Associative Memory: An Spiking Neural Network Robotic Implementation

This article proposes a novel minimalist bio-inspired associative memory (AM) mechanism based on a spiking neural network acting as a controller in simple virtual and physical robots. As such, several main features of a general AM concept were reproduced. Using the strength of temporal coding at the single spike resolution level, this study approaches the AM phenomenon with basic examples in the visual modality. Specifically, the AM include varying time delays in synaptic links and asymmetry in the spike-timing dependent plasticity learning rules to solve visual tasks of pattern-matching, pattern-completion and noise-tolerance for autoassociative and heteroassociative memories. This preliminary work could serve as a step toward future comparative analysis with traditional artificial neural networks.

[1]  Jan Wessnitzer,et al.  A model of associative learning in the mushroom body , 2008, Biological Cybernetics.

[2]  Y. Dan,et al.  Spike timing-dependent plasticity: a Hebbian learning rule. , 2008, Annual review of neuroscience.

[3]  Thomas Wennekers,et al.  Associative memory in networks of spiking neurons , 2001, Neural Networks.

[4]  A. Lansner,et al.  A working memory model based on fast Hebbian learning , 2003, Network.

[5]  K. Siwicki,et al.  Associative learning and memory in Drosophila: beyond olfactory conditioning , 2003, Behavioural Processes.

[6]  Teuvo Kohonen,et al.  Associative memory. A system-theoretical approach , 1977 .

[7]  T. Kohonen.  Self-organized formation of topographically correct feature maps , 1982 .

[8]  Brent Komer,et al.  A unified theoretical approach for biological cognition and learning , 2016, Current Opinion in Behavioral Sciences.

[9]  Alireza Sadeghian,et al.  A bidirectional associative memory based on cortical spiking neurons using temporal coding , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[10]  Cristian Jimenez-Romero,et al.  Designing Behaviour in Bio-inspired Robots Using Associative Topologies of Spiking-Neural-Networks , 2016, EAI Endorsed Trans. Collab. Comput..

[11]  Steve B. Furber,et al.  Efficient SpiNNaker simulation of a heteroassociative memory using the Neural Engineering Framework , 2016, 2016 International Joint Conference on Neural Networks (IJCNN).

[12]  M. Giurfa.  Cognition with few neurons: higher-order learning in insects , 2013, Trends in Neurosciences.

[13]  Mounir Boukadoum,et al.  Classical conditioning in different temporal constraints: an STDP learning rule for robots controlled by spiking neural networks , 2012, Adapt. Behav..

[14]  R. Hawkins,et al.  Associative learning in invertebrates. , 2015, Cold Spring Harbor perspectives in biology.

[15]  M. Giurfa,et al.  Conceptual learning by miniature brains , 2013, Proceedings of the Royal Society B: Biological Sciences.

[16]  Aram Kawewong,et al.  Self-Organizing Incremental Associative Memory-Based Robot Navigation , 2012, IEICE Trans. Inf. Syst..

[17]  Chin Hiong Tan,et al.  A computationally efficient associative memory model of hippocampus CA3 by spiking neurons , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[18]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[19]  Stefan Wermter,et al.  Temporal sequence detection with spiking neurons: towards recognizing robot language instructions , 2006, Connect. Sci..

[20]  Edmund T. Rolls,et al.  The mechanisms for pattern completion and pattern separation in the hippocampus , 2013, Front. Syst. Neurosci..

[21]  F. Attneave,et al.  The Organization of Behavior: A Neuropsychological Theory , 1949 .

[22]  Ken Lukowiak,et al.  Associative learning and memory in Lymnaea stagnalis: how well do they remember? , 2003, Journal of Experimental Biology.

[23]  G. Bi,et al.  Synaptic Modifications in Cultured Hippocampal Neurons: Dependence on Spike Timing, Synaptic Strength, and Postsynaptic Cell Type , 1998, The Journal of Neuroscience.

[24]  Evan L Ardiel,et al.  An elegant mind: learning and memory in Caenorhabditis elegans. , 2010, Learning & memory.

[25]  Y. Dan,et al.  Spike-timing-dependent synaptic modification induced by natural spike trains , 2002, Nature.

[26]  Kay Chen Tan,et al.  A Spiking Neural Network Model for Associative Memory Using Temporal Codes , 2015 .

[27]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[28]  LEARNING TEMPORAL CORRELATION BETWEEN INPUT NEURONS BY USING DENDRITIC PROPAGATION DELAYS AND STOCHASTIC SYNAPSES. , 2001 .

[29]  Florian Ostendorf,et al.  A role of the human thalamus in predicting the perceptual consequences of eye movements , 2013, Front. Syst. Neurosci..

[30]  Florian Engert,et al.  Prey Capture Behavior Evoked by Simple Visual Stimuli in Larval Zebrafish , 2011, Front. Syst. Neurosci..

[31]  Claude F. Touzet,et al.  Modeling and Simulation of Elementary Robot Behaviors using Associative Memories , 2006 .

[32]  Sylvain Chartier,et al.  2009 Special Issue: A new bidirectional heteroassociative memory encompassing correlational, competitive and topological properties , 2009 .

[33]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[34]  Shaojuan Zhu,et al.  Reinforcement learning in associative memory , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[35]  H. Shouval,et al.  Stochastic properties of synaptic transmission affect the shape of spike time-dependent plasticity curves. , 2005, Journal of neurophysiology.

[36]  G. Bi,et al.  Temporal asymmetry in spike timing-dependent synaptic plasticity , 2002, Physiology & Behavior.

[37]  D. Amit.  The Hebbian paradigm reintegrated: Local reverberations as internal representations , 1995, Behavioral and Brain Sciences.

[38]  Gail A. Carpenter,et al.  Neural network models for pattern recognition and associative memory , 1989, Neural Networks.

[39]  Eugene M. Izhikevich,et al.  Simple model of spiking neurons , 2003, IEEE Trans. Neural Networks.

[40]  Teuvo Kohonen,et al.  Self-organized formation of topologically correct feature maps , 2004, Biological Cybernetics.

[41]  Kay Chen Tan,et al.  A brain-inspired spiking neural network model with temporal encoding and learning , 2014, Neurocomputing.

[42]  Pierre Poirier,et al.  AI-SIMCOG: a simulator for spiking neurons and multiple animats’ behaviours , 2009, Neural Computing and Applications.