplitude, theta-gamma coupling and neuronal synchronization in inferotemporal cortex

PubMed Central

2011-01-01

Background How oscillatory brain rhythms alone, or in combination, influence cortical information processing to support learning has yet to be fully established. Local field potential and multi-unit neuronal activity recordings were made from 64-electrode arrays in the inferotemporal cortex of conscious sheep during and after visual discrimination learning of face or object pairs. A neural network model has been developed to simulate and aid functional interpretation of learning-evoked changes. Results Following learning the amplitude of theta (4-8 Hz), but not gamma (30-70 Hz) oscillations was increased, as was the ratio of theta to gamma. Over 75% of electrodes showed significant coupling between theta phase and gamma amplitude (theta-nested gamma). The strength of this coupling was also increased following learning and this was not simply a consequence of increased theta amplitude. Actual discrimination performance was significantly correlated with theta and theta-gamma coupling changes. Neuronal activity was phase-locked with theta but learning had no effect on firing rates or the magnitude or latencies of visual evoked potentials during stimuli. The neural network model developed showed that a combination of fast and slow inhibitory interneurons could generate theta-nested gamma. By increasing N-methyl-D-aspartate receptor sensitivity in the model similar changes were produced as in inferotemporal cortex after learning. The model showed that these changes could potentiate the firing of downstream neurons by a temporal desynchronization of excitatory neuron output without increasing the firing frequencies of the latter. This desynchronization effect was confirmed in IT neuronal activity following learning and its magnitude was correlated with discrimination performance. Conclusions Face discrimination learning produces significant increases in both theta amplitude and the strength of theta-gamma coupling in the inferotemporal cortex which are correlated with behavioral performance. A network model which can reproduce these changes suggests that a key function of such learning-evoked alterations in theta and theta-nested gamma activity may be increased temporal desynchronization in neuronal firing leading to optimal timing of inputs to downstream neural networks potentiating their responses. In this way learning can produce potentiation in neural networks simply through altering the temporal pattern of their inputs. PMID:21658251

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.

FoxP2 isoforms delineate spatiotemporal transcriptional networks for vocal learning in the zebra finch

PubMed Central

Day, Nancy F; Kimball, Todd Haswell; Aamodt, Caitlin M; Heston, Jonathan B; Hilliard, Austin T; Xiao, Xinshu; White, Stephanie A

2018-01-01

Human speech is one of the few examples of vocal learning among mammals yet ~half of avian species exhibit this ability. Its neurogenetic basis is largely unknown beyond a shared requirement for FoxP2 in both humans and zebra finches. We manipulated FoxP2 isoforms in Area X, a song-specific region of the avian striatopallidum analogous to human anterior striatum, during a critical period for song development. We delineate, for the first time, unique contributions of each isoform to vocal learning. Weighted gene coexpression network analysis of RNA-seq data revealed gene modules correlated to singing, learning, or vocal variability. Coexpression related to singing was found in juvenile and adult Area X whereas coexpression correlated to learning was unique to juveniles. The confluence of learning and singing coexpression in juvenile Area X may underscore molecular processes that drive vocal learning in young zebra finches and, by analogy, humans. PMID:29360038

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.

A spiking neural integrator model of the adaptive control of action by the medial prefrontal cortex.

PubMed

Bekolay, Trevor; Laubach, Mark; Eliasmith, Chris

2014-01-29

Subjects performing simple reaction-time tasks can improve reaction times by learning the expected timing of action-imperative stimuli and preparing movements in advance. Success or failure on the previous trial is often an important factor for determining whether a subject will attempt to time the stimulus or wait for it to occur before initiating action. The medial prefrontal cortex (mPFC) has been implicated in enabling the top-down control of action depending on the outcome of the previous trial. Analysis of spike activity from the rat mPFC suggests that neural integration is a key mechanism for adaptive control in precisely timed tasks. We show through simulation that a spiking neural network consisting of coupled neural integrators captures the neural dynamics of the experimentally recorded mPFC. Errors lead to deviations in the normal dynamics of the system, a process that could enable learning from past mistakes. We expand on this coupled integrator network to construct a spiking neural network that performs a reaction-time task by following either a cue-response or timing strategy, and show that it performs the task with similar reaction times as experimental subjects while maintaining the same spiking dynamics as the experimentally recorded mPFC.

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.

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

NASA Technical Reports Server (NTRS)

Williams, Peggy S.

2004-01-01

The NASA F-15 Intelligent Flight Control System project team has developed a series of flight control concepts designed to demonstrate the benefits of a neural network-based adaptive controller. The objective of the team is to develop and flight-test control systems that use neural network technology to optimize the performance of the aircraft under nominal conditions as well as stabilize the aircraft under failure conditions. Failure conditions include locked or failed control surfaces as well as unforeseen damage that might occur to the aircraft in flight. 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 the baseline aerodynamic derivatives in flight. This set of open-loop flight tests was performed in preparation for a future phase of flights 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 a pitch frequency sweep and an 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. An examination of flight data shows that addition of the flight-identified aerodynamic derivative increments into the simulation improved the pitch handling qualities of the aircraft.

Genetic attack on neural cryptography.

PubMed

Ruttor, Andreas; Kinzel, Wolfgang; Naeh, Rivka; Kanter, Ido

2006-03-01

Different scaling properties for the complexity of bidirectional synchronization and unidirectional learning are essential for the security of neural cryptography. Incrementing the synaptic depth of the networks increases the synchronization time only polynomially, but the success of the geometric attack is reduced exponentially and it clearly fails in the limit of infinite synaptic depth. This method is improved by adding a genetic algorithm, which selects the fittest neural networks. The probability of a successful genetic attack is calculated for different model parameters using numerical simulations. The results show that scaling laws observed in the case of other attacks hold for the improved algorithm, too. The number of networks needed for an effective attack grows exponentially with increasing synaptic depth. In addition, finite-size effects caused by Hebbian and anti-Hebbian learning are analyzed. These learning rules converge to the random walk rule if the synaptic depth is small compared to the square root of the system size.

Machine learning based Intelligent cognitive network using fog computing

NASA Astrophysics Data System (ADS)

Lu, Jingyang; Li, Lun; Chen, Genshe; Shen, Dan; Pham, Khanh; Blasch, Erik

2017-05-01

In this paper, a Cognitive Radio Network (CRN) based on artificial intelligence is proposed to distribute the limited radio spectrum resources more efficiently. The CRN framework can analyze the time-sensitive signal data close to the signal source using fog computing with different types of machine learning techniques. Depending on the computational capabilities of the fog nodes, different features and machine learning techniques are chosen to optimize spectrum allocation. Also, the computing nodes send the periodic signal summary which is much smaller than the original signal to the cloud so that the overall system spectrum source allocation strategies are dynamically updated. Applying fog computing, the system is more adaptive to the local environment and robust to spectrum changes. As most of the signal data is processed at the fog level, it further strengthens the system security by reducing the communication burden of the communications network.

Fast reversible learning based on neurons functioning as anisotropic multiplex hubs

NASA Astrophysics Data System (ADS)

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

2017-05-01

Neural networks are composed of neurons and synapses, which are responsible for learning in a slow adaptive dynamical process. Here we experimentally show that neurons act like independent anisotropic multiplex hubs, which relay and mute incoming signals following their input directions. Theoretically, the observed information routing enriches the computational capabilities of neurons by allowing, for instance, equalization among different information routes in the network, as well as high-frequency transmission of complex time-dependent signals constructed via several parallel routes. In addition, this kind of hubs adaptively eliminate very noisy neurons from the dynamics of the network, preventing masking of information transmission. The timescales for these features are several seconds at most, as opposed to the imprint of information by the synaptic plasticity, a process which exceeds minutes. Results open the horizon to the understanding of fast and adaptive learning realities in higher cognitive brain's functionalities.

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.

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

PubMed

McKinstry, Jeffrey L; Edelman, Gerald M

2013-01-01

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

Genetic attack on neural cryptography

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

Ruttor, Andreas; Kinzel, Wolfgang; Naeh, Rivka

2006-03-15

Different scaling properties for the complexity of bidirectional synchronization and unidirectional learning are essential for the security of neural cryptography. Incrementing the synaptic depth of the networks increases the synchronization time only polynomially, but the success of the geometric attack is reduced exponentially and it clearly fails in the limit of infinite synaptic depth. This method is improved by adding a genetic algorithm, which selects the fittest neural networks. The probability of a successful genetic attack is calculated for different model parameters using numerical simulations. The results show that scaling laws observed in the case of other attacks hold formore » the improved algorithm, too. The number of networks needed for an effective attack grows exponentially with increasing synaptic depth. In addition, finite-size effects caused by Hebbian and anti-Hebbian learning are analyzed. These learning rules converge to the random walk rule if the synaptic depth is small compared to the square root of the system size.« less

Genetic attack on neural cryptography

NASA Astrophysics Data System (ADS)

Ruttor, Andreas; Kinzel, Wolfgang; Naeh, Rivka; Kanter, Ido

2006-03-01

Different scaling properties for the complexity of bidirectional synchronization and unidirectional learning are essential for the security of neural cryptography. Incrementing the synaptic depth of the networks increases the synchronization time only polynomially, but the success of the geometric attack is reduced exponentially and it clearly fails in the limit of infinite synaptic depth. This method is improved by adding a genetic algorithm, which selects the fittest neural networks. The probability of a successful genetic attack is calculated for different model parameters using numerical simulations. The results show that scaling laws observed in the case of other attacks hold for the improved algorithm, too. The number of networks needed for an effective attack grows exponentially with increasing synaptic depth. In addition, finite-size effects caused by Hebbian and anti-Hebbian learning are analyzed. These learning rules converge to the random walk rule if the synaptic depth is small compared to the square root of the system size.

Spatiotemporal coding in the cortex: information flow-based learning in spiking neural networks.

PubMed

Deco, G; Schürmann, B

1999-05-15

We introduce a learning paradigm for networks of integrate-and-fire spiking neurons that is based on an information-theoretic criterion. This criterion can be viewed as a first principle that demonstrates the experimentally observed fact that cortical neurons display synchronous firing for some stimuli and not for others. The principle can be regarded as the postulation of a nonparametric reconstruction method as optimization criteria for learning the required functional connectivity that justifies and explains synchronous firing for binding of features as a mechanism for spatiotemporal coding. This can be expressed in an information-theoretic way by maximizing the discrimination ability between different sensory inputs in minimal time.

Low-cost autonomous perceptron neural network inspired by quantum computation

NASA Astrophysics Data System (ADS)

Zidan, Mohammed; Abdel-Aty, Abdel-Haleem; El-Sadek, Alaa; Zanaty, E. A.; Abdel-Aty, Mahmoud

2017-11-01

Achieving low cost learning with reliable accuracy is one of the important goals to achieve intelligent machines to save time, energy and perform learning process over limited computational resources machines. In this paper, we propose an efficient algorithm for a perceptron neural network inspired by quantum computing composite from a single neuron to classify inspirable linear applications after a single training iteration O(1). The algorithm is applied over a real world data set and the results are outer performs the other state-of-the art algorithms.

MHEG Based Distance Learning System on Information Superhighway.

ERIC Educational Resources Information Center

Lee, SeiHoon; Yoon, KyungSeob; Wang, ChangJong

As the need for distance education grows, requirements for the development of high-speed network-based real-time distance learning systems increases. MHEG-5 is the fifth part of the MHEG (Multimedia and Hypermedia information coding Experts Group) standard, and it defines a final-form representation for application interchange. This paper…

Leveraging the Talent-Driven Organization

ERIC Educational Resources Information Center

Adler, Richard

2010-01-01

This report details how a number of firms are using social networking tools to open up communication, collaboration and learning across boundaries, leveraging these tools to develop new products and real-time solutions for customers. It discusses the qualities of leadership throughout an organization that fosters innovation and learning. And it…

Modular, Hierarchical Learning By Artificial Neural Networks

NASA Technical Reports Server (NTRS)

Baldi, Pierre F.; Toomarian, Nikzad

1996-01-01

Modular and hierarchical approach to supervised learning by artificial neural networks leads to neural networks more structured than neural networks in which all neurons fully interconnected. These networks utilize general feedforward flow of information and sparse recurrent connections to achieve dynamical effects. The modular organization, sparsity of modular units and connections, and fact that learning is much more circumscribed are all attractive features for designing neural-network hardware. Learning streamlined by imitating some aspects of biological neural networks.

Inferring causal molecular networks: empirical assessment through a community-based effort

PubMed Central

Hill, Steven M.; Heiser, Laura M.; Cokelaer, Thomas; Unger, Michael; Nesser, Nicole K.; Carlin, Daniel E.; Zhang, Yang; Sokolov, Artem; Paull, Evan O.; Wong, Chris K.; Graim, Kiley; Bivol, Adrian; Wang, Haizhou; Zhu, Fan; Afsari, Bahman; Danilova, Ludmila V.; Favorov, Alexander V.; Lee, Wai Shing; Taylor, Dane; Hu, Chenyue W.; Long, Byron L.; Noren, David P.; Bisberg, Alexander J.; Mills, Gordon B.; Gray, Joe W.; Kellen, Michael; Norman, Thea; Friend, Stephen; Qutub, Amina A.; Fertig, Elana J.; Guan, Yuanfang; Song, Mingzhou; Stuart, Joshua M.; Spellman, Paul T.; Koeppl, Heinz; Stolovitzky, Gustavo; Saez-Rodriguez, Julio; Mukherjee, Sach

2016-01-01

Inferring molecular networks is a central challenge in computational biology. However, it has remained unclear whether causal, rather than merely correlational, relationships can be effectively inferred in complex biological settings. Here we describe the HPN-DREAM network inference challenge that focused on learning causal influences in signaling networks. We used phosphoprotein data from cancer cell lines as well as in silico data from a nonlinear dynamical model. Using the phosphoprotein data, we scored more than 2,000 networks submitted by challenge participants. The networks spanned 32 biological contexts and were scored in terms of causal validity with respect to unseen interventional data. A number of approaches were effective and incorporating known biology was generally advantageous. Additional sub-challenges considered time-course prediction and visualization. Our results constitute the most comprehensive assessment of causal network inference in a mammalian setting carried out to date and suggest that learning causal relationships may be feasible in complex settings such as disease states. Furthermore, our scoring approach provides a practical way to empirically assess the causal validity of inferred molecular networks. PMID:26901648

Enabling Functional Neural Circuit Simulations with Distributed Computing of Neuromodulated Plasticity

PubMed Central

Potjans, Wiebke; Morrison, Abigail; Diesmann, Markus

2010-01-01

A major puzzle in the field of computational neuroscience is how to relate system-level learning in higher organisms to synaptic plasticity. Recently, plasticity rules depending not only on pre- and post-synaptic activity but also on a third, non-local neuromodulatory signal have emerged as key candidates to bridge the gap between the macroscopic and the microscopic level of learning. Crucial insights into this topic are expected to be gained from simulations of neural systems, as these allow the simultaneous study of the multiple spatial and temporal scales that are involved in the problem. In particular, synaptic plasticity can be studied during the whole learning process, i.e., on a time scale of minutes to hours and across multiple brain areas. Implementing neuromodulated plasticity in large-scale network simulations where the neuromodulatory signal is dynamically generated by the network itself is challenging, because the network structure is commonly defined purely by the connectivity graph without explicit reference to the embedding of the nodes in physical space. Furthermore, the simulation of networks with realistic connectivity entails the use of distributed computing. A neuromodulated synapse must therefore be informed in an efficient way about the neuromodulatory signal, which is typically generated by a population of neurons located on different machines than either the pre- or post-synaptic neuron. Here, we develop a general framework to solve the problem of implementing neuromodulated plasticity in a time-driven distributed simulation, without reference to a particular implementation language, neuromodulator, or neuromodulated plasticity mechanism. We implement our framework in the simulator NEST and demonstrate excellent scaling up to 1024 processors for simulations of a recurrent network incorporating neuromodulated spike-timing dependent plasticity. PMID:21151370

Neural Networks for Modeling and Control of Particle Accelerators

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

Edelen, A. L.; Biedron, S. G.; Chase, B. E.

Myriad nonlinear and complex physical phenomena are host to particle accelerators. They often involve a multitude of interacting systems, are subject to tight performance demands, and should be able to run for extended periods of time with minimal interruptions. Often times, traditional control techniques cannot fully meet these requirements. One promising avenue is to introduce machine learning and sophisticated control techniques inspired by artificial intelligence, particularly in light of recent theoretical and practical advances in these fields. Within machine learning and artificial intelligence, neural networks are particularly well-suited to modeling, control, and diagnostic analysis of complex, nonlinear, and time-varying systems,more » as well as systems with large parameter spaces. Consequently, the use of neural network-based modeling and control techniques could be of significant benefit to particle accelerators. For the same reasons, particle accelerators are also ideal test-beds for these techniques. Moreover, many early attempts to apply neural networks to particle accelerators yielded mixed results due to the relative immaturity of the technology for such tasks. For the purpose of this paper is to re-introduce neural networks to the particle accelerator community and report on some work in neural network control that is being conducted as part of a dedicated collaboration between Fermilab and Colorado State University (CSU). We also describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.« less

Neural Networks for Modeling and Control of Particle Accelerators

NASA Astrophysics Data System (ADS)

Edelen, A. L.; Biedron, S. G.; Chase, B. E.; Edstrom, D.; Milton, S. V.; Stabile, P.

2016-04-01

Particle accelerators are host to myriad nonlinear and complex physical phenomena. They often involve a multitude of interacting systems, are subject to tight performance demands, and should be able to run for extended periods of time with minimal interruptions. Often times, traditional control techniques cannot fully meet these requirements. One promising avenue is to introduce machine learning and sophisticated control techniques inspired by artificial intelligence, particularly in light of recent theoretical and practical advances in these fields. Within machine learning and artificial intelligence, neural networks are particularly well-suited to modeling, control, and diagnostic analysis of complex, nonlinear, and time-varying systems, as well as systems with large parameter spaces. Consequently, the use of neural network-based modeling and control techniques could be of significant benefit to particle accelerators. For the same reasons, particle accelerators are also ideal test-beds for these techniques. Many early attempts to apply neural networks to particle accelerators yielded mixed results due to the relative immaturity of the technology for such tasks. The purpose of this paper is to re-introduce neural networks to the particle accelerator community and report on some work in neural network control that is being conducted as part of a dedicated collaboration between Fermilab and Colorado State University (CSU). We describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.

Neural Networks for Modeling and Control of Particle Accelerators

DOE PAGES

Edelen, A. L.; Biedron, S. G.; Chase, B. E.; ...

2016-04-01

Myriad nonlinear and complex physical phenomena are host to particle accelerators. They often involve a multitude of interacting systems, are subject to tight performance demands, and should be able to run for extended periods of time with minimal interruptions. Often times, traditional control techniques cannot fully meet these requirements. One promising avenue is to introduce machine learning and sophisticated control techniques inspired by artificial intelligence, particularly in light of recent theoretical and practical advances in these fields. Within machine learning and artificial intelligence, neural networks are particularly well-suited to modeling, control, and diagnostic analysis of complex, nonlinear, and time-varying systems,more » as well as systems with large parameter spaces. Consequently, the use of neural network-based modeling and control techniques could be of significant benefit to particle accelerators. For the same reasons, particle accelerators are also ideal test-beds for these techniques. Moreover, many early attempts to apply neural networks to particle accelerators yielded mixed results due to the relative immaturity of the technology for such tasks. For the purpose of this paper is to re-introduce neural networks to the particle accelerator community and report on some work in neural network control that is being conducted as part of a dedicated collaboration between Fermilab and Colorado State University (CSU). We also describe some of the challenges of particle accelerator control, highlight recent advances in neural network techniques, discuss some promising avenues for incorporating neural networks into particle accelerator control systems, and describe a neural network-based control system that is being developed for resonance control of an RF electron gun at the Fermilab Accelerator Science and Technology (FAST) facility, including initial experimental results from a benchmark controller.« less

Event-driven contrastive divergence for spiking neuromorphic systems.

PubMed

Neftci, Emre; Das, Srinjoy; Pedroni, Bruno; Kreutz-Delgado, Kenneth; Cauwenberghs, Gert

2013-01-01

Restricted Boltzmann Machines (RBMs) and Deep Belief Networks have been demonstrated to perform efficiently in a variety of applications, such as dimensionality reduction, feature learning, and classification. Their implementation on neuromorphic hardware platforms emulating large-scale networks of spiking neurons can have significant advantages from the perspectives of scalability, power dissipation and real-time interfacing with the environment. However, the traditional RBM architecture and the commonly used training algorithm known as Contrastive Divergence (CD) are based on discrete updates and exact arithmetics which do not directly map onto a dynamical neural substrate. Here, we present an event-driven variation of CD to train a RBM constructed with Integrate & Fire (I&F) neurons, that is constrained by the limitations of existing and near future neuromorphic hardware platforms. Our strategy is based on neural sampling, which allows us to synthesize a spiking neural network that samples from a target Boltzmann distribution. The recurrent activity of the network replaces the discrete steps of the CD algorithm, while Spike Time Dependent Plasticity (STDP) carries out the weight updates in an online, asynchronous fashion. We demonstrate our approach by training an RBM composed of leaky I&F neurons with STDP synapses to learn a generative model of the MNIST hand-written digit dataset, and by testing it in recognition, generation and cue integration tasks. Our results contribute to a machine learning-driven approach for synthesizing networks of spiking neurons capable of carrying out practical, high-level functionality.

Event-driven contrastive divergence for spiking neuromorphic systems

PubMed Central

Neftci, Emre; Das, Srinjoy; Pedroni, Bruno; Kreutz-Delgado, Kenneth; Cauwenberghs, Gert

2014-01-01

Restricted Boltzmann Machines (RBMs) and Deep Belief Networks have been demonstrated to perform efficiently in a variety of applications, such as dimensionality reduction, feature learning, and classification. Their implementation on neuromorphic hardware platforms emulating large-scale networks of spiking neurons can have significant advantages from the perspectives of scalability, power dissipation and real-time interfacing with the environment. However, the traditional RBM architecture and the commonly used training algorithm known as Contrastive Divergence (CD) are based on discrete updates and exact arithmetics which do not directly map onto a dynamical neural substrate. Here, we present an event-driven variation of CD to train a RBM constructed with Integrate & Fire (I&F) neurons, that is constrained by the limitations of existing and near future neuromorphic hardware platforms. Our strategy is based on neural sampling, which allows us to synthesize a spiking neural network that samples from a target Boltzmann distribution. The recurrent activity of the network replaces the discrete steps of the CD algorithm, while Spike Time Dependent Plasticity (STDP) carries out the weight updates in an online, asynchronous fashion. We demonstrate our approach by training an RBM composed of leaky I&F neurons with STDP synapses to learn a generative model of the MNIST hand-written digit dataset, and by testing it in recognition, generation and cue integration tasks. Our results contribute to a machine learning-driven approach for synthesizing networks of spiking neurons capable of carrying out practical, high-level functionality. PMID:24574952

Wireless Sensor Network Congestion Control Based on Standard Particle Swarm Optimization and Single Neuron PID

PubMed Central

Yang, Xiaoping; Chen, Xueying; Xia, Riting; Qian, Zhihong

2018-01-01

Aiming at the problem of network congestion caused by the large number of data transmissions in wireless routing nodes of wireless sensor network (WSN), this paper puts forward an algorithm based on standard particle swarm–neural PID congestion control (PNPID). Firstly, PID control theory was applied to the queue management of wireless sensor nodes. Then, the self-learning and self-organizing ability of neurons was used to achieve online adjustment of weights to adjust the proportion, integral and differential parameters of the PID controller. Finally, the standard particle swarm optimization to neural PID (NPID) algorithm of initial values of proportion, integral and differential parameters and neuron learning rates were used for online optimization. This paper describes experiments and simulations which show that the PNPID algorithm effectively stabilized queue length near the expected value. At the same time, network performance, such as throughput and packet loss rate, was greatly improved, which alleviated network congestion and improved network QoS. PMID:29671822

Wireless Sensor Network Congestion Control Based on Standard Particle Swarm Optimization and Single Neuron PID.

PubMed

Yang, Xiaoping; Chen, Xueying; Xia, Riting; Qian, Zhihong

2018-04-19

Aiming at the problem of network congestion caused by the large number of data transmissions in wireless routing nodes of wireless sensor network (WSN), this paper puts forward an algorithm based on standard particle swarm⁻neural PID congestion control (PNPID). Firstly, PID control theory was applied to the queue management of wireless sensor nodes. Then, the self-learning and self-organizing ability of neurons was used to achieve online adjustment of weights to adjust the proportion, integral and differential parameters of the PID controller. Finally, the standard particle swarm optimization to neural PID (NPID) algorithm of initial values of proportion, integral and differential parameters and neuron learning rates were used for online optimization. This paper describes experiments and simulations which show that the PNPID algorithm effectively stabilized queue length near the expected value. At the same time, network performance, such as throughput and packet loss rate, was greatly improved, which alleviated network congestion and improved network QoS.

Learning Probabilistic Inference through Spike-Timing-Dependent Plasticity.

PubMed

Pecevski, Dejan; Maass, Wolfgang

2016-01-01

Numerous experimental data show that the brain is able to extract information from complex, uncertain, and often ambiguous experiences. Furthermore, it can use such learnt information for decision making through probabilistic inference. Several models have been proposed that aim at explaining how probabilistic inference could be performed by networks of neurons in the brain. We propose here a model that can also explain how such neural network could acquire the necessary information for that from examples. We show that spike-timing-dependent plasticity in combination with intrinsic plasticity generates in ensembles of pyramidal cells with lateral inhibition a fundamental building block for that: probabilistic associations between neurons that represent through their firing current values of random variables. Furthermore, by combining such adaptive network motifs in a recursive manner the resulting network is enabled to extract statistical information from complex input streams, and to build an internal model for the distribution p (*) that generates the examples it receives. This holds even if p (*) contains higher-order moments. The analysis of this learning process is supported by a rigorous theoretical foundation. Furthermore, we show that the network can use the learnt internal model immediately for prediction, decision making, and other types of probabilistic inference.

Learning Probabilistic Inference through Spike-Timing-Dependent Plasticity123

PubMed Central

Pecevski, Dejan

2016-01-01

Abstract Numerous experimental data show that the brain is able to extract information from complex, uncertain, and often ambiguous experiences. Furthermore, it can use such learnt information for decision making through probabilistic inference. Several models have been proposed that aim at explaining how probabilistic inference could be performed by networks of neurons in the brain. We propose here a model that can also explain how such neural network could acquire the necessary information for that from examples. We show that spike-timing-dependent plasticity in combination with intrinsic plasticity generates in ensembles of pyramidal cells with lateral inhibition a fundamental building block for that: probabilistic associations between neurons that represent through their firing current values of random variables. Furthermore, by combining such adaptive network motifs in a recursive manner the resulting network is enabled to extract statistical information from complex input streams, and to build an internal model for the distribution p* that generates the examples it receives. This holds even if p* contains higher-order moments. The analysis of this learning process is supported by a rigorous theoretical foundation. Furthermore, we show that the network can use the learnt internal model immediately for prediction, decision making, and other types of probabilistic inference. PMID:27419214

On adaptive learning rate that guarantees convergence in feedforward networks.

PubMed

Behera, Laxmidhar; Kumar, Swagat; Patnaik, Awhan

2006-09-01

This paper investigates new learning algorithms (LF I and LF II) based on Lyapunov function for the training of feedforward neural networks. It is observed that such algorithms have interesting parallel with the popular backpropagation (BP) algorithm where the fixed learning rate is replaced by an adaptive learning rate computed using convergence theorem based on Lyapunov stability theory. LF II, a modified version of LF I, has been introduced with an aim to avoid local minima. This modification also helps in improving the convergence speed in some cases. Conditions for achieving global minimum for these kind of algorithms have been studied in detail. The performances of the proposed algorithms are compared with BP algorithm and extended Kalman filtering (EKF) on three bench-mark function approximation problems: XOR, 3-bit parity, and 8-3 encoder. The comparisons are made in terms of number of learning iterations and computational time required for convergence. It is found that the proposed algorithms (LF I and II) are much faster in convergence than other two algorithms to attain same accuracy. Finally, the comparison is made on a complex two-dimensional (2-D) Gabor function and effect of adaptive learning rate for faster convergence is verified. In a nutshell, the investigations made in this paper help us better understand the learning procedure of feedforward neural networks in terms of adaptive learning rate, convergence speed, and local minima.

A prototype implementation of a network-level intrusion detection system. Technical report number CS91-11

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

Heady, R.; Luger, G.F.; Maccabe, A.B.

1991-05-15

This paper presents the implementation of a prototype network level intrusion detection system. The prototype system monitors base level information in network packets (source, destination, packet size, time, and network protocol), learning the normal patterns and announcing anomalies as they occur. The goal of this research is to determine the applicability of current intrusion detection technology to the detection of network level intrusions. In particular, the authors are investigating the possibility of using this technology to detect and react to worm programs.

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…

The Significance of Kinship for Medical Education: Reflections on the Use of a Bespoke Social Network to Support Learners' Professional Identities.

PubMed

Hatzipanagos, Stylianos; John, Bernadette; Chiu, Yuan-Li Tiffany

2016-03-03

Social media can support and sustain communities much better than previous generations of learning technologies, where institutional barriers undermined any initiatives for embedding formal and informal learning. Some of the many types of social media have already had an impact on student learning, based on empirical evidence. One of these, social networking, has the potential to support communication in formal and informal spaces. In this paper we report on the evaluation of an institutional social network-King's Social Harmonisation Project (KINSHIP)-established to foster an improved sense of community, enhance communication, and serve as a space to model digital professionalism for students at King's College London, United Kingdom. Our evaluation focused on a study that examined students' needs and perceptions with regard to the provision of a cross-university platform. Data were collected from students, including those in the field of health and social care, in order to recommend a practical way forward to address current needs in this area. The findings indicate that the majority of the respondents were positive about using a social networking platform to develop their professional voice and profiles. Results suggest that timely promotion of the platform, emphasis on interface and learning design, and a clear identity are required in order to gain acceptance as the institutional social networking site. Empirical findings in this study project an advantage of an institutional social network such a KINSHIP over other social networks (eg, Facebook) because access is limited to staff and students and the site is mainly being used for academic purposes.

A robust sound perception model suitable for neuromorphic implementation.

PubMed

Coath, Martin; Sheik, Sadique; Chicca, Elisabetta; Indiveri, Giacomo; Denham, Susan L; Wennekers, Thomas

2013-01-01

We have recently demonstrated the emergence of dynamic feature sensitivity through exposure to formative stimuli in a real-time neuromorphic system implementing a hybrid analog/digital network of spiking neurons. This network, inspired by models of auditory processing in mammals, includes several mutually connected layers with distance-dependent transmission delays and learning in the form of spike timing dependent plasticity, which effects stimulus-driven changes in the network connectivity. Here we present results that demonstrate that the network is robust to a range of variations in the stimulus pattern, such as are found in naturalistic stimuli and neural responses. This robustness is a property critical to the development of realistic, electronic neuromorphic systems. We analyze the variability of the response of the network to "noisy" stimuli which allows us to characterize the acuity in information-theoretic terms. This provides an objective basis for the quantitative comparison of networks, their connectivity patterns, and learning strategies, which can inform future design decisions. We also show, using stimuli derived from speech samples, that the principles are robust to other challenges, such as variable presentation rate, that would have to be met by systems deployed in the real world. Finally we demonstrate the potential applicability of the approach to real sounds.

The architecture of a network level intrusion detection system

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

Heady, R.; Luger, G.; Maccabe, A.

1990-08-15

This paper presents the preliminary architecture of a network level intrusion detection system. The proposed system will monitor base level information in network packets (source, destination, packet size, and time), learning the normal patterns and announcing anomalies as they occur. The goal of this research is to determine the applicability of current intrusion detection technology to the detection of network level intrusions. In particular, the authors are investigating the possibility of using this technology to detect and react to worm programs.

A Recurrent Probabilistic Neural Network with Dimensionality Reduction Based on Time-series Discriminant Component Analysis.

PubMed

Hayashi, Hideaki; Shibanoki, Taro; Shima, Keisuke; Kurita, Yuichi; Tsuji, Toshio

2015-12-01

This paper proposes a probabilistic neural network (NN) developed on the basis of time-series discriminant component analysis (TSDCA) that can be used to classify high-dimensional time-series patterns. TSDCA involves the compression of high-dimensional time series into a lower dimensional space using a set of orthogonal transformations and the calculation of posterior probabilities based on a continuous-density hidden Markov model with a Gaussian mixture model expressed in the reduced-dimensional space. The analysis can be incorporated into an NN, which is named a time-series discriminant component network (TSDCN), so that parameters of dimensionality reduction and classification can be obtained simultaneously as network coefficients according to a backpropagation through time-based learning algorithm with the Lagrange multiplier method. The TSDCN is considered to enable high-accuracy classification of high-dimensional time-series patterns and to reduce the computation time taken for network training. The validity of the TSDCN is demonstrated for high-dimensional artificial data and electroencephalogram signals in the experiments conducted during the study.

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

PubMed

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

2017-12-01

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

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.

Using YOLO based deep learning network for real time detection and localization of lung nodules from low dose CT scans

NASA Astrophysics Data System (ADS)

Ramachandran S., Sindhu; George, Jose; Skaria, Shibon; V. V., Varun

2018-02-01

Lung cancer is the leading cause of cancer related deaths in the world. The survival rate can be improved if the presence of lung nodules are detected early. This has also led to more focus being given to computer aided detection (CAD) and diagnosis of lung nodules. The arbitrariness of shape, size and texture of lung nodules is a challenge to be faced when developing these detection systems. In the proposed work we use convolutional neural networks to learn the features for nodule detection, replacing the traditional method of handcrafting features like geometric shape or texture. Our network uses the DetectNet architecture based on YOLO (You Only Look Once) to detect the nodules in CT scans of lung. In this architecture, object detection is treated as a regression problem with a single convolutional network simultaneously predicting multiple bounding boxes and class probabilities for those boxes. By performing training using chest CT scans from Lung Image Database Consortium (LIDC), NVIDIA DIGITS and Caffe deep learning framework, we show that nodule detection using this single neural network can result in reasonably low false positive rates with high sensitivity and precision.

Failure prediction using machine learning and time series in optical network.

PubMed

Wang, Zhilong; Zhang, Min; Wang, Danshi; Song, Chuang; Liu, Min; Li, Jin; Lou, Liqi; Liu, Zhuo

2017-08-07

In this paper, we propose a performance monitoring and failure prediction method in optical networks based on machine learning. The primary algorithms of this method are the support vector machine (SVM) and double exponential smoothing (DES). With a focus on risk-aware models in optical networks, the proposed protection plan primarily investigates how to predict the risk of an equipment failure. To the best of our knowledge, this important problem has not yet been fully considered. Experimental results showed that the average prediction accuracy of our method was 95% when predicting the optical equipment failure state. This finding means that our method can forecast an equipment failure risk with high accuracy. Therefore, our proposed DES-SVM method can effectively improve traditional risk-aware models to protect services from possible failures and enhance the optical network stability.

Cognitive-Developmental Learning for a Humanoid Robot: A Caregiver’s Gift

DTIC Science & Technology

2004-05-01

system . We propose a real- time algorithm to infer depth and build 3-dimensional coarse maps for objects through the analysis of cues provided by an... system is well defined at the boundary of these regions (although the derivatives are not). A time domain analysis is presented for a piece-linear... Analysis of Multivariable Systems ......................... 266 D.3.1 Networks of Multiple Neural Oscillators ................. 266 D.3.2 Networks of

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.

Networks and Locations for Student Learning

ERIC Educational Resources Information Center

Jones, Chris; Healing, Graham

2010-01-01

This article examines the significance of place and location at a time when mobile and networked technologies allow students access from a diversity of contexts. The article reports a cultural probe exercise. Over a 24-hour period, undergraduate students received SMS text messages and recorded answers to a fixed set of prompt questions using a…

Building and Sustaining Citywide Afterschool Initiatives: Experiences of the Cross-Cities Network Citywide Afterschool Initiatives.

ERIC Educational Resources Information Center

Hall, Georgia; Harvey, Brooke

This paper highlights the experiences of several citywide after school initiatives from the Cross-Cities Network, describing activities and strategies that contributed to building operational and sustainable citywide delivery of out-of-school time programs. The paper presents evidence of success and notes lessons learned, identifying key elements…

An Evaluation of a Professional Learning Network for Computer Science Teachers

ERIC Educational Resources Information Center

Cutts, Quintin; Robertson, Judy; Donaldson, Peter; O'Donnell, Laurie

2017-01-01

This paper describes and evaluates aspects of a professional development programme for existing CS teachers in secondary schools (PLAN C) which was designed to support teachers at a time of substantial curricular change. The paper's particular focus is on the formation of a teacher professional development network across several hundred teachers…

Cognitive Affordances of the Cyberinfrastructure for Science and Math Learning

ERIC Educational Resources Information Center

Martinez, Michael E.; Peters Burton, Erin E.

2011-01-01

The "cyberinfrastucture" is a broad informational network that entails connections to real-time data sensors as well as tools that permit visualization and other forms of analysis, and that facilitates access to vast scientific databases. This multifaceted network, already a major boon to scientific discovery, now shows exceptional promise in…

Design and simulation of programmable relational optoelectronic time-pulse coded processors as base elements for sorting neural networks

NASA Astrophysics Data System (ADS)

Krasilenko, Vladimir G.; Nikolsky, Alexander I.; Lazarev, Alexander A.; Lazareva, Maria V.

2010-05-01

In the paper we show that the biologically motivated conception of time-pulse encoding usage gives a set of advantages (single methodological basis, universality, tuning simplicity, learning and programming et al) at creation and design of sensor systems with parallel input-output and processing for 2D structures hybrid and next generations neuro-fuzzy neurocomputers. We show design principles of programmable relational optoelectronic time-pulse encoded processors on the base of continuous logic, order logic and temporal waves processes. We consider a structure that execute analog signal extraction, analog and time-pulse coded variables sorting. We offer optoelectronic realization of such base relational order logic element, that consists of time-pulse coded photoconverters (pulse-width and pulse-phase modulators) with direct and complementary outputs, sorting network on logical elements and programmable commutation blocks. We make technical parameters estimations of devices and processors on such base elements by simulation and experimental research: optical input signals power 0.2 - 20 uW, processing time 1 - 10 us, supply voltage 1 - 3 V, consumption power 10 - 100 uW, extended functional possibilities, learning possibilities. We discuss some aspects of possible rules and principles of learning and programmable tuning on required function, relational operation and realization of hardware blocks for modifications of such processors. We show that it is possible to create sorting machines, neural networks and hybrid data-processing systems with untraditional numerical systems and pictures operands on the basis of such quasiuniversal hardware simple blocks with flexible programmable tuning.

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…

Hybrid Spintronic-CMOS Spiking Neural Network with On-Chip Learning: Devices, Circuits, and Systems

NASA Astrophysics Data System (ADS)

Sengupta, Abhronil; Banerjee, Aparajita; Roy, Kaushik

2016-12-01

Over the past decade, spiking neural networks (SNNs) have emerged as one of the popular architectures to emulate the brain. In SNNs, information is temporally encoded and communication between neurons is accomplished by means of spikes. In such networks, spike-timing-dependent plasticity mechanisms require the online programing of synapses based on the temporal information of spikes transmitted by spiking neurons. In this work, we propose a spintronic synapse with decoupled spike-transmission and programing-current paths. The spintronic synapse consists of a ferromagnet-heavy-metal heterostructure where the programing current through the heavy metal generates spin-orbit torque to modulate the device conductance. Low programing energy and fast programing times demonstrate the efficacy of the proposed device as a nanoelectronic synapse. We perform a simulation study based on an experimentally benchmarked device-simulation framework to demonstrate the interfacing of such spintronic synapses with CMOS neurons and learning circuits operating in the transistor subthreshold region to form a network of spiking neurons that can be utilized for pattern-recognition problems.

Quick fuzzy backpropagation algorithm.

PubMed

Nikov, A; Stoeva, S

2001-03-01

A modification of the fuzzy backpropagation (FBP) algorithm called QuickFBP algorithm is proposed, where the computation of the net function is significantly quicker. It is proved that the FBP algorithm is of exponential time complexity, while the QuickFBP algorithm is of polynomial time complexity. Convergence conditions of the QuickFBP, resp. the FBP algorithm are defined and proved for: (1) single output neural networks in case of training patterns with different targets; and (2) multiple output neural networks in case of training patterns with equivalued target vector. They support the automation of the weights training process (quasi-unsupervised learning) establishing the target value(s) depending on the network's input values. In these cases the simulation results confirm the convergence of both algorithms. An example with a large-sized neural network illustrates the significantly greater training speed of the QuickFBP rather than the FBP algorithm. The adaptation of an interactive web system to users on the basis of the QuickFBP algorithm is presented. Since the QuickFBP algorithm ensures quasi-unsupervised learning, this implies its broad applicability in areas of adaptive and adaptable interactive systems, data mining, etc. applications.

Real-Time Adaptive Color Segmentation by Neural Networks

NASA Technical Reports Server (NTRS)

Duong, Tuan A.

2004-01-01

Artificial neural networks that would utilize the cascade error projection (CEP) algorithm have been proposed as means of autonomous, real-time, adaptive color segmentation of images that change with time. In the original intended application, such a neural network would be used to analyze digitized color video images of terrain on a remote planet as viewed from an uninhabited spacecraft approaching the planet. During descent toward the surface of the planet, information on the segmentation of the images into differently colored areas would be updated adaptively in real time to capture changes in contrast, brightness, and resolution, all in an effort to identify a safe and scientifically productive landing site and provide control feedback to steer the spacecraft toward that site. Potential terrestrial applications include monitoring images of crops to detect insect invasions and monitoring of buildings and other facilities to detect intruders. The CEP algorithm is reliable and is well suited to implementation in very-large-scale integrated (VLSI) circuitry. It was chosen over other neural-network learning algorithms because it is better suited to realtime learning: It provides a self-evolving neural-network structure, requires fewer iterations to converge and is more tolerant to low resolution (that is, fewer bits) in the quantization of neural-network synaptic weights. Consequently, a CEP neural network learns relatively quickly, and the circuitry needed to implement it is relatively simple. Like other neural networks, a CEP neural network includes an input layer, hidden units, and output units (see figure). As in other neural networks, a CEP network is presented with a succession of input training patterns, giving rise to a set of outputs that are compared with the desired outputs. Also as in other neural networks, the synaptic weights are updated iteratively in an effort to bring the outputs closer to target values. A distinctive feature of the CEP neural network and algorithm is that each update of synaptic weights takes place in conjunction with the addition of another hidden unit, which then remains in place as still other hidden units are added on subsequent iterations. For a given training pattern, the synaptic weight between (1) the inputs and the previously added hidden units and (2) the newly added hidden unit is updated by an amount proportional to the partial derivative of a quadratic error function with respect to the synaptic weight. The synaptic weight between the newly added hidden unit and each output unit is given by a more complex function that involves the errors between the outputs and their target values, the transfer functions (hyperbolic tangents) of the neural units, and the derivatives of the transfer functions.

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.

Evaluation of Deep Learning Models for Predicting CO2 Flux

NASA Astrophysics Data System (ADS)

Halem, M.; Nguyen, P.; Frankel, D.

2017-12-01

Artificial neural networks have been employed to calculate surface flux measurements from station data because they are able to fit highly nonlinear relations between input and output variables without knowing the detail relationships between the variables. However, the accuracy in performing neural net estimates of CO2 flux from observations of CO2 and other atmospheric variables is influenced by the architecture of the neural model, the availability, and complexity of interactions between physical variables such as wind, temperature, and indirect variables like latent heat, and sensible heat, etc. We evaluate two deep learning models, feed forward and recurrent neural network models to learn how they each respond to the physical measurements, time dependency of the measurements of CO2 concentration, humidity, pressure, temperature, wind speed etc. for predicting the CO2 flux. In this paper, we focus on a) building neural network models for estimating CO2 flux based on DOE data from tower Atmospheric Radiation Measurement data; b) evaluating the impact of choosing the surface variables and model hyper-parameters on the accuracy and predictions of surface flux; c) assessing the applicability of the neural network models on estimate CO2 flux by using OCO-2 satellite data; d) studying the efficiency of using GPU-acceleration for neural network performance using IBM Power AI deep learning software and packages on IBM Minsky system.

Learning fuzzy logic control system

NASA Technical Reports Server (NTRS)

Lung, Leung Kam

1994-01-01

The performance of the Learning Fuzzy Logic Control System (LFLCS), developed in this thesis, has been evaluated. The Learning Fuzzy Logic Controller (LFLC) learns to control the motor by learning the set of teaching values that are generated by a classical PI controller. It is assumed that the classical PI controller is tuned to minimize the error of a position control system of the D.C. motor. The Learning Fuzzy Logic Controller developed in this thesis is a multi-input single-output network. Training of the Learning Fuzzy Logic Controller is implemented off-line. Upon completion of the training process (using Supervised Learning, and Unsupervised Learning), the LFLC replaces the classical PI controller. In this thesis, a closed loop position control system of a D.C. motor using the LFLC is implemented. The primary focus is on the learning capabilities of the Learning Fuzzy Logic Controller. The learning includes symbolic representation of the Input Linguistic Nodes set and Output Linguistic Notes set. In addition, we investigate the knowledge-based representation for the network. As part of the design process, we implement a digital computer simulation of the LFLCS. The computer simulation program is written in 'C' computer language, and it is implemented in DOS platform. The LFLCS, designed in this thesis, has been developed on a IBM compatible 486-DX2 66 computer. First, the performance of the Learning Fuzzy Logic Controller is evaluated by comparing the angular shaft position of the D.C. motor controlled by a conventional PI controller and that controlled by the LFLC. Second, the symbolic representation of the LFLC and the knowledge-based representation for the network are investigated by observing the parameters of the Fuzzy Logic membership functions and the links at each layer of the LFLC. While there are some limitations of application with this approach, the result of the simulation shows that the LFLC is able to control the angular shaft position of the D.C. motor. Furthermore, the LFLC has better performance in rise time, settling time and steady state error than to the conventional PI controller. This abstract accurately represents the content of the candidate's thesis. I recommend its publication.

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.

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.

Reconstructing Genetic Regulatory Networks Using Two-Step Algorithms with the Differential Equation Models of Neural Networks.

PubMed

Chen, Chi-Kan

2017-07-26

The identification of genetic regulatory networks (GRNs) provides insights into complex cellular processes. A class of recurrent neural networks (RNNs) captures the dynamics of GRN. Algorithms combining the RNN and machine learning schemes were proposed to reconstruct small-scale GRNs using gene expression time series. We present new GRN reconstruction methods with neural networks. The RNN is extended to a class of recurrent multilayer perceptrons (RMLPs) with latent nodes. Our methods contain two steps: the edge rank assignment step and the network construction step. The former assigns ranks to all possible edges by a recursive procedure based on the estimated weights of wires of RNN/RMLP (RE RNN /RE RMLP ), and the latter constructs a network consisting of top-ranked edges under which the optimized RNN simulates the gene expression time series. The particle swarm optimization (PSO) is applied to optimize the parameters of RNNs and RMLPs in a two-step algorithm. The proposed RE RNN -RNN and RE RMLP -RNN algorithms are tested on synthetic and experimental gene expression time series of small GRNs of about 10 genes. The experimental time series are from the studies of yeast cell cycle regulated genes and E. coli DNA repair genes. The unstable estimation of RNN using experimental time series having limited data points can lead to fairly arbitrary predicted GRNs. Our methods incorporate RNN and RMLP into a two-step structure learning procedure. Results show that the RE RMLP using the RMLP with a suitable number of latent nodes to reduce the parameter dimension often result in more accurate edge ranks than the RE RNN using the regularized RNN on short simulated time series. Combining by a weighted majority voting rule the networks derived by the RE RMLP -RNN using different numbers of latent nodes in step one to infer the GRN, the method performs consistently and outperforms published algorithms for GRN reconstruction on most benchmark time series. The framework of two-step algorithms can potentially incorporate with different nonlinear differential equation models to reconstruct the GRN.

A novel deep learning approach for classification of EEG motor imagery signals.

PubMed

Tabar, Yousef Rezaei; Halici, Ugur

2017-02-01

Signal classification is an important issue in brain computer interface (BCI) systems. Deep learning approaches have been used successfully in many recent studies to learn features and classify different types of data. However, the number of studies that employ these approaches on BCI applications is very limited. In this study we aim to use deep learning methods to improve classification performance of EEG motor imagery signals. In this study we investigate convolutional neural networks (CNN) and stacked autoencoders (SAE) to classify EEG Motor Imagery signals. A new form of input is introduced to combine time, frequency and location information extracted from EEG signal and it is used in CNN having one 1D convolutional and one max-pooling layers. We also proposed a new deep network by combining CNN and SAE. In this network, the features that are extracted in CNN are classified through the deep network SAE. The classification performance obtained by the proposed method on BCI competition IV dataset 2b in terms of kappa value is 0.547. Our approach yields 9% improvement over the winner algorithm of the competition. Our results show that deep learning methods provide better classification performance compared to other state of art approaches. These methods can be applied successfully to BCI systems where the amount of data is large due to daily recording.

A reconfigurable on-line learning spiking neuromorphic processor comprising 256 neurons and 128K synapses.

PubMed

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

2015-01-01

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

Neural Networks for Signal Processing and Control

NASA Astrophysics Data System (ADS)

Hesselroth, Ted Daniel

Neural networks are developed for controlling a robot-arm and camera system and for processing images. The networks are based upon computational schemes that may be found in the brain. In the first network, a neural map algorithm is employed to control a five-joint pneumatic robot arm and gripper through feedback from two video cameras. The pneumatically driven robot arm employed shares essential mechanical characteristics with skeletal muscle systems. To control the position of the arm, 200 neurons formed a network representing the three-dimensional workspace embedded in a four-dimensional system of coordinates from the two cameras, and learned a set of pressures corresponding to the end effector positions, as well as a set of Jacobian matrices for interpolating between these positions. Because of the properties of the rubber-tube actuators of the arm, the position as a function of supplied pressure is nonlinear, nonseparable, and exhibits hysteresis. Nevertheless, through the neural network learning algorithm the position could be controlled to an accuracy of about one pixel (~3 mm) after two hundred learning steps. Applications of repeated corrections in each step via the Jacobian matrices leads to a very robust control algorithm since the Jacobians learned by the network have to satisfy the weak requirement that they yield a reduction of the distance between gripper and target. The second network is proposed as a model for the mammalian vision system in which backward connections from the primary visual cortex (V1) to the lateral geniculate nucleus play a key role. The application of hebbian learning to the forward and backward connections causes the formation of receptive fields which are sensitive to edges, bars, and spatial frequencies of preferred orientations. The receptive fields are learned in such a way as to maximize the rate of transfer of information from the LGN to V1. Orientational preferences are organized into a feature map in the primary visual cortex by the application of lateral interactions during the learning phase. The organization of the mature network is compared to that found in the macaque monkey by several analytical tests. The capacity of the network to process images is investigated. By a method of reconstructing the input images in terms of V1 activities, the simulations show that images can be faithfully represented in V1 by the proposed network. The signal-to-noise ratio of the image is improved by the representation, and compression ratios of well over two-hundred are possible. Lateral interactions between V1 neurons sharpen their orientational tuning. We further study the dynamics of the processing, showing that the rate of decrease of the error of the reconstruction is maximized for the receptive fields used. Lastly, we employ a Fokker-Planck equation for a more detailed prediction of the error value vs. time. The Fokker-Planck equation for an underdamped system with a driving force is derived, yielding an energy-dependent diffusion coefficient which is the integral of the spectral densities of the force and the velocity of the system. The theory is applied to correlated noise activation and resonant activation. Simulation results for the error of the network vs time are compared to the solution of the Fokker-Planck equation.

Growing a professional network to over 3000 members in less than 4 years: evaluation of InspireNet, British Columbia's virtual nursing health services research network.

PubMed

Frisch, Noreen; Atherton, Pat; Borycki, Elizabeth; Mickelson, Grace; Cordeiro, Jennifer; Novak Lauscher, Helen; Black, Agnes

2014-02-21

Use of Web 2.0 and social media technologies has become a new area of research among health professionals. Much of this work has focused on the use of technologies for health self-management and the ways technologies support communication between care providers and consumers. This paper addresses a new use of technology in providing a platform for health professionals to support professional development, increase knowledge utilization, and promote formal/informal professional communication. Specifically, we report on factors necessary to attract and sustain health professionals' use of a network designed to increase nurses' interest in and use of health services research and to support knowledge utilization activities in British Columbia, Canada. "InspireNet", a virtual professional network for health professionals, is a living laboratory permitting documentation of when and how professionals take up Web 2.0 and social media. Ongoing evaluation documents our experiences in establishing, operating, and evaluating this network. Overall evaluation methods included (1) tracking website use, (2) conducting two member surveys, and (3) soliciting member feedback through focus groups and interviews with those who participated in electronic communities of practice (eCoPs) and other stakeholders. These data have been used to learn about the types of support that seem relevant to network growth. Network growth exceeded all expectations. Members engaged with varying aspects of the network's virtual technologies, such as teams of professionals sharing a common interest, research teams conducting their work, and instructional webinars open to network members. Members used wikis, blogs, and discussion groups to support professional work, as well as a members' database with contact information and areas of interest. The database is accessed approximately 10 times per day. InspireNet public blog posts are accessed roughly 500 times each. At the time of writing, 21 research teams conduct their work virtually using the InspireNet platform; 10 topic-based Action Teams meet to address issues of mutual concern. Nursing and other health professionals, even those who rated themselves as computer literate, required significant mentoring and support in their efforts to adopt their practice to a virtual environment. There was a steep learning curve for professionals to learn to work in a virtual environment and to benefit from the available technologies. Virtual professional networks can be positioned to make a significant contribution to ongoing professional practice and to creating environments supportive of information sharing, mentoring, and learning across geographical boundaries. Nonetheless, creation of a Web 2.0 and social media platform is not sufficient, in and of itself, to attract or sustain a vibrant community of professionals interested in improving their practice. Essential support includes instruction in the use of Web-based activities and time management, a biweekly e-Newsletter, regular communication from leaders, and an annual face-to-face conference.

Searching for exoplanets using artificial intelligence

NASA Astrophysics Data System (ADS)

Pearson, Kyle A.; Palafox, Leon; Griffith, Caitlin A.

2018-02-01

In the last decade, over a million stars were monitored to detect transiting planets. Manual interpretation of potential exoplanet candidates is labor intensive and subject to human error, the results of which are difficult to quantify. Here we present a new method of detecting exoplanet candidates in large planetary search projects which, unlike current methods uses a neural network. Neural networks, also called "deep learning" or "deep nets" are designed to give a computer perception into a specific problem by training it to recognize patterns. Unlike past transit detection algorithms deep nets learn to recognize planet features instead of relying on hand-coded metrics that humans perceive as the most representative. Our convolutional neural network is capable of detecting Earth-like exoplanets in noisy time-series data with a greater accuracy than a least-squares method. Deep nets are highly generalizable allowing data to be evaluated from different time series after interpolation without compromising performance. As validated by our deep net analysis of Kepler light curves, we detect periodic transits consistent with the true period without any model fitting. Our study indicates that machine learning will facilitate the characterization of exoplanets in future analysis of large astronomy data sets.

Providing QoS through machine-learning-driven adaptive multimedia applications.

PubMed

Ruiz, Pedro M; Botía, Juan A; Gómez-Skarmeta, Antonio

2004-06-01

We investigate the optimization of the quality of service (QoS) offered by real-time multimedia adaptive applications through machine learning algorithms. These applications are able to adapt in real time their internal settings (i.e., video sizes, audio and video codecs, among others) to the unpredictably changing capacity of the network. Traditional adaptive applications just select a set of settings to consume less than the available bandwidth. We propose a novel approach in which the selected set of settings is the one which offers a better user-perceived QoS among all those combinations which satisfy the bandwidth restrictions. We use a genetic algorithm to decide when to trigger the adaptation process depending on the network conditions (i.e., loss-rate, jitter, etc.). Additionally, the selection of the new set of settings is done according to a set of rules which model the user-perceived QoS. These rules are learned using the SLIPPER rule induction algorithm over a set of examples extracted from scores provided by real users. We will demonstrate that the proposed approach guarantees a good user-perceived QoS even when the network conditions are constantly changing.

Learning in the model space for cognitive fault diagnosis.

PubMed

Chen, Huanhuan; Tino, Peter; Rodan, Ali; Yao, Xin

2014-01-01

The emergence of large sensor networks has facilitated the collection of large amounts of real-time data to monitor and control complex engineering systems. However, in many cases the collected data may be incomplete or inconsistent, while the underlying environment may be time-varying or unformulated. In this paper, we develop an innovative cognitive fault diagnosis framework that tackles the above challenges. This framework investigates fault diagnosis in the model space instead of the signal space. Learning in the model space is implemented by fitting a series of models using a series of signal segments selected with a sliding window. By investigating the learning techniques in the fitted model space, faulty models can be discriminated from healthy models using a one-class learning algorithm. The framework enables us to construct a fault library when unknown faults occur, which can be regarded as cognitive fault isolation. This paper also theoretically investigates how to measure the pairwise distance between two models in the model space and incorporates the model distance into the learning algorithm in the model space. The results on three benchmark applications and one simulated model for the Barcelona water distribution network confirm the effectiveness of the proposed framework.

A Deep Learning based Approach to Reduced Order Modeling of Fluids using LSTM Neural Networks

NASA Astrophysics Data System (ADS)

Mohan, Arvind; Gaitonde, Datta

2017-11-01

Reduced Order Modeling (ROM) can be used as surrogates to prohibitively expensive simulations to model flow behavior for long time periods. ROM is predicated on extracting dominant spatio-temporal features of the flow from CFD or experimental datasets. We explore ROM development with a deep learning approach, which comprises of learning functional relationships between different variables in large datasets for predictive modeling. Although deep learning and related artificial intelligence based predictive modeling techniques have shown varied success in other fields, such approaches are in their initial stages of application to fluid dynamics. Here, we explore the application of the Long Short Term Memory (LSTM) neural network to sequential data, specifically to predict the time coefficients of Proper Orthogonal Decomposition (POD) modes of the flow for future timesteps, by training it on data at previous timesteps. The approach is demonstrated by constructing ROMs of several canonical flows. Additionally, we show that statistical estimates of stationarity in the training data can indicate a priori how amenable a given flow-field is to this approach. Finally, the potential and limitations of deep learning based ROM approaches will be elucidated and further developments discussed.

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.

Convolutional Neural Network Based on Extreme Learning Machine for Maritime Ships Recognition in Infrared Images.

PubMed

Khellal, Atmane; Ma, Hongbin; Fei, Qing

2018-05-09

The success of Deep Learning models, notably convolutional neural networks (CNNs), makes them the favorable solution for object recognition systems in both visible and infrared domains. However, the lack of training data in the case of maritime ships research leads to poor performance due to the problem of overfitting. In addition, the back-propagation algorithm used to train CNN is very slow and requires tuning many hyperparameters. To overcome these weaknesses, we introduce a new approach fully based on Extreme Learning Machine (ELM) to learn useful CNN features and perform a fast and accurate classification, which is suitable for infrared-based recognition systems. The proposed approach combines an ELM based learning algorithm to train CNN for discriminative features extraction and an ELM based ensemble for classification. The experimental results on VAIS dataset, which is the largest dataset of maritime ships, confirm that the proposed approach outperforms the state-of-the-art models in term of generalization performance and training speed. For instance, the proposed model is up to 950 times faster than the traditional back-propagation based training of convolutional neural networks, primarily for low-level features extraction.

Learning Control Over Emotion Networks Through Connectivity-Based Neurofeedback.

PubMed

Koush, Yury; Meskaldji, Djalel-E; Pichon, Swann; Rey, Gwladys; Rieger, Sebastian W; Linden, David E J; Van De Ville, Dimitri; Vuilleumier, Patrik; Scharnowski, Frank

2017-02-01

Most mental functions are associated with dynamic interactions within functional brain networks. Thus, training individuals to alter functional brain networks might provide novel and powerful means to improve cognitive performance and emotions. Using a novel connectivity-neurofeedback approach based on functional magnetic resonance imaging (fMRI), we show for the first time that participants can learn to change functional brain networks. Specifically, we taught participants control over a key component of the emotion regulation network, in that they learned to increase top-down connectivity from the dorsomedial prefrontal cortex, which is involved in cognitive control, onto the amygdala, which is involved in emotion processing. After training, participants successfully self-regulated the top-down connectivity between these brain areas even without neurofeedback, and this was associated with concomitant increases in subjective valence ratings of emotional stimuli of the participants. Connectivity-based neurofeedback goes beyond previous neurofeedback approaches, which were limited to training localized activity within a brain region. It allows to noninvasively and nonpharmacologically change interconnected functional brain networks directly, thereby resulting in specific behavioral changes. Our results demonstrate that connectivity-based neurofeedback training of emotion regulation networks enhances emotion regulation capabilities. This approach can potentially lead to powerful therapeutic emotion regulation protocols for neuropsychiatric disorders. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Slow feature analysis: unsupervised learning of invariances.

PubMed

Wiskott, Laurenz; Sejnowski, Terrence J

2002-04-01

Invariant features of temporally varying signals are useful for analysis and classification. Slow feature analysis (SFA) is a new method for learning invariant or slowly varying features from a vectorial input signal. It is based on a nonlinear expansion of the input signal and application of principal component analysis to this expanded signal and its time derivative. It is guaranteed to find the optimal solution within a family of functions directly and can learn to extract a large number of decorrelated features, which are ordered by their degree of invariance. SFA can be applied hierarchically to process high-dimensional input signals and extract complex features. SFA is applied first to complex cell tuning properties based on simple cell output, including disparity and motion. Then more complicated input-output functions are learned by repeated application of SFA. Finally, a hierarchical network of SFA modules is presented as a simple model of the visual system. The same unstructured network can learn translation, size, rotation, contrast, or, to a lesser degree, illumination invariance for one-dimensional objects, depending on only the training stimulus. Surprisingly, only a few training objects suffice to achieve good generalization to new objects. The generated representation is suitable for object recognition. Performance degrades if the network is trained to learn multiple invariances simultaneously.

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.

Toward Development of Distance Learning Environment in the Grid

ERIC Educational Resources Information Center

Li, Kuan-Ching; Tsai, Yin-Te; Tsai, Chuan-Ko

2008-01-01

In recent years, with the rapid development of communication and network technologies, distance learning has been popularized and it became one of the most well-known teaching methods, due to its practicability. Over the Internet, learners are free to access new knowledge without restrictions on time or location. However, current distance learning…

Tools for Schools. Volume 12, Number 4, May-June 2009

ERIC Educational Resources Information Center

von Frank, Valerie, Ed.

2009-01-01

This newsletter is published four times a year. It offers articles on school improvement, organizational planning, training, and managing change. This issue contains: (1) Link Up & Learn: Use Technology to Create a Personal Learning Network to Connect with Experts and Mentors Everywhere (Valerie von Frank); (2) NSDC Tool: Get Connected with…

Near Real-Time Comprehension Classification with Artificial Neural Networks: Decoding e-Learner Non-Verbal Behavior

ERIC Educational Resources Information Center

Holmes, Mike; Latham, Annabel; Crockett, Keeley; O'Shea, James D.

2018-01-01

Comprehension is an important cognitive state for learning. Human tutors recognize comprehension and non-comprehension states by interpreting learner non-verbal behavior (NVB). Experienced tutors adapt pedagogy, materials, and instruction to provide additional learning scaffold in the context of perceived learner comprehension. Near real-time…

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…

An Overview on Evaluation of E-Learning/Training Response Time Considering Artificial Neural Networks Modeling

ERIC Educational Resources Information Center

Mustafa, Hassan M. H.; Tourkia, Fadhel Ben; Ramadan, Ramadan Mohamed

2017-01-01

The objective of this piece of research is to interpret and investigate systematically an observed brain functional phenomenon which is associated with proceeding of e-learning processes. More specifically, this work addresses an interesting and challenging educational issue concerned with dynamical evaluation of elearning performance considering…

Analysing Students' Interactions through Social Presence and Social Network Metrics

ERIC Educational Resources Information Center

Martins da Silva, Vanessa Cristina; Siqueira, Sean Wolfgand Matsui

2016-01-01

In online learning environments, tutors have several problems to carry out their activities, such as evaluating the student, knowing the right way to guide each student, promoting discussions, and knowing the right time to interact or let students build knowledge alone. We consider scenarios in which teaching and learning occurs in online social…

Exploring Complex Engineering Learning over Time with Epistemic Network Analysis

ERIC Educational Resources Information Center

Svarovsky, Gina Navoa

2011-01-01

Recently, K-12 engineering education has received increased attention as a pathway to building stronger foundations in math and science and introducing young people to the profession. However, the National Academy of Engineering found that many K-12 engineering programs focus heavily on engineering design and science and math learning while…

Deep learning for studies of galaxy morphology

NASA Astrophysics Data System (ADS)

Tuccillo, D.; Huertas-Company, M.; Decencière, E.; Velasco-Forero, S.

2017-06-01

Establishing accurate morphological measurements of galaxies in a reasonable amount of time for future big-data surveys such as EUCLID, the Large Synoptic Survey Telescope or the Wide Field Infrared Survey Telescope is a challenge. Because of its high level of abstraction with little human intervention, deep learning appears to be a promising approach. Deep learning is a rapidly growing discipline that models high-level patterns in data as complex multilayered networks. In this work we test the ability of deep convolutional networks to provide parametric properties of Hubble Space Telescope like galaxies (half-light radii, Sérsic indices, total flux etc..). We simulate a set of galaxies including point spread function and realistic noise from the CANDELS survey and try to recover the main galaxy parameters using deep-learning. We compare the results with the ones obtained with the commonly used profile fitting based software GALFIT. This way showing that with our method we obtain results at least equally good as the ones obtained with GALFIT but, once trained, with a factor 5 hundred time faster.

Time-lagged autoencoders: Deep learning of slow collective variables for molecular kinetics

NASA Astrophysics Data System (ADS)

Wehmeyer, Christoph; Noé, Frank

2018-06-01

Inspired by the success of deep learning techniques in the physical and chemical sciences, we apply a modification of an autoencoder type deep neural network to the task of dimension reduction of molecular dynamics data. We can show that our time-lagged autoencoder reliably finds low-dimensional embeddings for high-dimensional feature spaces which capture the slow dynamics of the underlying stochastic processes—beyond the capabilities of linear dimension reduction techniques.

Synchronization and Inter-Layer Interactions of Noise-Driven Neural Networks

PubMed Central

Yuniati, Anis; Mai, Te-Lun; Chen, Chi-Ming

2017-01-01

In this study, we used the Hodgkin-Huxley (HH) model of neurons to investigate the phase diagram of a developing single-layer neural network and that of a network consisting of two weakly coupled neural layers. These networks are noise driven and learn through the spike-timing-dependent plasticity (STDP) or the inverse STDP rules. We described how these networks transited from a non-synchronous background activity state (BAS) to a synchronous firing state (SFS) by varying the network connectivity and the learning efficacy. In particular, we studied the interaction between a SFS layer and a BAS layer, and investigated how synchronous firing dynamics was induced in the BAS layer. We further investigated the effect of the inter-layer interaction on a BAS to SFS repair mechanism by considering three types of neuron positioning (random, grid, and lognormal distributions) and two types of inter-layer connections (random and preferential connections). Among these scenarios, we concluded that the repair mechanism has the largest effect for a network with the lognormal neuron positioning and the preferential inter-layer connections. PMID:28197088

Synchronization and Inter-Layer Interactions of Noise-Driven Neural Networks.

PubMed

Yuniati, Anis; Mai, Te-Lun; Chen, Chi-Ming

2017-01-01

In this study, we used the Hodgkin-Huxley (HH) model of neurons to investigate the phase diagram of a developing single-layer neural network and that of a network consisting of two weakly coupled neural layers. These networks are noise driven and learn through the spike-timing-dependent plasticity (STDP) or the inverse STDP rules. We described how these networks transited from a non-synchronous background activity state (BAS) to a synchronous firing state (SFS) by varying the network connectivity and the learning efficacy. In particular, we studied the interaction between a SFS layer and a BAS layer, and investigated how synchronous firing dynamics was induced in the BAS layer. We further investigated the effect of the inter-layer interaction on a BAS to SFS repair mechanism by considering three types of neuron positioning (random, grid, and lognormal distributions) and two types of inter-layer connections (random and preferential connections). Among these scenarios, we concluded that the repair mechanism has the largest effect for a network with the lognormal neuron positioning and the preferential inter-layer connections.

Using an Extended Kalman Filter Learning Algorithm for Feed-Forward Neural Networks to Describe Tracer Correlations

NASA Technical Reports Server (NTRS)

Lary, David J.; Mussa, Yussuf

2004-01-01

In this study a new extended Kalman filter (EKF) learning algorithm for feed-forward neural networks (FFN) is used. With the EKF approach, the training of the FFN can be seen as state estimation for a non-linear stationary process. The EKF method gives excellent convergence performances provided that there is enough computer core memory and that the machine precision is high. Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and CH4 volume mixing ratio (v.m.r.). The neural network was able to reproduce the CH4-N2O correlation with a correlation coefficient between simulated and training values of 0.9997. The neural network Fortran code used is available for download.

Adaptive robotic control driven by a versatile spiking cerebellar network.

PubMed

Casellato, Claudia; Antonietti, Alberto; Garrido, Jesus A; Carrillo, Richard R; Luque, Niceto R; Ros, Eduardo; Pedrocchi, Alessandra; D'Angelo, Egidio

2014-01-01

The cerebellum is involved in a large number of different neural processes, especially in associative learning and in fine motor control. To develop a comprehensive theory of sensorimotor learning and control, it is crucial to determine the neural basis of coding and plasticity embedded into the cerebellar neural circuit and how they are translated into behavioral outcomes in learning paradigms. Learning has to be inferred from the interaction of an embodied system with its real environment, and the same cerebellar principles derived from cell physiology have to be able to drive a variety of tasks of different nature, calling for complex timing and movement patterns. We have coupled a realistic cerebellar spiking neural network (SNN) with a real robot and challenged it in multiple diverse sensorimotor tasks. Encoding and decoding strategies based on neuronal firing rates were applied. Adaptive motor control protocols with acquisition and extinction phases have been designed and tested, including an associative Pavlovian task (Eye blinking classical conditioning), a vestibulo-ocular task and a perturbed arm reaching task operating in closed-loop. The SNN processed in real-time mossy fiber inputs as arbitrary contextual signals, irrespective of whether they conveyed a tone, a vestibular stimulus or the position of a limb. A bidirectional long-term plasticity rule implemented at parallel fibers-Purkinje cell synapses modulated the output activity in the deep cerebellar nuclei. In all tasks, the neurorobot learned to adjust timing and gain of the motor responses by tuning its output discharge. It succeeded in reproducing how human biological systems acquire, extinguish and express knowledge of a noisy and changing world. By varying stimuli and perturbations patterns, real-time control robustness and generalizability were validated. The implicit spiking dynamics of the cerebellar model fulfill timing, prediction and learning functions.

Maximal switchability of centralized networks

NASA Astrophysics Data System (ADS)

Vakulenko, Sergei; Morozov, Ivan; Radulescu, Ovidiu

2016-08-01

We consider continuous time Hopfield-like recurrent networks as dynamical models for gene regulation and neural networks. We are interested in networks that contain n high-degree nodes preferably connected to a large number of N s weakly connected satellites, a property that we call n/N s -centrality. If the hub dynamics is slow, we obtain that the large time network dynamics is completely defined by the hub dynamics. Moreover, such networks are maximally flexible and switchable, in the sense that they can switch from a globally attractive rest state to any structurally stable dynamics when the response time of a special controller hub is changed. In particular, we show that a decrease of the controller hub response time can lead to a sharp variation in the network attractor structure: we can obtain a set of new local attractors, whose number can increase exponentially with N, the total number of nodes of the nework. These new attractors can be periodic or even chaotic. We provide an algorithm, which allows us to design networks with the desired switching properties, or to learn them from time series, by adjusting the interactions between hubs and satellites. Such switchable networks could be used as models for context dependent adaptation in functional genetics or as models for cognitive functions in neuroscience.

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

Deep greedy learning under thermal variability in full diurnal cycles

NASA Astrophysics Data System (ADS)

Rauss, Patrick; Rosario, Dalton

2017-08-01

We study the generalization and scalability behavior of a deep belief network (DBN) applied to a challenging long-wave infrared hyperspectral dataset, consisting of radiance from several manmade and natural materials within a fixed site located 500 m from an observation tower. The collections cover multiple full diurnal cycles and include different atmospheric conditions. Using complementary priors, a DBN uses a greedy algorithm that can learn deep, directed belief networks one layer at a time and has two layers form to provide undirected associative memory. The greedy algorithm initializes a slower learning procedure, which fine-tunes the weights, using a contrastive version of the wake-sleep algorithm. After fine-tuning, a network with three hidden layers forms a very good generative model of the joint distribution of spectral data and their labels, despite significant data variability between and within classes due to environmental and temperature variation occurring within and between full diurnal cycles. We argue, however, that more questions than answers are raised regarding the generalization capacity of these deep nets through experiments aimed at investigating their training and augmented learning behavior.

Exploring the spatio-temporal neural basis of face learning

PubMed Central

Yang, Ying; Xu, Yang; Jew, Carol A.; Pyles, John A.; Kass, Robert E.; Tarr, Michael J.

2017-01-01

Humans are experts at face individuation. Although previous work has identified a network of face-sensitive regions and some of the temporal signatures of face processing, as yet, we do not have a clear understanding of how such face-sensitive regions support learning at different time points. To study the joint spatio-temporal neural basis of face learning, we trained subjects to categorize two groups of novel faces and recorded their neural responses using magnetoencephalography (MEG) throughout learning. A regression analysis of neural responses in face-sensitive regions against behavioral learning curves revealed significant correlations with learning in the majority of the face-sensitive regions in the face network, mostly between 150–250 ms, but also after 300 ms. However, the effect was smaller in nonventral regions (within the superior temporal areas and prefrontal cortex) than that in the ventral regions (within the inferior occipital gyri (IOG), midfusiform gyri (mFUS) and anterior temporal lobes). A multivariate discriminant analysis also revealed that IOG and mFUS, which showed strong correlation effects with learning, exhibited significant discriminability between the two face categories at different time points both between 150–250 ms and after 300 ms. In contrast, the nonventral face-sensitive regions, where correlation effects with learning were smaller, did exhibit some significant discriminability, but mainly after 300 ms. In sum, our findings indicate that early and recurring temporal components arising from ventral face-sensitive regions are critically involved in learning new faces. PMID:28570739

Exploring the spatio-temporal neural basis of face learning.

PubMed

Yang, Ying; Xu, Yang; Jew, Carol A; Pyles, John A; Kass, Robert E; Tarr, Michael J

2017-06-01

Humans are experts at face individuation. Although previous work has identified a network of face-sensitive regions and some of the temporal signatures of face processing, as yet, we do not have a clear understanding of how such face-sensitive regions support learning at different time points. To study the joint spatio-temporal neural basis of face learning, we trained subjects to categorize two groups of novel faces and recorded their neural responses using magnetoencephalography (MEG) throughout learning. A regression analysis of neural responses in face-sensitive regions against behavioral learning curves revealed significant correlations with learning in the majority of the face-sensitive regions in the face network, mostly between 150-250 ms, but also after 300 ms. However, the effect was smaller in nonventral regions (within the superior temporal areas and prefrontal cortex) than that in the ventral regions (within the inferior occipital gyri (IOG), midfusiform gyri (mFUS) and anterior temporal lobes). A multivariate discriminant analysis also revealed that IOG and mFUS, which showed strong correlation effects with learning, exhibited significant discriminability between the two face categories at different time points both between 150-250 ms and after 300 ms. In contrast, the nonventral face-sensitive regions, where correlation effects with learning were smaller, did exhibit some significant discriminability, but mainly after 300 ms. In sum, our findings indicate that early and recurring temporal components arising from ventral face-sensitive regions are critically involved in learning new faces.

Social networking and Internet use among pelvic floor patients: a multicenter survey.

PubMed

Mazloomdoost, Donna; Kanter, Gregory; Chan, Robert C; Deveaneau, Nicolette; Wyman, Allison M; Von Bargen, Emily C; Chaudhry, Zaid; Elshatanoufy, Solafa; Miranne, Jeannine M; Chu, Christine M; Pauls, Rachel N; Arya, Lily A; Antosh, Danielle D

2016-11-01

Internet resources are becoming increasingly important for patients seeking medical knowledge. It is imperative to understand patient use and preferences for using the Internet and social networking websites to optimize patient education. The purpose of this study was to evaluate social networking and Internet use among women with pelvic floor complaints to seek information for their conditions as well as describe the likelihood, preferences, and predictors of website usage. This was a cross-sectional, multicenter study of women presenting to clinical practices of 10 female pelvic medicine and reconstructive surgery fellowship programs across the United States, affiliated with the Fellows' Pelvic Research Network. New female patients presenting with pelvic floor complaints, including urinary incontinence, pelvic organ prolapse, and fecal incontinence were eligible. Participants completed a 24 item questionnaire designed by the authors to assess demographic information, general Internet use, preferences regarding social networking websites, referral patterns, and resources utilized to learn about their pelvic floor complaints. Internet use was quantified as high (≥4 times/wk), moderate (2-3 times/wk), or minimal (≤1 time/wk). Means were used for normally distributed data and medians for data not meeting this assumption. Fisher's exact and χ 2 tests were used to evaluate the associations between variables and Internet use. A total of 282 surveys were analyzed. The majority of participants, 83.3%, were white. The mean age was 55.8 years old. Referrals to urogynecology practices were most frequently from obstetrician/gynecologists (39.9%) and primary care providers (27.8%). Subjects were well distributed geographically, with the largest representation from the South (38.0%). Almost one third (29.9%) were most bothered by prolapse complaints, 22.0% by urgency urinary incontinence, 20.9% by stress urinary incontinence, 14.9% by urgency/frequency symptoms, and 4.1% by fecal incontinence. The majority, 75.0%, described high Internet use, whereas 8.5% moderately and 4.8% minimally used the Internet. Women most often used the Internet for personal motivations including medical research (76.4%), and 42.6% reported Google to be their primary search engine. Despite this, only 4.9% primarily used the Internet to learn about their pelvic floor condition, more commonly consulting an obstetrician-gynecologist for this information (39.4%). The majority (74.1%) held a social networking account, and 45.9% visited these daily. Nearly half, 41.7%, expressed the desire to use social networking websites to learn about their condition. Women <65 years old were significantly more likely to have high Internet use (83.4% vs 68.8%, P = .018) and to desire using social networking websites to learn about their pelvic floor complaint (P = .008). The presenting complaint was not associated with Internet use (P = .905) or the desire to use social networking websites to learn about pelvic floor disorders (P = .201). Women presenting to urogynecology practices have high Internet use and a desire to learn about their conditions via social networking websites. Despite this, obstetrician-gynecologists remain a common resource for information. Nonetheless, urogynecology practices and national organizations would likely benefit from increasing their Internet resources for patient education in pelvic floor disorders, though patients should be made aware of available resources. Copyright © 2016 Elsevier Inc. All rights reserved.

State-space model with deep learning for functional dynamics estimation in resting-state fMRI.

PubMed

Suk, Heung-Il; Wee, Chong-Yaw; Lee, Seong-Whan; Shen, Dinggang

2016-04-01

Studies on resting-state functional Magnetic Resonance Imaging (rs-fMRI) have shown that different brain regions still actively interact with each other while a subject is at rest, and such functional interaction is not stationary but changes over time. In terms of a large-scale brain network, in this paper, we focus on time-varying patterns of functional networks, i.e., functional dynamics, inherent in rs-fMRI, which is one of the emerging issues along with the network modelling. Specifically, we propose a novel methodological architecture that combines deep learning and state-space modelling, and apply it to rs-fMRI based Mild Cognitive Impairment (MCI) diagnosis. We first devise a Deep Auto-Encoder (DAE) to discover hierarchical non-linear functional relations among regions, by which we transform the regional features into an embedding space, whose bases are complex functional networks. Given the embedded functional features, we then use a Hidden Markov Model (HMM) to estimate dynamic characteristics of functional networks inherent in rs-fMRI via internal states, which are unobservable but can be inferred from observations statistically. By building a generative model with an HMM, we estimate the likelihood of the input features of rs-fMRI as belonging to the corresponding status, i.e., MCI or normal healthy control, based on which we identify the clinical label of a testing subject. In order to validate the effectiveness of the proposed method, we performed experiments on two different datasets and compared with state-of-the-art methods in the literature. We also analyzed the functional networks learned by DAE, estimated the functional connectivities by decoding hidden states in HMM, and investigated the estimated functional connectivities by means of a graph-theoretic approach. Copyright © 2016 Elsevier Inc. All rights reserved.

State-space model with deep learning for functional dynamics estimation in resting-state fMRI

PubMed Central

Suk, Heung-Il; Wee, Chong-Yaw; Lee, Seong-Whan; Shen, Dinggang

2017-01-01

Studies on resting-state functional Magnetic Resonance Imaging (rs-fMRI) have shown that different brain regions still actively interact with each other while a subject is at rest, and such functional interaction is not stationary but changes over time. In terms of a large-scale brain network, in this paper, we focus on time-varying patterns of functional networks, i.e., functional dynamics, inherent in rs-fMRI, which is one of the emerging issues along with the network modelling. Specifically, we propose a novel methodological architecture that combines deep learning and state-space modelling, and apply it to rs-fMRI based Mild Cognitive Impairment (MCI) diagnosis. We first devise a Deep Auto-Encoder (DAE) to discover hierarchical non-linear functional relations among regions, by which we transform the regional features into an embedding space, whose bases are complex functional networks. Given the embedded functional features, we then use a Hidden Markov Model (HMM) to estimate dynamic characteristics of functional networks inherent in rs-fMRI via internal states, which are unobservable but can be inferred from observations statistically. By building a generative model with an HMM, we estimate the likelihood of the input features of rs-fMRI as belonging to the corresponding status, i.e., MCI or normal healthy control, based on which we identify the clinical label of a testing subject. In order to validate the effectiveness of the proposed method, we performed experiments on two different datasets and compared with state-of-the-art methods in the literature. We also analyzed the functional networks learned by DAE, estimated the functional connectivities by decoding hidden states in HMM, and investigated the estimated functional connectivities by means of a graph-theoretic approach. PMID:26774612

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

Classification of time-series images using deep convolutional neural networks

NASA Astrophysics Data System (ADS)

Hatami, Nima; Gavet, Yann; Debayle, Johan

2018-04-01

Convolutional Neural Networks (CNN) has achieved a great success in image recognition task by automatically learning a hierarchical feature representation from raw data. While the majority of Time-Series Classification (TSC) literature is focused on 1D signals, this paper uses Recurrence Plots (RP) to transform time-series into 2D texture images and then take advantage of the deep CNN classifier. Image representation of time-series introduces different feature types that are not available for 1D signals, and therefore TSC can be treated as texture image recognition task. CNN model also allows learning different levels of representations together with a classifier, jointly and automatically. Therefore, using RP and CNN in a unified framework is expected to boost the recognition rate of TSC. Experimental results on the UCR time-series classification archive demonstrate competitive accuracy of the proposed approach, compared not only to the existing deep architectures, but also to the state-of-the art TSC algorithms.

Neural networks for tracking of unknown SISO discrete-time nonlinear dynamic systems.

PubMed

Aftab, Muhammad Saleheen; Shafiq, Muhammad

2015-11-01

This article presents a Lyapunov function based neural network tracking (LNT) strategy for single-input, single-output (SISO) discrete-time nonlinear dynamic systems. The proposed LNT architecture is composed of two feedforward neural networks operating as controller and estimator. A Lyapunov function based back propagation learning algorithm is used for online adjustment of the controller and estimator parameters. The controller and estimator error convergence and closed-loop system stability analysis is performed by Lyapunov stability theory. Moreover, two simulation examples and one real-time experiment are investigated as case studies. The achieved results successfully validate the controller performance. Copyright © 2015 ISA. Published by Elsevier Ltd. All rights reserved.

Deep Recurrent Neural Networks for Human Activity Recognition

PubMed Central

Murad, Abdulmajid

2017-01-01

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

Deep Recurrent Neural Networks for Human Activity Recognition.

PubMed

Murad, Abdulmajid; Pyun, Jae-Young

2017-11-06

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

Fault detection and diagnosis using neural network approaches

NASA Technical Reports Server (NTRS)

Kramer, Mark A.

1992-01-01

Neural networks can be used to detect and identify abnormalities in real-time process data. Two basic approaches can be used, the first based on training networks using data representing both normal and abnormal modes of process behavior, and the second based on statistical characterization of the normal mode only. Given data representative of process faults, radial basis function networks can effectively identify failures. This approach is often limited by the lack of fault data, but can be facilitated by process simulation. The second approach employs elliptical and radial basis function neural networks and other models to learn the statistical distributions of process observables under normal conditions. Analytical models of failure modes can then be applied in combination with the neural network models to identify faults. Special methods can be applied to compensate for sensor failures, to produce real-time estimation of missing or failed sensors based on the correlations codified in the neural network.

Autonomous reinforcement learning with experience replay.

PubMed

Wawrzyński, Paweł; Tanwani, Ajay Kumar

2013-05-01

This paper considers the issues of efficiency and autonomy that are required to make reinforcement learning suitable for real-life control tasks. A real-time reinforcement learning algorithm is presented that repeatedly adjusts the control policy with the use of previously collected samples, and autonomously estimates the appropriate step-sizes for the learning updates. The algorithm is based on the actor-critic with experience replay whose step-sizes are determined on-line by an enhanced fixed point algorithm for on-line neural network training. An experimental study with simulated octopus arm and half-cheetah demonstrates the feasibility of the proposed algorithm to solve difficult learning control problems in an autonomous way within reasonably short time. Copyright © 2012 Elsevier Ltd. All rights reserved.

Peer Learning Network: Implementing and Sustaining Cooperative Learning by Teacher Collaboration

ERIC Educational Resources Information Center

Miquel, Ester; Duran, David

2017-01-01

This article describes an in-service teachers', staff-development model "Peer Learning Network" and presents results about its efficiency. "Peer Learning Network" promotes three levels of peer learning simultaneously (among pupils, teachers, and schools). It supports pairs of teachers from several schools, who are linked…

The Integration of Personal Learning Environments & Open Network Learning Environments

ERIC Educational Resources Information Center

Tu, Chih-Hsiung; Sujo-Montes, Laura; Yen, Cherng-Jyh; Chan, Junn-Yih; Blocher, Michael

2012-01-01

Learning management systems traditionally provide structures to guide online learners to achieve their learning goals. Web 2.0 technology empowers learners to create, share, and organize their personal learning environments in open network environments; and allows learners to engage in social networking and collaborating activities. Advanced…

The World as Functional Learning Environment: An Intercultural Learning Network. Interactive Technology Laboratory Report #7.

ERIC Educational Resources Information Center

Cohen, Moshe; And Others

Electronic networks provide new opportunities to create functional learning environments which allow students in many different locations to carry out joint educational activities. A set of participant observation studies was conducted in the context of a cross-cultural, cross-language network called the Intercultural Learning Network in order to…

Satellite -Based Networks for U-Health & U-Learning

NASA Astrophysics Data System (ADS)

Graschew, G.; Roelofs, T. A.; Rakowsky, S.; Schlag, P. M.

2008-08-01

The use of modern Information and Communication Technologies (ICT) as enabling tools for healthcare services (eHealth) introduces new ways of creating ubiquitous access to high-level medical care for all, anytime and anywhere (uHealth). Satellite communication constitutes one of the most flexible methods of broadband communication offering high reliability and cost-effectiveness of connections meeting telemedicine communication requirements. Global networks and the use of computers for educational purposes stimulate and support the development of virtual universities for e-learning. Especially real-time interactive applications can play an important role in tailored and personalised services.

Covering #SAE: A Mobile Reporting Class's Changing Patterns of Interaction on Twitter over Time

ERIC Educational Resources Information Center

Jones, Julie

2015-01-01

This study examined the social network that emerged on Twitter surrounding a mobile reporting class as they covered a national breaking news event. The work introduces pedagogical strategies that enhance students' learning opportunities. Through NodeXL and social network cluster analysis, six groups emerged from the Twitter interactions tied to…

Leadership of Self-Organized Networks Lessons from the War on Terror

ERIC Educational Resources Information Center

Wheatley, Margaret J.

2007-01-01

In the past few decades, scientists have developed a rich understanding of how living systems organize and function. They describe life's capacity to self-organize as networks of interdependent relationships, to learn and adapt, and to grow more capable and orderly over time. These dynamics and descriptions stand in stark contrast to how we humans…

Odyssey of the Mind: Social Networking in Cyberschool

ERIC Educational Resources Information Center

Barbour, Michael K.; Plough, Cory

2012-01-01

K-12 online learning and cyber charter schools have grown at a tremendous rate over the past decade. At the same time, these online programs have struggled to provide the social spaces where students can interact that K-12 schools are traditionally able to provide. Social networking presents a unique opportunity to provide these kinds of social…

Finite-horizon control-constrained nonlinear optimal control using single network adaptive critics.

PubMed

Heydari, Ali; Balakrishnan, Sivasubramanya N

2013-01-01

To synthesize fixed-final-time control-constrained optimal controllers for discrete-time nonlinear control-affine systems, a single neural network (NN)-based controller called the Finite-horizon Single Network Adaptive Critic is developed in this paper. Inputs to the NN are the current system states and the time-to-go, and the network outputs are the costates that are used to compute optimal feedback control. Control constraints are handled through a nonquadratic cost function. Convergence proofs of: 1) the reinforcement learning-based training method to the optimal solution; 2) the training error; and 3) the network weights are provided. The resulting controller is shown to solve the associated time-varying Hamilton-Jacobi-Bellman equation and provide the fixed-final-time optimal solution. Performance of the new synthesis technique is demonstrated through different examples including an attitude control problem wherein a rigid spacecraft performs a finite-time attitude maneuver subject to control bounds. The new formulation has great potential for implementation since it consists of only one NN with single set of weights and it provides comprehensive feedback solutions online, though it is trained offline.

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.

Collaborative Supervised Learning for Sensor Networks

NASA Technical Reports Server (NTRS)

Wagstaff, Kiri L.; Rebbapragada, Umaa; Lane, Terran

2011-01-01

Collaboration methods for distributed machine-learning algorithms involve the specification of communication protocols for the learners, which can query other learners and/or broadcast their findings preemptively. Each learner incorporates information from its neighbors into its own training set, and they are thereby able to bootstrap each other to higher performance. Each learner resides at a different node in the sensor network and makes observations (collects data) independently of the other learners. After being seeded with an initial labeled training set, each learner proceeds to learn in an iterative fashion. New data is collected and classified. The learner can then either broadcast its most confident classifications for use by other learners, or can query neighbors for their classifications of its least confident items. As such, collaborative learning combines elements of both passive (broadcast) and active (query) learning. It also uses ideas from ensemble learning to combine the multiple responses to a given query into a single useful label. This approach has been evaluated against current non-collaborative alternatives, including training a single classifier and deploying it at all nodes with no further learning possible, and permitting learners to learn from their own most confident judgments, absent interaction with their neighbors. On several data sets, it has been consistently found that active collaboration is the best strategy for a distributed learner network. The main advantages include the ability for learning to take place autonomously by collaboration rather than by requiring intervention from an oracle (usually human), and also the ability to learn in a distributed environment, permitting decisions to be made in situ and to yield faster response time.

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

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

PubMed Central

Balduzzi, David; Tononi, Giulio

2012-01-01

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

Indirect adaptive fuzzy wavelet neural network with self- recurrent consequent part for AC servo system.

PubMed

Hou, Runmin; Wang, Li; Gao, Qiang; Hou, Yuanglong; Wang, Chao

2017-09-01

This paper proposes a novel indirect adaptive fuzzy wavelet neural network (IAFWNN) to control the nonlinearity, wide variations in loads, time-variation and uncertain disturbance of the ac servo system. In the proposed approach, the self-recurrent wavelet neural network (SRWNN) is employed to construct an adaptive self-recurrent consequent part for each fuzzy rule of TSK fuzzy model. For the IAFWNN controller, the online learning algorithm is based on back propagation (BP) algorithm. Moreover, an improved particle swarm optimization (IPSO) is used to adapt the learning rate. The aid of an adaptive SRWNN identifier offers the real-time gradient information to the adaptive fuzzy wavelet neural controller to overcome the impact of parameter variations, load disturbances and other uncertainties effectively, and has a good dynamic. The asymptotical stability of the system is guaranteed by using the Lyapunov method. The result of the simulation and the prototype test prove that the proposed are effective and suitable. Copyright © 2017. Published by Elsevier Ltd.

Prolongation of SMAP to Spatiotemporally Seamless Coverage of Continental U.S. Using a Deep Learning Neural Network

NASA Astrophysics Data System (ADS)

Fang, Kuai; Shen, Chaopeng; Kifer, Daniel; Yang, Xiao

2017-11-01

The Soil Moisture Active Passive (SMAP) mission has delivered valuable sensing of surface soil moisture since 2015. However, it has a short time span and irregular revisit schedules. Utilizing a state-of-the-art time series deep learning neural network, Long Short-Term Memory (LSTM), we created a system that predicts SMAP level-3 moisture product with atmospheric forcings, model-simulated moisture, and static physiographic attributes as inputs. The system removes most of the bias with model simulations and improves predicted moisture climatology, achieving small test root-mean-square errors (<0.035) and high-correlation coefficients >0.87 for over 75% of Continental United States, including the forested southeast. As the first application of LSTM in hydrology, we show the proposed network avoids overfitting and is robust for both temporal and spatial extrapolation tests. LSTM generalizes well across regions with distinct climates and environmental settings. With high fidelity to SMAP, LSTM shows great potential for hindcasting, data assimilation, and weather forecasting.

Robust model predictive control of nonlinear systems with unmodeled dynamics and bounded uncertainties based on neural networks.

PubMed

Yan, Zheng; Wang, Jun

2014-03-01

This paper presents a neural network approach to robust model predictive control (MPC) for constrained discrete-time nonlinear systems with unmodeled dynamics affected by bounded uncertainties. The exact nonlinear model of underlying process is not precisely known, but a partially known nominal model is available. This partially known nonlinear model is first decomposed to an affine term plus an unknown high-order term via Jacobian linearization. The linearization residue combined with unmodeled dynamics is then modeled using an extreme learning machine via supervised learning. The minimax methodology is exploited to deal with bounded uncertainties. The minimax optimization problem is reformulated as a convex minimization problem and is iteratively solved by a two-layer recurrent neural network. The proposed neurodynamic approach to nonlinear MPC improves the computational efficiency and sheds a light for real-time implementability of MPC technology. Simulation results are provided to substantiate the effectiveness and characteristics of the proposed approach.

Online Learning Flight Control for Intelligent Flight Control Systems (IFCS)

NASA Technical Reports Server (NTRS)

Niewoehner, Kevin R.; Carter, John (Technical Monitor)

2001-01-01

The research accomplishments for the cooperative agreement 'Online Learning Flight Control for Intelligent Flight Control Systems (IFCS)' include the following: (1) previous IFC program data collection and analysis; (2) IFC program support site (configured IFC systems support network, configured Tornado/VxWorks OS development system, made Configuration and Documentation Management Systems Internet accessible); (3) Airborne Research Test Systems (ARTS) II Hardware (developed hardware requirements specification, developing environmental testing requirements, hardware design, and hardware design development); (4) ARTS II software development laboratory unit (procurement of lab style hardware, configured lab style hardware, and designed interface module equivalent to ARTS II faceplate); (5) program support documentation (developed software development plan, configuration management plan, and software verification and validation plan); (6) LWR algorithm analysis (performed timing and profiling on algorithm); (7) pre-trained neural network analysis; (8) Dynamic Cell Structures (DCS) Neural Network Analysis (performing timing and profiling on algorithm); and (9) conducted technical interchange and quarterly meetings to define IFC research goals.

Decentralized stabilization for a class of continuous-time nonlinear interconnected systems using online learning optimal control approach.

PubMed

Liu, Derong; Wang, Ding; Li, Hongliang

2014-02-01

In this paper, using a neural-network-based online learning optimal control approach, a novel decentralized control strategy is developed to stabilize a class of continuous-time nonlinear interconnected large-scale systems. First, optimal controllers of the isolated subsystems are designed with cost functions reflecting the bounds of interconnections. Then, it is proven that the decentralized control strategy of the overall system can be established by adding appropriate feedback gains to the optimal control policies of the isolated subsystems. Next, an online policy iteration algorithm is presented to solve the Hamilton-Jacobi-Bellman equations related to the optimal control problem. Through constructing a set of critic neural networks, the cost functions can be obtained approximately, followed by the control policies. Furthermore, the dynamics of the estimation errors of the critic networks are verified to be uniformly and ultimately bounded. Finally, a simulation example is provided to illustrate the effectiveness of the present decentralized control scheme.

Synaptic State Matching: A Dynamical Architecture for Predictive Internal Representation and Feature Detection

PubMed Central

Tavazoie, Saeed

2013-01-01

Here we explore the possibility that a core function of sensory cortex is the generation of an internal simulation of sensory environment in real-time. A logical elaboration of this idea leads to a dynamical neural architecture that oscillates between two fundamental network states, one driven by external input, and the other by recurrent synaptic drive in the absence of sensory input. Synaptic strength is modified by a proposed synaptic state matching (SSM) process that ensures equivalence of spike statistics between the two network states. Remarkably, SSM, operating locally at individual synapses, generates accurate and stable network-level predictive internal representations, enabling pattern completion and unsupervised feature detection from noisy sensory input. SSM is a biologically plausible substrate for learning and memory because it brings together sequence learning, feature detection, synaptic homeostasis, and network oscillations under a single unifying computational framework. PMID:23991161

Development of a Deep Learning Algorithm for Automatic Diagnosis of Diabetic Retinopathy.

PubMed

Raju, Manoj; Pagidimarri, Venkatesh; Barreto, Ryan; Kadam, Amrit; Kasivajjala, Vamsichandra; Aswath, Arun

2017-01-01

This paper mainly focuses on the deep learning application in classifying the stage of diabetic retinopathy and detecting the laterality of the eye using funduscopic images. Diabetic retinopathy is a chronic, progressive, sight-threatening disease of the retinal blood vessels. Ophthalmologists diagnose diabetic retinopathy through early funduscopic screening. Normally, there is a time delay in reporting and intervention, apart from the financial cost and risk of blindness associated with it. Using a convolutional neural network based approach for automatic diagnosis of diabetic retinopathy, we trained the prediction network on the publicly available Kaggle dataset. Approximately 35,000 images were used to train the network, which observed a sensitivity of 80.28% and a specificity of 92.29% on the validation dataset of ~53,000 images. Using 8,810 images, the network was trained for detecting the laterality of the eye and observed an accuracy of 93.28% on the validation set of 8,816 images.

The applications of deep neural networks to sdBV classification

NASA Astrophysics Data System (ADS)

Boudreaux, Thomas M.

2017-12-01

With several new large-scale surveys on the horizon, including LSST, TESS, ZTF, and Evryscope, faster and more accurate analysis methods will be required to adequately process the enormous amount of data produced. Deep learning, used in industry for years now, allows for advanced feature detection in minimally prepared datasets at very high speeds; however, despite the advantages of this method, its application to astrophysics has not yet been extensively explored. This dearth may be due to a lack of training data available to researchers. Here we generate synthetic data loosely mimicking the properties of acoustic mode pulsating stars and we show that two separate paradigms of deep learning - the Artificial Neural Network And the Convolutional Neural Network - can both be used to classify this synthetic data effectively. And that additionally this classification can be performed at relatively high levels of accuracy with minimal time spent adjusting network hyperparameters.

Social Learning Network Analysis Model to Identify Learning Patterns Using Ontology Clustering Techniques and Meaningful Learning

ERIC Educational Resources Information Center

Firdausiah Mansur, Andi Besse; Yusof, Norazah

2013-01-01

Clustering on Social Learning Network still not explored widely, especially when the network focuses on e-learning system. Any conventional methods are not really suitable for the e-learning data. SNA requires content analysis, which involves human intervention and need to be carried out manually. Some of the previous clustering techniques need…

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.

A deep learning-based reconstruction of cosmic ray-induced air showers

NASA Astrophysics Data System (ADS)

Erdmann, M.; Glombitza, J.; Walz, D.

2018-01-01

We describe a method of reconstructing air showers induced by cosmic rays using deep learning techniques. We simulate an observatory consisting of ground-based particle detectors with fixed locations on a regular grid. The detector's responses to traversing shower particles are signal amplitudes as a function of time, which provide information on transverse and longitudinal shower properties. In order to take advantage of convolutional network techniques specialized in local pattern recognition, we convert all information to the image-like grid of the detectors. In this way, multiple features, such as arrival times of the first particles and optimized characterizations of time traces, are processed by the network. The reconstruction quality of the cosmic ray arrival direction turns out to be competitive with an analytic reconstruction algorithm. The reconstructed shower direction, energy and shower depth show the expected improvement in resolution for higher cosmic ray energy.

Fuzzy Counter Propagation Neural Network Control for a Class of Nonlinear Dynamical Systems

PubMed Central

Sakhre, Vandana; Jain, Sanjeev; Sapkal, Vilas S.; Agarwal, Dev P.

2015-01-01

Fuzzy Counter Propagation Neural Network (FCPN) controller design is developed, for a class of nonlinear dynamical systems. In this process, the weight connecting between the instar and outstar, that is, input-hidden and hidden-output layer, respectively, is adjusted by using Fuzzy Competitive Learning (FCL). FCL paradigm adopts the principle of learning, which is used to calculate Best Matched Node (BMN) which is proposed. This strategy offers a robust control of nonlinear dynamical systems. FCPN is compared with the existing network like Dynamic Network (DN) and Back Propagation Network (BPN) on the basis of Mean Absolute Error (MAE), Mean Square Error (MSE), Best Fit Rate (BFR), and so forth. It envisages that the proposed FCPN gives better results than DN and BPN. The effectiveness of the proposed FCPN algorithms is demonstrated through simulations of four nonlinear dynamical systems and multiple input and single output (MISO) and a single input and single output (SISO) gas furnace Box-Jenkins time series data. PMID:26366169

Fuzzy Counter Propagation Neural Network Control for a Class of Nonlinear Dynamical Systems.

PubMed

Sakhre, Vandana; Jain, Sanjeev; Sapkal, Vilas S; Agarwal, Dev P

2015-01-01

Fuzzy Counter Propagation Neural Network (FCPN) controller design is developed, for a class of nonlinear dynamical systems. In this process, the weight connecting between the instar and outstar, that is, input-hidden and hidden-output layer, respectively, is adjusted by using Fuzzy Competitive Learning (FCL). FCL paradigm adopts the principle of learning, which is used to calculate Best Matched Node (BMN) which is proposed. This strategy offers a robust control of nonlinear dynamical systems. FCPN is compared with the existing network like Dynamic Network (DN) and Back Propagation Network (BPN) on the basis of Mean Absolute Error (MAE), Mean Square Error (MSE), Best Fit Rate (BFR), and so forth. It envisages that the proposed FCPN gives better results than DN and BPN. The effectiveness of the proposed FCPN algorithms is demonstrated through simulations of four nonlinear dynamical systems and multiple input and single output (MISO) and a single input and single output (SISO) gas furnace Box-Jenkins time series data.

Development and Flight Testing of a Neural Network Based Flight Control System on the NF-15B Aircraft

NASA Technical Reports Server (NTRS)

Bomben, Craig R.; Smolka, James W.; Bosworth, John T.; Silliams-Hayes, Peggy S.; Burken, John J.; Larson, Richard R.; Buschbacher, Mark J.; Maliska, Heather A.

2006-01-01

The Intelligent Flight Control System (IFCS) project at the NASA Dryden Flight Research Center, Edwards AFB, CA, has been investigating the use of neural network based adaptive control on a unique NF-15B test aircraft. The IFCS neural network is a software processor that stores measured aircraft response information to dynamically alter flight control gains. In 2006, the neural network was engaged and allowed to learn in real time to dynamically alter the aircraft handling qualities characteristics in the presence of actual aerodynamic failure conditions injected into the aircraft through the flight control system. The use of neural network and similar adaptive technologies in the design of highly fault and damage tolerant flight control systems shows promise in making future aircraft far more survivable than current technology allows. This paper will present the results of the IFCS flight test program conducted at the NASA Dryden Flight Research Center in 2006, with emphasis on challenges encountered and lessons learned.

Learning in a Network: A "Third Way" between School Learning and Workplace Learning?

ERIC Educational Resources Information Center

Bottrup, Pernille

2005-01-01

Purpose--The aim of this article is to examine network-based learning and discuss how participation in network can enhance organisational learning. Design/methodology/approach--In recent years, companies have increased their collaboration with other organisations, suppliers, customers, etc., in order to meet challenges from a globalised market.…

How Neural Networks Learn from Experience.

ERIC Educational Resources Information Center

Hinton, Geoffrey E.

1992-01-01

Discusses computational studies of learning in artificial neural networks and findings that may provide insights into the learning abilities of the human brain. Describes efforts to test theories about brain information processing, using artificial neural networks. Vignettes include information concerning how a neural network represents…

Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis

NASA Astrophysics Data System (ADS)

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

2017-10-01

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

Learning to play Go using recursive neural networks.

PubMed

Wu, Lin; Baldi, Pierre

2008-11-01

Go is an ancient board game that poses unique opportunities and challenges for artificial intelligence. Currently, there are no computer Go programs that can play at the level of a good human player. However, the emergence of large repositories of games is opening the door for new machine learning approaches to address this challenge. Here we develop a machine learning approach to Go, and related board games, focusing primarily on the problem of learning a good evaluation function in a scalable way. Scalability is essential at multiple levels, from the library of local tactical patterns, to the integration of patterns across the board, to the size of the board itself. The system we propose is capable of automatically learning the propensity of local patterns from a library of games. Propensity and other local tactical information are fed into recursive neural networks, derived from a probabilistic Bayesian network architecture. The recursive neural networks in turn integrate local information across the board in all four cardinal directions and produce local outputs that represent local territory ownership probabilities. The aggregation of these probabilities provides an effective strategic evaluation function that is an estimate of the expected area at the end, or at various other stages, of the game. Local area targets for training can be derived from datasets of games played by human players. In this approach, while requiring a learning time proportional to N(4), skills learned on a board of size N(2) can easily be transferred to boards of other sizes. A system trained using only 9 x 9 amateur game data performs surprisingly well on a test set derived from 19 x 19 professional game data. Possible directions for further improvements are briefly discussed.

A novel joint-processing adaptive nonlinear equalizer using a modular recurrent neural network for chaotic communication systems.

PubMed

Zhao, Haiquan; Zeng, Xiangping; Zhang, Jiashu; Liu, Yangguang; Wang, Xiaomin; Li, Tianrui

2011-01-01

To eliminate nonlinear channel distortion in chaotic communication systems, a novel joint-processing adaptive nonlinear equalizer based on a pipelined recurrent neural network (JPRNN) is proposed, using a modified real-time recurrent learning (RTRL) algorithm. Furthermore, an adaptive amplitude RTRL algorithm is adopted to overcome the deteriorating effect introduced by the nesting process. Computer simulations illustrate that the proposed equalizer outperforms the pipelined recurrent neural network (PRNN) and recurrent neural network (RNN) equalizers. Copyright © 2010 Elsevier Ltd. All rights reserved.

Complex Rotation Quantum Dynamic Neural Networks (CRQDNN) using Complex Quantum Neuron (CQN): Applications to time series prediction.

PubMed

Cui, Yiqian; Shi, Junyou; Wang, Zili

2015-11-01

Quantum Neural Networks (QNN) models have attracted great attention since it innovates a new neural computing manner based on quantum entanglement. However, the existing QNN models are mainly based on the real quantum operations, and the potential of quantum entanglement is not fully exploited. In this paper, we proposes a novel quantum neuron model called Complex Quantum Neuron (CQN) that realizes a deep quantum entanglement. Also, a novel hybrid networks model Complex Rotation Quantum Dynamic Neural Networks (CRQDNN) is proposed based on Complex Quantum Neuron (CQN). CRQDNN is a three layer model with both CQN and classical neurons. An infinite impulse response (IIR) filter is embedded in the Networks model to enable the memory function to process time series inputs. The Levenberg-Marquardt (LM) algorithm is used for fast parameter learning. The networks model is developed to conduct time series predictions. Two application studies are done in this paper, including the chaotic time series prediction and electronic remaining useful life (RUL) prediction. Copyright © 2015 Elsevier Ltd. All rights reserved.

Creating a Powerful Learning Environment with Networked Mobile Learning Devices

ERIC Educational Resources Information Center

Crawford, Valerie M.

2007-01-01

Highly mobile devices can make important information available to teachers in real-time, anywhere in the classroom, and in the form of easy-to-read graphical displays that support classroom decision making. By supporting such important teaching activities, we can create a high-performance classroom that supports teachers and the art of teaching,…

Families, Equity, and Technology: "The 81 Percent Solution" Revisited.

ERIC Educational Resources Information Center

Komoski, Ken

Because students spend only 19% of their time each year in school, families and schools need to focus jointly on "the 81% solution" to improve learning beyond the school day and year. This paper discusses examples of the 81% solution that are being implemented in a variety of communities by the LINCT (Learning and Information Networking for…

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.

Encoding Time in Feedforward Trajectories of a Recurrent Neural Network Model.

PubMed

Hardy, N F; Buonomano, Dean V

2018-02-01

Brain activity evolves through time, creating trajectories of activity that underlie sensorimotor processing, behavior, and learning and memory. Therefore, understanding the temporal nature of neural dynamics is essential to understanding brain function and behavior. In vivo studies have demonstrated that sequential transient activation of neurons can encode time. However, it remains unclear whether these patterns emerge from feedforward network architectures or from recurrent networks and, furthermore, what role network structure plays in timing. We address these issues using a recurrent neural network (RNN) model with distinct populations of excitatory and inhibitory units. Consistent with experimental data, a single RNN could autonomously produce multiple functionally feedforward trajectories, thus potentially encoding multiple timed motor patterns lasting up to several seconds. Importantly, the model accounted for Weber's law, a hallmark of timing behavior. Analysis of network connectivity revealed that efficiency-a measure of network interconnectedness-decreased as the number of stored trajectories increased. Additionally, the balance of excitation (E) and inhibition (I) shifted toward excitation during each unit's activation time, generating the prediction that observed sequential activity relies on dynamic control of the E/I balance. Our results establish for the first time that the same RNN can generate multiple functionally feedforward patterns of activity as a result of dynamic shifts in the E/I balance imposed by the connectome of the RNN. We conclude that recurrent network architectures account for sequential neural activity, as well as for a fundamental signature of timing behavior: Weber's law.

Decoding of finger trajectory from ECoG using deep learning.

PubMed

Xie, Ziqian; Schwartz, Odelia; Prasad, Abhishek

2018-06-01

Conventional decoding pipeline for brain-machine interfaces (BMIs) consists of chained different stages of feature extraction, time-frequency analysis and statistical learning models. Each of these stages uses a different algorithm trained in a sequential manner, which makes it difficult to make the whole system adaptive. The goal was to create an adaptive online system with a single objective function and a single learning algorithm so that the whole system can be trained in parallel to increase the decoding performance. Here, we used deep neural networks consisting of convolutional neural networks (CNN) and a special kind of recurrent neural network (RNN) called long short term memory (LSTM) to address these needs. We used electrocorticography (ECoG) data collected by Kubanek et al. The task consisted of individual finger flexions upon a visual cue. Our model combined a hierarchical feature extractor CNN and a RNN that was able to process sequential data and recognize temporal dynamics in the neural data. CNN was used as the feature extractor and LSTM was used as the regression algorithm to capture the temporal dynamics of the signal. We predicted the finger trajectory using ECoG signals and compared results for the least angle regression (LARS), CNN-LSTM, random forest, LSTM model (LSTM_HC, for using hard-coded features) and a decoding pipeline consisting of band-pass filtering, energy extraction, feature selection and linear regression. The results showed that the deep learning models performed better than the commonly used linear model. The deep learning models not only gave smoother and more realistic trajectories but also learned the transition between movement and rest state. This study demonstrated a decoding network for BMI that involved a convolutional and recurrent neural network model. It integrated the feature extraction pipeline into the convolution and pooling layer and used LSTM layer to capture the state transitions. The discussed network eliminated the need to separately train the model at each step in the decoding pipeline. The whole system can be jointly optimized using stochastic gradient descent and is capable of online learning.

Decoding of finger trajectory from ECoG using deep learning

NASA Astrophysics Data System (ADS)

Xie, Ziqian; Schwartz, Odelia; Prasad, Abhishek

2018-06-01

Objective. Conventional decoding pipeline for brain-machine interfaces (BMIs) consists of chained different stages of feature extraction, time-frequency analysis and statistical learning models. Each of these stages uses a different algorithm trained in a sequential manner, which makes it difficult to make the whole system adaptive. The goal was to create an adaptive online system with a single objective function and a single learning algorithm so that the whole system can be trained in parallel to increase the decoding performance. Here, we used deep neural networks consisting of convolutional neural networks (CNN) and a special kind of recurrent neural network (RNN) called long short term memory (LSTM) to address these needs. Approach. We used electrocorticography (ECoG) data collected by Kubanek et al. The task consisted of individual finger flexions upon a visual cue. Our model combined a hierarchical feature extractor CNN and a RNN that was able to process sequential data and recognize temporal dynamics in the neural data. CNN was used as the feature extractor and LSTM was used as the regression algorithm to capture the temporal dynamics of the signal. Main results. We predicted the finger trajectory using ECoG signals and compared results for the least angle regression (LARS), CNN-LSTM, random forest, LSTM model (LSTM_HC, for using hard-coded features) and a decoding pipeline consisting of band-pass filtering, energy extraction, feature selection and linear regression. The results showed that the deep learning models performed better than the commonly used linear model. The deep learning models not only gave smoother and more realistic trajectories but also learned the transition between movement and rest state. Significance. This study demonstrated a decoding network for BMI that involved a convolutional and recurrent neural network model. It integrated the feature extraction pipeline into the convolution and pooling layer and used LSTM layer to capture the state transitions. The discussed network eliminated the need to separately train the model at each step in the decoding pipeline. The whole system can be jointly optimized using stochastic gradient descent and is capable of online learning.

A high-capacity model for one shot association learning in the brain

PubMed Central

Einarsson, Hafsteinn; Lengler, Johannes; Steger, Angelika

2014-01-01

We present a high-capacity model for one-shot association learning (hetero-associative memory) in sparse networks. We assume that basic patterns are pre-learned in networks and associations between two patterns are presented only once and have to be learned immediately. The model is a combination of an Amit-Fusi like network sparsely connected to a Willshaw type network. The learning procedure is palimpsest and comes from earlier work on one-shot pattern learning. However, in our setup we can enhance the capacity of the network by iterative retrieval. This yields a model for sparse brain-like networks in which populations of a few thousand neurons are capable of learning hundreds of associations even if they are presented only once. The analysis of the model is based on a novel result by Janson et al. on bootstrap percolation in random graphs. PMID:25426060

A high-capacity model for one shot association learning in the brain.

PubMed

Einarsson, Hafsteinn; Lengler, Johannes; Steger, Angelika

2014-01-01

We present a high-capacity model for one-shot association learning (hetero-associative memory) in sparse networks. We assume that basic patterns are pre-learned in networks and associations between two patterns are presented only once and have to be learned immediately. The model is a combination of an Amit-Fusi like network sparsely connected to a Willshaw type network. The learning procedure is palimpsest and comes from earlier work on one-shot pattern learning. However, in our setup we can enhance the capacity of the network by iterative retrieval. This yields a model for sparse brain-like networks in which populations of a few thousand neurons are capable of learning hundreds of associations even if they are presented only once. The analysis of the model is based on a novel result by Janson et al. on bootstrap percolation in random graphs.

The Structural Underpinnings of Policy Learning: A Classroom Policy Simulation

NASA Astrophysics Data System (ADS)

Bird, Stephen

This paper investigates the relationship between the centrality of individual actors in a social network structure and their policy learning performance. In a dynamic comparable to real-world policy networks, results from a classroom simulation demonstrate a strong relationship between centrality in social learning networks and grade performance. Previous research indicates that social network centrality should have a positive effect on learning in other contexts and this link is tested in a policy learning context. Second, the distinction between collaborative learning versus information diffusion processes in policy learning is examined. Third, frequency of interaction is analyzed to determine whether consistent, frequent tics have a greater impact on the learning process. Finally, the data arc analyzed to determine if the benefits of centrality have limitations or thresholds when benefits no longer accrue. These results demonstrate the importance of network structure, and support a collaborative conceptualization of the policy learning process.

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

PubMed

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

2018-02-22

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

How Are Television Networks Involved in Distance Learning?

ERIC Educational Resources Information Center

Bucher, Katherine

1996-01-01

Reviews the involvement of various television networks in distance learning, including public broadcasting stations, Cable in the Classroom, Arts and Entertainment Network, Black Entertainment Television, C-SPAN, CNN (Cable News Network), The Discovery Channel, The Learning Channel, Mind Extension University, The Weather Channel, National Teacher…

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.

Rethinking the learning of belief network probabilities

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

Musick, R.

Belief networks are a powerful tool for knowledge discovery that provide concise, understandable probabilistic models of data. There are methods grounded in probability theory to incrementally update the relationships described by the belief network when new information is seen, to perform complex inferences over any set of variables in the data, to incorporate domain expertise and prior knowledge into the model, and to automatically learn the model from data. This paper concentrates on part of the belief network induction problem, that of learning the quantitative structure (the conditional probabilities), given the qualitative structure. In particular, the current practice of rotemore » learning the probabilities in belief networks can be significantly improved upon. We advance the idea of applying any learning algorithm to the task of conditional probability learning in belief networks, discuss potential benefits, and show results of applying neutral networks and other algorithms to a medium sized car insurance belief network. The results demonstrate from 10 to 100% improvements in model error rates over the current approaches.« less

Conduction Delay Learning Model for Unsupervised and Supervised Classification of Spatio-Temporal Spike Patterns

PubMed Central

Matsubara, Takashi

2017-01-01

Precise spike timing is considered to play a fundamental role in communications and signal processing in biological neural networks. Understanding the mechanism of spike timing adjustment would deepen our understanding of biological systems and enable advanced engineering applications such as efficient computational architectures. However, the biological mechanisms that adjust and maintain spike timing remain unclear. Existing algorithms adopt a supervised approach, which adjusts the axonal conduction delay and synaptic efficacy until the spike timings approximate the desired timings. This study proposes a spike timing-dependent learning model that adjusts the axonal conduction delay and synaptic efficacy in both unsupervised and supervised manners. The proposed learning algorithm approximates the Expectation-Maximization algorithm, and classifies the input data encoded into spatio-temporal spike patterns. Even in the supervised classification, the algorithm requires no external spikes indicating the desired spike timings unlike existing algorithms. Furthermore, because the algorithm is consistent with biological models and hypotheses found in existing biological studies, it could capture the mechanism underlying biological delay learning. PMID:29209191

Conduction Delay Learning Model for Unsupervised and Supervised Classification of Spatio-Temporal Spike Patterns.

PubMed

Matsubara, Takashi

2017-01-01

Precise spike timing is considered to play a fundamental role in communications and signal processing in biological neural networks. Understanding the mechanism of spike timing adjustment would deepen our understanding of biological systems and enable advanced engineering applications such as efficient computational architectures. However, the biological mechanisms that adjust and maintain spike timing remain unclear. Existing algorithms adopt a supervised approach, which adjusts the axonal conduction delay and synaptic efficacy until the spike timings approximate the desired timings. This study proposes a spike timing-dependent learning model that adjusts the axonal conduction delay and synaptic efficacy in both unsupervised and supervised manners. The proposed learning algorithm approximates the Expectation-Maximization algorithm, and classifies the input data encoded into spatio-temporal spike patterns. Even in the supervised classification, the algorithm requires no external spikes indicating the desired spike timings unlike existing algorithms. Furthermore, because the algorithm is consistent with biological models and hypotheses found in existing biological studies, it could capture the mechanism underlying biological delay learning.

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

PubMed

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

2016-10-01

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

The effect of learning on bursting.

PubMed

Stegenga, Jan; Le Feber, Joost; Marani, Enrico; Rutten, Wim L C

2009-04-01

We have studied the effect that learning a new stimulus-response (SR) relationship had within a neuronal network cultured on a multielectrode array. For training, we applied repetitive focal electrical stimulation delivered at a low rate (<1/s). Stimulation was withdrawn when a desired SR success ratio was achieved. It has been shown elsewhere, and we verified that this training algorithm, named conditional repetitive stimulation (CRS), can be used to strengthen an initially weak SR. So far, it remained unclear what the role of the rest of the network during learning was. We therefore studied the effect of CRS on spontaneously occurring network bursts. To this end, we made profiles of the firing rates within network bursts. We have earlier shown that these profiles change shape on a time base of several hours during spontaneous development. We show here that profiles of summed activity, called burst profiles, changed shape at an increased rate during CRS. This suggests that the whole network was involved in making the changes necessary to incorporate the desired SR relationship. However, a local (path-specific) component to learning was also found by analyzing profiles of single-electrode-activity phase profiles. Phase profiles that were not part of the SR relationship changed far less during CRS than the phase profiles of the electrodes that were part of the SR relationship. Finally, the manner in which phase profiles changed shape varied and could not be linked to the SR relationship.

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

NASA Astrophysics Data System (ADS)

Antropova, Natasha; Huynh, Benjamin; Giger, Maryellen

2018-02-01

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

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

PubMed Central

Staras, Kevin

2016-01-01

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

Learning in Artificial Neural Systems

NASA Technical Reports Server (NTRS)

Matheus, Christopher J.; Hohensee, William E.

1987-01-01

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

Brain tumor segmentation in multi-spectral MRI using convolutional neural networks (CNN).

PubMed

Iqbal, Sajid; Ghani, M Usman; Saba, Tanzila; Rehman, Amjad

2018-04-01

A tumor could be found in any area of the brain and could be of any size, shape, and contrast. There may exist multiple tumors of different types in a human brain at the same time. Accurate tumor area segmentation is considered primary step for treatment of brain tumors. Deep Learning is a set of promising techniques that could provide better results as compared to nondeep learning techniques for segmenting timorous part inside a brain. This article presents a deep convolutional neural network (CNN) to segment brain tumors in MRIs. The proposed network uses BRATS segmentation challenge dataset which is composed of images obtained through four different modalities. Accordingly, we present an extended version of existing network to solve segmentation problem. The network architecture consists of multiple neural network layers connected in sequential order with the feeding of Convolutional feature maps at the peer level. Experimental results on BRATS 2015 benchmark data thus show the usability of the proposed approach and its superiority over the other approaches in this area of research. © 2018 Wiley Periodicals, Inc.