Access the full text.
Sign up today, get DeepDyve free for 14 days.
D. Hebb (1988)
The organization of behavior
E. Izhikevich (2007)
Solving the distal reward problem through linkage of STDP and dopamine signalingBMC Neuroscience, 8
E. Ronco (1995)
Modular Neural Networks: a state of the art
M. Kubát (2017)
An Introduction to Machine Learning
Rapid Application Prototyping for Hardware
D. Heiss-Czedik (1997)
An Introduction to Genetic Algorithms.Artificial Life, 3
S. Pande, F. Morgan, G. Smit, T. Bruintjes, J. Rutgers, Brian McGinley, Seamus Cawley, J. Harkin, L. McDaid (2013)
Fixed latency on-chip interconnect for hardware spiking neural network architecturesParallel Comput., 39
Bart Happel, J. Murre (1994)
Design and evolution of modular neural network architecturesNeural Networks, 7
Dorit Baras, R. Meir (2007)
Reinforcement Learning, Spike-Time-Dependent Plasticity, and the BCM RuleNeural Computation, 19
Jorge Santos, Luís Alexandre, J. Sá (2006)
Modular Neural Network Task Decomposition Via Entropic ClusteringSixth International Conference on Intelligent Systems Design and Applications, 1
R. Vaughan (2008)
Massively multi-robot simulation in stageSwarm Intelligence, 2
E Izhikevich (2007)
Solving the distal reward problem through linkage of STDP and dopamine signalingCereb Cortex, 17
D. Osherson, S. Weinstein, M. Stob (1993)
Modular learning
W. Gerstner, W. Kistler (2002)
Spiking Neuron Models: Single Neurons, Populations, Plasticity
Florian Landis, T. Ott, R. Stoop (2010)
Hebbian Self-Organizing Integrate-and-Fire Networks for Data ClusteringNeural Computation, 22
S. Bohté, J. Kok (2005)
Applications of spiking neural networksInf. Process. Lett., 95
S. Guan, Shanchun Li, Syn Tan (2004)
NEURAL NETWORK TASK DECOMPOSITION BASED ON OUTPUT PARTITIONING
E. Paolo (2002)
Spike-Timing Dependent Plasticity for Evolved RobotsAdapt. Behav., 10
T. Natschläger, Berthold Ruf (1998)
Online Clustering with Spiking Neurons Using Temporal Coding
S. Pande, F. Morgan, Seamus Cawley, Brian McGinley, J. Harkin, Snaider Carrillo, L. McDaid (2011)
Addressing the Hardware Resource Requirements of Network-on-chip based Neural Architectures
J. Hopfield (1995)
Pattern recognition computation using action potential timing for stimulus representationNature, 376
J. Thangavelautham, G. D’Eleuterio (2004)
A Neuroevolutionary Approach to Emergent Task Decomposition
S. Bohté, J. Kok, H. Poutré (2000)
Error-backpropagation in temporally encoded networks of spiking neuronsNeurocomputing, 48
G. Auda, M. Kamel (1999)
Modular Neural Networks A SurveyInternational journal of neural systems, 9 2
Seamus Cawley, F. Morgan, Brian McGinley, S. Pande, L. McDaid, Snaider Carrillo, J. Harkin (2011)
Hardware spiking neural network prototyping and applicationGenetic Programming and Evolvable Machines, 12
R. Legenstein, Christian Naeger, W. Maass (2005)
What Can a Neuron Learn with Spike-Timing-Dependent Plasticity?Neural Computation, 17
T. Binzegger, R. Douglas, K. Martin (2007)
Stereotypical Bouton Clustering of Individual Neurons in Cat Primary Visual CortexThe Journal of Neuroscience, 27
Razvan Florian (2007)
Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic PlasticityNeural Computation, 19
M. Farries, A. Fairhall (2007)
Reinforcement learning with modulated spike timing dependent synaptic plasticity.Journal of neurophysiology, 98 6
Neural Comput & Applic
A Robust Layered Control Syste For A Mobile Robot
S. Haykin (1998)
Neural Networks: A Comprehensive Foundation
S. Johannes, B. Wieringa, M. Matzke, T. Münte (1996)
Hierarchical visual stimuli: electrophysiological evidence for separate left hemispheric global and local processing mechanisms in humansNeuroscience Letters, 210
Dmitri Vainbrand, R. Ginosar (2011)
Scalable network-on-chip architecture for configurable neural networksMicroprocess. Microsystems, 35
Masood Zamani, A. Sadeghian, S. Chartier (2010)
A bidirectional associative memory based on cortical spiking neurons using temporal codingThe 2010 International Joint Conference on Neural Networks (IJCNN)
V. Khare, X. Yao, B. Sendhoff, Yaochu Jin, H. Wersing (2005)
Co-evolutionary modular neural networks for automatic problem decomposition2005 IEEE Congress on Evolutionary Computation, 3
Deliang Wang (2001)
Unsupervised Learning: Foundations of Neural ComputationAI Mag., 22
E. Vasilaki, Nicolas Frémaux, R. Urbanczik, W. Senn, W. Gerstner (2009)
Spike-Based Reinforcement Learning in Continuous State and Action Space: When Policy Gradient Methods FailPLoS Computational Biology, 5
S. Bohté, H. Poutré, J. Kok (2002)
Unsupervised clustering with spiking neurons by sparse temporal coding and multilayer RBF networksIEEE transactions on neural networks, 13 2
F. Morgan, Seamus Cawley, Brian McGinely, S. Pande, L. McDaid, B. Glackin, John Maher, J. Harkin (2009)
Exploring the evolution of NoC-based Spiking Neural Networks on FPGAs2009 International Conference on Field-Programmable Technology
J. Harkin, F. Morgan, L. McDaid, S. Hall, Brian McGinley, Seamus Cawley (2009)
A Reconfigurable and Biologically Inspired Paradigm for Computation Using Network-On-Chip and Spiking Neural NetworksInt. J. Reconfigurable Comput., 2009
W. Maas (1997)
Networks of spiking neurons: the third generation of neural network modelsNeural Networks, 14
S. Pande, F. Morgan, Seamus Cawley, T. Bruintjes, G. Smit, Brian McGinley, Snaider Carrillo, J. Harkin, L. McDaid (2013)
Modular Neural Tile Architecture for Compact Embedded Hardware Spiking Neural NetworkNeural Processing Letters, 38
R. Legenstein, Dejan Pecevski, W. Maass (2008)
A Learning Theory for Reward-Modulated Spike-Timing-Dependent Plasticity with Application to BiofeedbackPLoS Computational Biology, 4
W. Maass (1996)
Networks of Spiking Neurons: The Third Generation of Neural Network ModelsElectron. Colloquium Comput. Complex., TR96
Bao-Liang Lu, Masami Ito (1999)
Task decomposition and module combination based on class relations: a modular neural network for pattern classificationIEEE transactions on neural networks, 10 5
M. Pearson, A. Pipe, B. Mitchinson, K. Gurney, C. Melhuish, Ian Gilhespy, M. Nibouche (2007)
Implementing Spiking Neural Networks for Real-Time Signal-Processing and Control Applications: A Model-Validated FPGA ApproachIEEE Transactions on Neural Networks, 18
W. Gerstner, J. Hemmen (1992)
Associative memory in a network of ‘spiking’ neuronsNetwork: Computation In Neural Systems, 3
D. Essen, C. Anderson, D. Felleman (1992)
Information processing in the primate visual system: an integrated systems perspective.Science, 255 5043
H. Hagras, Anthony Pounds-Cornish, M. Colley, V. Callaghan, G. Clarke (2004)
Evolving spiking neural network controllers for autonomous robotsIEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004, 5
F. Attneave, M. B., D. Hebb (1949)
The Organization of Behavior: A Neuropsychological Theory
Razvan Florian (2005)
A reinforcement learning algorithm for spiking neural networksSeventh International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC'05)
Spiking neural networks (SNNs) are well suited for functions such as data/pattern classification, estimation, prediction, signal processing and robotic control applications. Whereas the real-world embedded applications are often multi-functional with orthogonal or contradicting functional requirements. The EMBRACE hardware modular SNN architecture has been previously reported as an embedded computing platform for complex real-world applications. The EMBRACE architecture employs genetic algorithm (GA) for training the SNN which offers faster prototyping of SNN applications, but exhibits a number of limitations including poor scalability and search space explosions for the evolution of large-scale, complex, real-world applications. This paper investigates the limitations of evolving real-world embedded applications with orthogonal functional goals on hardware SNN using GA-based training. This paper presents a novel, fast and efficient application prototyping technique using the EMBRACE hardware modular SNN architecture and the GA-based evolution platform. Modular design and evolution of a robotic navigational controller application decomposed into obstacle avoidance controller and speed and direction manager application subtasks is presented. The proposed modular evolution technique successfully integrates the orthogonal functionalities of the application and helps to overcome contradicting application scenarios gracefully. Results illustrate that the modular evolution of the application reduces the SNN configuration search space and complexity for the GA-based SNN evolution, offering rapid and successful prototyping of complex applications on the hardware SNN platform. The paper presents validation results of the evolved robotic application implemented on the EMBRACE architecture prototyped on Xilinx Virtex-6 FPGA interacting with the player-stage robotics simulator.
Neural Computing and Applications – Springer Journals
Published: Feb 8, 2016
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.