A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks

We use a supervised multi-spike learning algorithm for spiking neural networks (SNNs) with temporal encoding to simulate the learning mechanism of biological neurons in which the SNN output spike trains are encoded by firing times. We first analyze why existing gradient-descent-based learning methods for SNNs have difficulty in achieving multi-spike learning. We then propose a new multi-spike learning method for SNNs based on gradient descent that solves the problems of error function construction and interference among multiple output spikes during learning. The method could be widely applied to single spiking neurons to learn desired output spike trains and to multilayer SNNs to solve classification problems. By overcoming learning interference among multiple spikes, our method has high learning accuracy when there are a relatively large number of output spikes in need of learning. We also develop an output encoding strategy with respect to multiple spikes for classification problems. This effectively improves the classification accuracy of multi-spike learning compared to that of single-spike learning.

[1]  Hojjat Adeli,et al.  Improved spiking neural networks for EEG classification and epilepsy and seizure detection , 2007, Integr. Comput. Aided Eng..

[2]  Jianguo Xin,et al.  Supervised learning with spiking neural networks , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[3]  D. Johnston,et al.  Regulation of Synaptic Efficacy by Coincidence of Postsynaptic APs and EPSPs , 1997 .

[4]  Peter Tiño,et al.  Learning Beyond Finite Memory in Recurrent Networks of Spiking Neurons , 2005, ICNC.

[5]  Filip Ponulak,et al.  Analysis of the ReSuMe Learning Process For Spiking Neural Networks , 2008, Int. J. Appl. Math. Comput. Sci..

[6]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[7]  E. Adrian,et al.  The impulses produced by sensory nerve‐endings , 1926 .

[8]  Ammar Belatreche,et al.  A Method for Supervised Training of Spiking Neural Networks , 2003 .

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

[10]  Daniel Richardson,et al.  Linear Algebra for Time Series of Spikes , 2005, ESANN.

[11]  B. Schrauwen,et al.  Extending SpikeProp , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

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

[13]  Andrzej J. Kasinski,et al.  Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting , 2010, Neural Computation.

[14]  E. Adrian,et al.  The impulses produced by sensory nerve-endings: Part II. The response of a Single End-Organ. , 2006, The Journal of physiology.

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

[16]  Robert A. Legenstein,et al.  What Can a Neuron Learn with Spike-Timing-Dependent Plasticity? , 2005, Neural Computation.

[17]  Tao Xiong,et al.  A combined SVM and LDA approach for classification , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[18]  Linda Bushnell,et al.  Fast Modifications of the SpikeProp Algorithm , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[19]  O. Mangasarian,et al.  Multisurface method of pattern separation for medical diagnosis applied to breast cytology. , 1990, Proceedings of the National Academy of Sciences of the United States of America.

[20]  Hojjat Adeli,et al.  A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection , 2009, Neural Networks.

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

[22]  Sander M. Bohte,et al.  Error-backpropagation in temporally encoded networks of spiking neurons , 2000, Neurocomputing.

[23]  D. J. Newman,et al.  UCI Repository of Machine Learning Database , 1998 .

[24]  John P. Miller,et al.  Temporal encoding in nervous systems: A rigorous definition , 1995, Journal of Computational Neuroscience.

[25]  M. Alexander,et al.  Principles of Neural Science , 1981 .

[26]  Rufin van Rullen,et al.  Rate Coding Versus Temporal Order Coding: What the Retinal Ganglion Cells Tell the Visual Cortex , 2001, Neural Computation.

[27]  F. Ponulak.  ReSuMe-New Supervised Learning Method for Spiking Neural Networks , 2005 .

[28]  Patrick D. Roberts,et al.  Spike timing dependent synaptic plasticity in biological systems , 2002, Biological Cybernetics.

[29]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[30]  Andrzej Kasiński,et al.  Comparison of supervised learning methods for spike time coding in spiking neural networks , 2006 .

[31]  N. K. Bose,et al.  Neural Network Fundamentals with Graphs, Algorithms and Applications , 1995 .

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

[33]  Wolfgang Maass,et al.  Fast Sigmoidal Networks via Spiking Neurons , 1997, Neural Computation.

[34]  Razvan V. Florian,et al.  Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity , 2007, Neural Computation.

[35]  H. Sompolinsky,et al.  The tempotron: a neuron that learns spike timing–based decisions , 2006, Nature Neuroscience.

[36]  Robert A. Legenstein,et al.  A Learning Theory for Reward-Modulated Spike-Timing-Dependent Plasticity with Application to Biofeedback , 2008, PLoS Comput. Biol..

[37]  Paul H. E. Tiesinga,et al.  A New Correlation-Based Measure of Spike Timing Reliability , 2002, Neurocomputing.

[38]  Hieu Tat Nguyen,et al.  A gradient descent rule for spiking neurons emitting multiple spikes , 2005, Inf. Process. Lett..

[39]  Qingxiang Wu,et al.  Learning under weight constraints in networks of temporal encoding spiking neurons , 2006, Neurocomputing.

[40]  Benjamin Schrauwen,et al.  Backpropagation for Population-Temporal Coded Spiking Neural Networks , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[41]  Eric Postma,et al.  Combining Structural Connectivity and Response Latencies to Model the Structure of the Visual System , 2008, PLoS Comput. Biol..

[42]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[43]  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.

[44]  Jean-Pascal Pfister,et al.  Optimal Spike-Timing-Dependent Plasticity for Precise Action Potential Firing in Supervised Learning , 2005, Neural Computation.