ReSuMe-New Supervised Learning Method for Spiking Neural Networks

In this report I introduce ReSuMe a new supervised learning method for Spiking Neural Networks. The research on ReSuMe has been primarily motivated by the need of inventing an efficient learni ng method for control of movement for the physically disabled. Howeve r, thorough analysis of the ReSuMe method reveals its suitability not on ly to the task of movement control, but also to other real-life applicatio ns including modeling, identification and control of diverse non-statio nary, nonlinear objects. ReSuMe integrates the idea of learning windows, known from t he spikebased Hebbian rules, with a novel concept of remote supervis ion. General overview of the method, the basic definitions, the netwo rk architecture and the details of the learning algorithm are presented . The properties of ReSuMe such as locality, computational simplicity a nd the online processing suitability are discussed. ReSuMe learning abi lities are illustrated in a verification experiment.

[1]  A. Aertsen,et al.  Synaptic plasticity in rat hippocampal slice cultures: local "Hebbian" conjunction of pre- and postsynaptic stimulation leads to distributed synaptic enhancement. , 1989, Proceedings of the National Academy of Sciences of the United States of America.

[2]  Wolfgang Maass,et al.  Noisy Spiking Neurons with Temporal Coding have more Computational Power than Sigmoidal Neurons , 1996, NIPS.

[3]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

[4]  Wolfgang Maass,et al.  Networks of spiking neurons can emulate arbitrary Hopfield nets in temporal coding , 1997 .

[5]  Christopher J. Bishop,et al.  Pulsed Neural Networks , 1998 .

[6]  T. Sinkjær,et al.  Control of Movement for the Physically Disabled , 2000 .

[7]  Li I. Zhang,et al.  Selective Presynaptic Propagation of Long-Term Potentiation in Defined Neural Networks , 2000, The Journal of Neuroscience.

[8]  James J. Abbas,et al.  Using electrical stimulation to control standing posture , 2001 .

[9]  S. Schultz.  Principles of Neural Science, 4th ed. , 2001 .

[10]  G. Johnson.  Control of Movement for the Physically Disabled , 2001 .

[11]  Guo-Qiang Bi,et al.  Spatiotemporal specificity of synaptic plasticity: cellular rules and mechanisms , 2002, Biological Cybernetics.

[12]  David Barber,et al.  Learning in Spiking Neural Assemblies , 2002, NIPS.

[13]  Werner M. Kistler,et al.  Spike-timing dependent synaptic plasticity: a phenomenological framework , 2002, Biological Cybernetics.

[14]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[15]  Wulfram Gerstner,et al.  Mathematical formulations of Hebbian learning , 2002, Biological Cybernetics.

[16]  Henry Markram,et al.  Computer models and analysis tools for neural microcircuits , 2003 .

[17]  Xiaohui Xie,et al.  Learning in neural networks by reinforcement of irregular spiking. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[18]  Henry Markram,et al.  Computational models for generic cortical microcircuits , 2004 .

[19]  Michael Schmitt,et al.  Learning Temporally Encoded Patterns in Networks of Spiking Neurons , 2004, Neural Processing Letters.

[20]  S. Thorpe,et al.  Spike times make sense , 2005, Trends in Neurosciences.

[21]  Andrzej J. Kasinski,et al.  Experimental Demonstration of Learning Properties of a New Supervised Learning Method for the Spiking Neural Networks , 2005, ICANN.