A Supervised Learning Algorithm for Spiking Neurons Using Spike Train Kernel Based on a Unit of Pair-Spike

In recent years, neuroscientists have discovered that the neural information is encoded by spike trains with precise times. Supervised learning algorithm based on the precise times for spiking neurons becomes an important research field. Although many existing algorithms have the excellent learning ability, most of their mechanisms still have some complex computations and certain limitations. Moreover, the discontinuity of spiking process also makes it very difficult to build an efficient algorithm. This paper proposes a supervised learning algorithm for spiking neurons using the kernel function of spike trains based on a unit of pair-spike. Firstly, we comprehensively divide the intervals of spike trains. Then, we construct an optimal selection and computation method of spikes based on the unit of pair-spike. This method avoids some wrong computations and reduces the computational cost by using each effective input spike only once in every epoch. Finally, we use the kernel function defined by an inner product operator to solve the computing problem of discontinue spike process and multiple output spikes. The proposed algorithm is successfully applied to many learning tasks of spike trains, where the effect of our optimal selection and computation method is verified and the influence of learning factors such as learning kernel, learning rate, and learning epoch is analyzed. Moreover, compared with other algorithms, all experimental results show that our proposed algorithm has the higher learning accuracy and good learning efficiency.

[1]  Wulfram Gerstner,et al.  Spike-response model , 2008, Scholarpedia.

[2]  Tiejun Huang,et al.  Spike Coding for Dynamic Vision Sensor in Intelligent Driving , 2019, IEEE Internet of Things Journal.

[3]  Chris Christodoulou,et al.  Multiagent Reinforcement Learning: Spiking and Nonspiking Agents in the Iterated Prisoner's Dilemma , 2011, IEEE Transactions on Neural Networks.

[4]  Yuan Xie,et al.  Rethinking the performance comparison between SNNS and ANNS , 2020, Neural Networks.

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

[6]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[7]  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.

[8]  Justin K. Romberg,et al.  Convergence and Rate Analysis of Neural Networks for Sparse Approximation , 2011, IEEE Transactions on Neural Networks and Learning Systems.

[9]  Gunnar Rätsch,et al.  An introduction to kernel-based learning algorithms , 2001, IEEE Trans. Neural Networks.

[10]  Nicu Sebe,et al.  Temporal Spiking Recurrent Neural Network for Action Recognition , 2019, IEEE Access.

[11]  Witold Pedrycz,et al.  Logic-oriented neural networks for fuzzy neurocomputing , 2009, Neurocomputing.

[12]  Timothée Masquelier,et al.  Deep Learning in Spiking Neural Networks , 2018, Neural Networks.

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

[14]  Thomas Kreuz,et al.  Which spike train distance is most suitable for distinguishing rate and temporal coding? , 2017, Journal of Neuroscience Methods.

[15]  L. Abbott,et al.  Competitive Hebbian learning through spike-timing-dependent synaptic plasticity , 2000, Nature Neuroscience.

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

[17]  Lin Xiang-hon,et al.  Supervised Learning Algorithms for Spiking Neural Networks: A Review , 2015 .

[18]  Sander M. Bohte,et al.  The evidence for neural information processing with precise spike-times: A survey , 2004, Natural Computing.

[19]  Zhang Yi,et al.  A Highly Effective and Robust Membrane Potential-Driven Supervised Learning Method for Spiking Neurons , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[20]  Maryam Gholami Doborjeh,et al.  Mapping, Learning, Visualization, Classification, and Understanding of fMRI Data in the NeuCube Evolving Spatiotemporal Data Machine of Spiking Neural Networks , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[21]  Huifang Ma,et al.  An Improved Supervised Learning Algorithm Using Triplet-Based Spike-Timing-Dependent Plasticity , 2016, ICIC.

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

[23]  I. Fried,et al.  Rapid Encoding of New Memories by Individual Neurons in the Human Brain , 2015, Neuron.

[24]  José Carlos Príncipe,et al.  Kernel Methods on Spike Train Space for Neuroscience: A Tutorial , 2013, IEEE Signal Processing Magazine.

[25]  Sebastian Risi,et al.  Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks , 2017, Neural Networks.

[26]  Paul W. Munro,et al.  The Effect of Spike Redistribution in a Reciprocally Connected Pair of Neurons with Spike Timing-Dependent Plasticity , 2002, Neurocomputing.

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

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

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

[30]  Liam McDaid,et al.  SWAT: A Spiking Neural Network Training Algorithm for Classification Problems , 2010, IEEE Transactions on Neural Networks.

[31]  Nikola Kasabov,et al.  New Algorithms for Encoding, Learning and Classification of fMRI Data in a Spiking Neural Network Architecture: A Case on Modeling and Understanding of Dynamic Cognitive Processes , 2017, IEEE Transactions on Cognitive and Developmental Systems.

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

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

[34]  Alexander Cerquera,et al.  How spurious correlations affect a correlation-based measure of spike timing reliability , 2012, Neurocomputing.

[35]  Ammar Belatreche,et al.  A review of learning in biologically plausible spiking neural networks , 2019, Neural Networks.

[36]  Taro Tezuka,et al.  Multineuron spike train analysis with R-convolution linear combination kernel , 2018, Neural Networks.

[37]  Wulfram Gerstner,et al.  Reducing Spike Train Variability: A Computational Theory Of Spike-Timing Dependent Plasticity , 2004, BNAIC.

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

[39]  André Grüning,et al.  Learning Temporally Precise Spiking Patterns through Reward Modulated Spike-Timing-Dependent Plasticity , 2013, ICANN.

[40]  Blaine Rister,et al.  Piecewise convexity of artificial neural networks , 2016, Neural Networks.

[41]  Daniel M. Wolpert,et al.  Forward Models for Physiological Motor Control , 1996, Neural Networks.

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

[43]  Xiaochao Dang,et al.  A Delay Learning Algorithm Based on Spike Train Kernels for Spiking Neurons , 2019, Front. Neurosci..

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

[45]  André Grüning,et al.  Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding , 2016, PloS one.

[46]  V. Canals,et al.  A Stochastic Spiking Neural Network for Virtual Screening , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[47]  N. Lemon,et al.  Conditional spike backpropagation generates burst discharge in a sensory neuron. , 2000, Journal of neurophysiology.

[48]  Albert Bifet,et al.  Spiking Neural Networks and Online Learning: An Overview and Perspectives , 2019, Neural Networks.

[49]  J. Knott.  The organization of behavior: A neuropsychological theory , 1951 .

[50]  M. Farries,et al.  Reinforcement learning with modulated spike timing dependent synaptic plasticity. , 2007, Journal of neurophysiology.

[51]  Tm McGinnity,et al.  Optimization of Output Spike Train Encoding for a Spiking Neuron Based on its Spatio–Temporal Input Pattern , 2020, IEEE Transactions on Cognitive and Developmental Systems.

[52]  Xianghong Lin,et al.  Supervised learning in multilayer spiking neural networks with inner products of spike trains , 2017, Neurocomputing.