Delay learning and polychronization for reservoir computing

We propose a multi-timescale learning rule for spiking neuron networks, in the line of the recently emerging field of reservoir computing. The reservoir is a network model of spiking neurons, with random topology and driven by STDP (spike-time-dependent plasticity), a temporal Hebbian unsupervised learning mode, biologically observed. The model is further driven by a supervised learning algorithm, based on a margin criterion, that affects the synaptic delays linking the network to the readout neurons, with classification as a goal task. The network processing and the resulting performance can be explained by the concept of polychronization, proposed by Izhikevich [Polychronization: computation with spikes, Neural Comput. 18(2) (2006) 245-282], on physiological grounds. The model emphasizes that polychronization can be used as a tool for exploiting the computational power of synaptic delays and for monitoring the topology and activity of a spiking neuron network.

[1]  H. Paugam-Moisy,et al.  Evolutionary supervision of a dynamical neural network allows learning with on-going weights , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[2]  Niraj S. Desai,et al.  Plasticity in the intrinsic excitability of cortical pyramidal neurons , 1999, Nature Neuroscience.

[3]  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.

[4]  Gordon Pipa,et al.  2007 Special Issue: Fading memory and time series prediction in recurrent networks with different forms of plasticity , 2007 .

[5]  Henry Markram,et al.  Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations , 2002, Neural Computation.

[6]  M. Poo,et al.  Coincident Pre- and Postsynaptic Activity Modifies GABAergic Synapses by Postsynaptic Changes in Cl− Transporter Activity , 2003, Neuron.

[7]  Michael Schmitt,et al.  On the Complexity of Learning for Spiking Neurons with Temporal Coding , 1999, Inf. Comput..

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

[9]  Benjamin Schrauwen,et al.  An overview of reservoir computing: theory, applications and implementations , 2007, ESANN.

[10]  Moshe Abeles,et al.  Corticonics: Neural Circuits of Cerebral Cortex , 1991 .

[11]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[12]  José Carlos Príncipe,et al.  Special issue on echo state networks and liquid state machines , 2007, Neural Networks.

[13]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[14]  Wulfram Gerstner,et al.  Spiking Neuron Models: An Introduction , 2002 .

[15]  Jirí Sgall,et al.  On the Nonlearnability of a Single Spiking Neuron , 2005, Neural Computation.

[16]  Michael Schmitt,et al.  On the complexity of learning for a spiking neuron (extended abstract) , 1997, COLT '97.

[17]  W. Gerstner,et al.  Generalized Bienenstock-Cooper-Munro rule for spiking neurons that maximizes information transmission. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[18]  T Natschläger,et al.  Spatial and temporal pattern analysis via spiking neurons. , 1998, Network.

[19]  Hélène Paugam-Moisy.  Spiking Neuron Networks A survey , 2006 .

[20]  Martin Schneider,et al.  Activity-Dependent Development of Axonal and Dendritic Delays, or, Why Synaptic Transmission Should Be Unreliable , 2002, Neural Computation.

[21]  Herbert Jaeger,et al.  The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[22]  D. Debanne,et al.  Long-term plasticity of intrinsic excitability: learning rules and mechanisms. , 2003, Learning & memory.

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

[24]  Sander M. Bohte,et al.  Reducing the Variability of Neural Responses: A Computational Theory of Spike-Timing-Dependent Plasticity , 2007, Neural Computation.

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

[26]  Jochen J. Steil,et al.  Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning , 2007, Neural Networks.

[27]  Thomas Nowotny,et al.  Enhancement of Synchronization in a Hybrid Neural Circuit by Spike-Timing Dependent Plasticity , 2003, The Journal of Neuroscience.

[28]  Dan Ventura,et al.  Preparing More Effective Liquid State Machines Using Hebbian Learning , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

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

[30]  Jochen J. Steil,et al.  Intrinsic plasticity for reservoir learning algorithms , 2007, ESANN.

[31]  Hermann Ney,et al.  Combination of Tangent Vectors and Local Representations for Handwritten Digit Recognition , 2002, SSPR/SPR.

[32]  Prof. Dr. Valentino Braitenberg,et al.  Anatomy of the Cortex , 1991, Studies of Brain Function.

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

[34]  Herbert Jaeger,et al.  Adaptive Nonlinear System Identification with Echo State Networks , 2002, NIPS.

[35]  L. Abbott,et al.  Synaptic plasticity: taming the beast , 2000, Nature Neuroscience.

[36]  Gal Chechik,et al.  Spike-Timing-Dependent Plasticity and Relevant Mutual Information Maximization , 2003, Neural Computation.

[37]  Jochen Triesch,et al.  Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm , 2022 .

[38]  M. Aminoff.  Principles of Neural Science. 4th edition , 2001 .

[39]  Wolfgang Maass,et al.  On the relevance of time in neural computation and learning , 2001, Theor. Comput. Sci..

[40]  Eugene M. Izhikevich,et al.  Polychronization: Computation with Spikes , 2006, Neural Computation.

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

[42]  Jochen Triesch,et al.  A Gradient Rule for the Plasticity of a Neuron's Intrinsic Excitability , 2005, ICANN.

[43]  Samy Bengio,et al.  A supervised learning approach based on STDP and polychronization in spiking neuron networks , 2007, ESANN.

[44]  T. M. Mayhew,et al.  Anatomy of the Cortex: Statistics and Geometry. , 1991 .

[45]  Benjamin Schrauwen,et al.  An experimental unification of reservoir computing methods , 2007, Neural Networks.

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

[47]  Ad Aertsen,et al.  Stable propagation of synchronous spiking in cortical neural networks , 1999, Nature.

[48]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[49]  Daniel D. Lee,et al.  Equilibrium properties of temporally asymmetric Hebbian plasticity. , 2000, Physical review letters.

[50]  H. Swadlow.  Physiological properties of individual cerebral axons studied in vivo for as long as one year. , 1985, Journal of neurophysiology.

[51]  R. Kempter,et al.  Hebbian learning and spiking neurons , 1999 .

[52]  Wolf Singer,et al.  Neuronal Synchrony: A Versatile Code for the Definition of Relations? , 1999, Neuron.

[53]  Alan F. Murray,et al.  Synaptic Rewiring for Topographic Map Formation , 2008, ICANN.

[54]  H. Swadlow.  Monitoring the excitability of neocortical efferent neurons to direct activation by extracellular current pulses. , 1992, Journal of neurophysiology.

[55]  Michael Schmitt,et al.  On computing Boolean functions by a spiking neuron , 1998, Annals of Mathematics and Artificial Intelligence.

[56]  J.J. Steil,et al.  Backpropagation-decorrelation: online recurrent learning with O(N) complexity , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[57]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .