Pattern Classification by Spiking Neural Networks Combining Self-Organized and Reward-Related Spike-Timing-Dependent Plasticity

Open access

Abstract

Many recent studies have applied to spike neural networks with spike-timing-dependent plasticity (STDP) to machine learning problems. The learning abilities of dopamine-modulated STDP (DA-STDP) for reward-related synaptic plasticity have also been gathering attention. Following these studies, we hypothesize that a network structure combining self-organized STDP and reward-related DA-STDP can solve the machine learning problem of pattern classification. Therefore, we studied the ability of a network in which recurrent spiking neural networks are combined with STDP for non-supervised learning, with an output layer joined by DA-STDP for supervised learning, to perform pattern classification. We confirmed that this network could perform pattern classification using the STDP effect for emphasizing features of the input spike pattern and DA-STDP supervised learning. Therefore, our proposed spiking neural network may prove to be a useful approach for machine learning problems.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • [1] M. I. Rabinovich P. Varona A. I. Selverston and H. D. Abarbanel Dynamical principles in neuro-science Reviews of modern physics vol. 78 no. 4 pp. 1213–1265 2006.

  • [2] R. Q. Quiroga and S. Panzeri Principles of neural coding. CRC Press 2013.

  • [3] S. Panzeri J. H. Macke J. Gross and C. Kayser Neural population coding: combining insights from microscopic and mass signals Trends in cognitive sciences vol. 19 no. 3 pp. 162–172 2015.

  • [4] N. Schweighofer K. Doya H. Fukai J. V. Chiron T. Furukawa and M. Kawato Chaos may enhance information transmission in the inferior olive Proceedings of the National Academy of Sciences vol. 101 no. 13 pp. 4655–4660 2004.

  • [5] J. Mejias and A. Longtin Optimal heterogeneity for coding in spiking neural networks Physical Review Letters vol. 108 no. 22 228102 2012.

  • [6] N. Hiratani J.-N. Teramae and T. Fukai Associative memory model with long-tail-distributed hebbian synaptic connections Frontiers in computational neuroscience vol. 6 102 2013.

  • [7] S. Nobukawa and H. Nishimura Chaotic resonance in coupled inferior olive neurons with the llinás approach neuron model Neural computation vol. 28 no. 11 pp. 2505–2532 2016.

  • [8] S. Nobukawa H. Nishimura and T. Yamanishi Chaotic resonance in typical routes to chaos in the Izhikevich neuron model Scientific reports vol. 7 no. 1 1331 2017.

  • [9] N. K. Kasabov Neucube: A spiking neural network architecture for mapping learning and understanding of spatio-temporal brain data Neural Networks vol. 52 pp. 62–76 2014.

  • [10] J. H. Lee T. Delbruck and M. Pfeiffer Training deep spiking neural networks using backpropagation Frontiers in neuroscience vol. 10 508 2016.

  • [11] X. Lin X. Wang and Z. Hao Supervised learning in multilayer spiking neural networks with inner products of spike trains Neurocomputing vol. 237 pp. 59–70 2017.

  • [12] S. R. Kulkarni and B. Rajendran Spiking neural networks for handwritten digit recognition–supervised learning and network optimization Neural Networks vol. 103 pp. 118–127 2018.

  • [13] S. R. Kheradpisheh M. Ganjtabesh S. J. Thorpe and T. Masquelier STDP-based spiking deep convolutional neural networks for object recognition Neural Networks vol. 99 pp. 56–67 2018.

  • [14] Z. Lin D. Ma J. Meng and L. Chen Relative ordering learning in spiking neural network for pattern recognition Neurocomputing vol. 275 pp. 94–106 2018.

  • [15] A. Tavanaei T. Masquelier and A. Maida Representation learning using event-based STDP Neural Networks vol. 105 pp. 294–303 2018.

  • [16] M. Mozafari S. R. Kheradpisheh T. Masquelier A. Nowzari-Dalini and M. Ganjtabesh First-spike-based visual categorization using reward-modulated STDP IEEE Transactions on Neural Networks and Learning Systems vol. 99 pp. 1–13 2018.

  • [17] A. Tavanaei Z. Kirby and A. S. Maida Training spiking convnets by STDP and gradient descent in Proceedings of 2018 International Joint Conference on Neural Networks (IJCNN). IEEE 2018 pp. 1–8.

  • [18] Y. Wu L. Deng G. Li J. Zhu and L. Shi Spatio-temporal backpropagation for training high-performance spiking neural networks Frontiers in neuroscience vol. 12 331 2018.

  • [19] M. Bernardo C. Budd A. R. Champneys and P. Kowalczyk Piecewise-smooth dynamical systems: theory and applications. Springer Science & Business Media 2008 vol. 163.

  • [20] N. Kasabov Neucube evospike architecture for spatio-temporal modelling and pattern recognition of brain signals in Proceedings of IAPR Workshop on Artificial Neural Networks in Pattern Recognition. Springer 2012 pp. 225–243.

  • [21] N. Kasabov and E. Capecci Spiking neural network methodology for modelling classification and understanding of EEG spatio-temporal data measuring cognitive processes Information Sciences vol. 294 pp. 565–575 2015.

  • [22] C. Ge N. Kasabov Z. Liu and J. Yang A spiking neural network model for obstacle avoidance in simulated prosthetic vision Information Sciences vol. 399 pp. 30–42 2017.

  • [23] D. Verstraeten B. Schrauwen D. Stroobandt and J. Van Campenhout Isolated word recognition with the liquid state machine: a case study Information Processing Letters vol. 95 no. 6 pp. 521–528 2005.

  • [24] A. Ghani T. M. McGinnity L. P. Maguire and J. Harkin Neuro-inspired speech recognition with recurrent spiking neurons in Proceedings of International Conference on Artificial Neural Networks. Springer 2008 pp. 513–522.

  • [25] Z. Yanduo and W. Kun The application of liquid state machines in robot path planning Journal of Computers vol. 4 no. 11 pp. 1183–1186 2009.

  • [26] Y. Zhang P. Li Y. Jin and Y. Choe A digital liquid state machine with biologically inspired learning and its application to speech recognition IEEE transactions on neural networks and learning systems vol. 26 no. 11 pp. 2635–2649 2015.

  • [27] Y. Jin and P. Li Calcium-modulated supervised spike-timing-dependent plasticity for readout training and sparsification of the liquid state machine in Proceedings of 2017 International Joint Conference on Neural Networks (IJCNN). IEEE 2017 pp. 2007–2014.

  • [28] R. V. Florian Reinforcement learning through modulation of spike-timing-dependent synaptic plasticity Neural Computation vol. 19 no. 6 pp. 1468–1502 2007.

  • [29] N. Frémaux H. Sprekeler and W. Gerstner Functional requirements for reward-modulated spike-timing-dependent plasticity Journal of Neuro-science vol. 30 no. 40 pp. 13 326–13 337 2010.

  • [30] T.-S. Chou L. D. Bucci and J. L. Krichmar Learning touch preferences with a tactile robot using dopamine modulated STDP in a model of insular cortex Frontiers in neurorobotics vol. 9 p. 6 2015.

  • [31] A. H. Marblestone G. Wayne and K. P. Kording Toward an integration of deep learning and neuroscience Frontiers in computational neuroscience vol. 10 94 2016.

  • [32] A. S. Warlaumont and M. K. Finnegan Learning to produce syllabic speech sounds via reward-modulated neural plasticity PloS one vol. 11 no. 1 e0145096 2016.

  • [33] Y. Kawai T. Takimoto J. Park and M. Asada Efficient reward-based learning through body representation in a spiking neural network in Proceedings of the 8th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. IEEE 2018 pp. 198–203.

  • [34] E. M. Izhikevich Polychronization: computation with spikes Neural computation vol. 18 no. 2 pp. 245–282 2006.

  • [35] E. M. Izhikevich Solving the distal reward problem through linkage of STDP and dopamine signaling Cerebral cortex vol. 17 no. 10 pp. 2443–2452 2007.

Search
Journal information
Impact Factor


CiteScore 2018: 4.70

SCImago Journal Rank (SJR) 2018: 0.351
Source Normalized Impact per Paper (SNIP) 2018: 4.066

Metrics
All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 437 437 87
PDF Downloads 185 185 85