A Highly Effective and Robust Membrane Potential-Driven Supervised Learning Method for Spiking Neurons

Spiking neurons are becoming increasingly popular owing to their biological plausibility and promising computational properties. Unlike traditional rate-based neural models, spiking neurons encode information in the temporal patterns of the transmitted spike trains, which makes them more suitable for processing spatiotemporal information. One of the fundamental computations of spiking neurons is to transform streams of input spike trains into precisely timed firing activity. However, the existing learning methods, used to realize such computation, often result in relatively low accuracy performance and poor robustness to noise. In order to address these limitations, we propose a novel highly effective and robust membrane potential-driven supervised learning (MemPo-Learn) method, which enables the trained neurons to generate desired spike trains with higher precision, higher efficiency, and better noise robustness than the current state-of-the-art spiking neuron learning methods. While the traditional spike-driven learning methods use an error function based on the difference between the actual and desired output spike trains, the proposed MemPo-Learn method employs an error function based on the difference between the output neuron membrane potential and its firing threshold. The efficiency of the proposed learning method is further improved through the introduction of an adaptive strategy, called skip scan training strategy, that selectively identifies the time steps when to apply weight adjustment. The proposed strategy enables the MemPo-Learn method to effectively and efficiently learn the desired output spike train even when much smaller time steps are used. In addition, the learning rule of MemPo-Learn is improved further to help mitigate the impact of the input noise on the timing accuracy and reliability of the neuron firing dynamics. The proposed learning method is thoroughly evaluated on synthetic data and is further demonstrated on real-world classification tasks. Experimental results show that the proposed method can achieve high learning accuracy with a significant improvement in learning time and better robustness to different types of noise.

[1]  Wenwen Wang,et al.  Neural Modeling of Episodic Memory: Encoding, Retrieval, and Forgetting , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Michael J. Berry,et al.  Refractoriness and Neural Precision , 1997, The Journal of Neuroscience.

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

[4]  J. J. Hopfield,et al.  Pattern recognition computation using action potential timing for stimulus representation , 1995, Nature.

[5]  Malu Zhang,et al.  Improved perception-based spiking neuron learning rule for real-time user authentication , 2015, Neurocomputing.

[6]  Alex M. Andrew,et al.  Spiking Neuron Models: Single Neurons, Populations, Plasticity , 2003 .

[7]  Jing Yang,et al.  A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks , 2013, Neural Networks.

[8]  Masao Ito.  Mechanisms of motor learning in the cerebellum 1 1 Published on the World Wide Web on 24 November 2000. , 2000, Brain Research.

[9]  Peter A. Cariani,et al.  Temporal codes and computations for sensory representation and scene analysis , 2004, IEEE Transactions on Neural Networks.

[10]  Alexander Borst,et al.  Information theory and neural coding , 1999, Nature Neuroscience.

[11]  Haizhou Li,et al.  How the Brain Formulates Memory: A Spatio-Temporal Model Research Frontier , 2016, IEEE Computational Intelligence Magazine.

[12]  W. T. Thach.  Motor Learning and Synaptic Plasticity in the Cerebellum: On the specific role of the cerebellum in motor learning and cognition: Clues from PET activation and lesion studies in man , 1997 .

[13]  Herman J. M. Steeneken,et al.  Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems , 1993, Speech Commun..

[14]  Tsuyoshi Murata,et al.  {m , 1934, ACML.

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

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

[17]  Jonathan D. Victor,et al.  Metric-space analysis of spike trains: theory, algorithms and application , 1998, q-bio/0309031.

[18]  Malu Zhang,et al.  Supervised learning in spiking neural networks with noise-threshold , 2017, Neurocomputing.

[19]  VargaAndrew,et al.  Assessment for automatic speech recognition II , 1993 .

[20]  Zhang Yi,et al.  Efficient Shortest-Path-Tree Computation in Network Routing Based on Pulse-Coupled Neural Networks , 2013, IEEE Transactions on Cybernetics.

[21]  Stefan Schliebs,et al.  Span: Spike Pattern Association Neuron for Learning Spatio-Temporal Spike Patterns , 2012, Int. J. Neural Syst..

[22]  Christof Koch,et al.  Temporal Precision of Spike Trains in Extrastriate Cortex of the Behaving Macaque Monkey , 1999, Neural Computation.

[23]  E. Chichilnisky,et al.  Precision of spike trains in primate retinal ganglion cells. , 2004, Journal of neurophysiology.

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

[25]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[26]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[27]  Zhang Yi,et al.  Real-Time Robot Path Planning Based on a Modified Pulse-Coupled Neural Network Model , 2009, IEEE Transactions on Neural Networks.

[28]  R. Reid,et al.  Temporal Coding of Visual Information in the Thalamus , 2000, The Journal of Neuroscience.

[29]  E. Knudsen.  Supervised learning in the brain , 1994, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[30]  Wulfram Gerstner,et al.  Spike-Based Compared to Rate-Based Hebbian Learning , 1998, NIPS.

[31]  Haizhou Li,et al.  Rapid Feedforward Computation by Temporal Encoding and Learning With Spiking Neurons , 2013, IEEE Transactions on Neural Networks and Learning Systems.

[32]  Robert Gütig,et al.  Spiking neurons can discover predictive features by aggregate-label learning , 2016, Science.

[33]  Haizhou Li,et al.  A Spiking Neural Network System for Robust Sequence Recognition , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[34]  Haim Sompolinsky,et al.  Learning Precisely Timed Spikes , 2014, Neuron.

[35]  Haizhou Li,et al.  A Spike-Timing-Based Integrated Model for Pattern Recognition , 2013, Neural Computation.

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

[37]  Mark C. W. van Rossum,et al.  A Novel Spike Distance , 2001, Neural Computation.

[38]  Stefan Schliebs,et al.  Training spiking neural networks to associate spatio-temporal input-output spike patterns , 2013, Neurocomputing.

[39]  A. Hodgkin,et al.  A quantitative description of membrane current and its application to conduction and excitation in nerve , 1990 .

[40]  Tim Gollisch,et al.  Rapid Neural Coding in the Retina with Relative Spike Latencies , 2008, Science.

[41]  Mark C. W. van Rossum,et al.  Effects of noise on the spike timing precision of retinal ganglion cells. , 2003, Journal of neurophysiology.

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

[43]  Huajin Tang,et al.  Precise-Spike-Driven Synaptic Plasticity: Learning Hetero-Association of Spatiotemporal Spike Patterns , 2013, PloS one.

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

[45]  Anthony M. Zador.  Spikes: Exploring the Neural Code , 1997 .

[46]  Razvan V. Florian,et al.  The Chronotron: A Neuron That Learns to Fire Temporally Precise Spike Patterns , 2010, PloS one.

[47]  Malu Zhang,et al.  EMPD: An Efficient Membrane Potential Driven Supervised Learning Algorithm for Spiking Neurons , 2018, IEEE Transactions on Cognitive and Developmental Systems.

[48]  Satoshi Nakamura,et al.  RWCP Sound Scene Database in Real Acoustic Environment , 2002 .

[49]  K. Pawelzik,et al.  Learning of Precise Spike Times with Homeostatic Membrane Potential Dependent Synaptic Plasticity , 2016, PloS one.

[50]  Hojjat Adeli,et al.  Spiking Neural Networks , 2009, Int. J. Neural Syst..

[51]  Ammar Belatreche,et al.  DL-ReSuMe: A Delay Learning-Based Remote Supervised Method for Spiking Neurons , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[52]  Daniel Jachyra,et al.  Neural Network Structure for Spatio-Temporal Long-Term Memory , 2012, IEEE Transactions on Neural Networks and Learning Systems.

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

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

[55]  Xiaoqin Zeng,et al.  A New Supervised Learning Algorithm for Spiking Neurons , 2013, Neural Computation.

[56]  J Gautrais,et al.  Rate coding versus temporal order coding: a theoretical approach. , 1998, Bio Systems.

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

[58]  Julie A. Wall,et al.  Spiking Neural Network Model of Sound Localization Using the Interaural Intensity Difference , 2012, IEEE Transactions on Neural Networks and Learning Systems.