Supervised Learning Algorithm for Spiking Neurons Based on Nonlinear Inner Products of Spike Trains

详细信息    查看全文

• 关键词：Spiking neural networks ; Supervised learning ; Nonlinear inner products of spike trains ; Widrow ; Hoff rule
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9772
• 期：1
• 页码：95-104
• 全文大小：392 KB
• 参考文献：1.Quiroga, R.Q., Panzeri, S.: Principles of Neural Coding. CRC Press, Boca Raton (2013)CrossRef
  2.Ghosh-Dastidar, S., Adeli, H.: Spiking neural networks. Int. J. Neural Syst. 19(4), 295–308 (2009)CrossRef
  3.Kasiński, A., Ponulak, F.: Comparison of supervised learning methods for spike time coding in spiking neural networks. Int. J. Appl. Math. Comput. Sci. 16(1), 101–113 (2006)MathSciNet MATH
  4.Lin, X., Wang, X., Zhang, N., et al.: Supervised learning algorithms for spiking neural networks: a review. Acta Electronica Sinica 43(3), 577–586 (2015)
  5.Bohte, S.M., Kok, J.N., La Poutré, J.A.: Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48(1), 17–37 (2002)CrossRef MATH
  6.Gerstner, W., Kistler, W.M.: Spiking Neuron Models: Single Neurons, Populations, Plasticity. Cambridge University Press, Cambridge (2002)CrossRef MATH
  7.Shrestha, S.B., Song, Q.: Adaptive learning rate of SpikeProp based on weight convergence analysis. Neural Networks 63, 185–198 (2015)CrossRef MATH
  8.Ghosh-Dastidar, S., Adeli, H.: A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection. Neural Networks 22(10), 1419–1431 (2009)CrossRef
  9.Xu, Y., Zeng, X., Han, L., et al.: A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks. Neural Networks 43, 99–113 (2013)CrossRef MATH
  10.Ponulak, F., Kasinski, A.: Supervised learning in spiking neural networks with ReSuMe: sequence learning, classification, and spike shifting. Neural Comput. 22(2), 467–510 (2010)MathSciNet CrossRef MATH
  11.Ponulak, F.: Analysis of the ReSuMe learning process for spiking neural networks. Int. J. Appl. Math. Comput. Sci. 18(2), 117–127 (2008)MathSciNet CrossRef
  12.Sporea, I., Grüning, A.: Supervised learning in multilayer spiking neural networks. Neural Comput. 25(2), 473–509 (2013)MathSciNet CrossRef MATH
  13.Taherkhani, A., Belatreche, A., Li, Y., et al.: DL-ReSuMe: a delay learning-based remote supervised method for spiking neurons. IEEE Trans. Neural Netw. Learn. Syst. 26(12), 3137–3149 (2015)MathSciNet CrossRef
  14.Taherkhani, A., Belatreche, A., Li, Y., et al.: Multi-DL-ReSuMe: multiple neurons delay learning remote supervised method. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1–7. IEEE (2015)
  15.Mohemmed, A., Schliebs, S., Matsuda, S., et al.: SPAN: spike pattern association neuron for learning spatio-temporal spike patterns. Int. J. Neural Syst. 22(4), 786–803 (2012)CrossRef
  16.Mohemmed, A., Schliebs, S., Matsuda, S., et al.: Training spiking neural networks to associate spatio-temporal input–output spike patterns. Neurocomputing 107, 3–10 (2013)CrossRef
  17.Yu, Q., Tang, H., Tan, K.C., et al.: Precise-spike-driven synaptic plasticity: learning hetero-association of spatiotemporal spike patterns. PLoS One 8(11), e78318 (2013)CrossRef
  18.Yu, Q., Tang, H., Tan, K.C., et al.: A brain-inspired spiking neural network model with temporal encoding and learning. Neurocomputing 138, 3–13 (2014)CrossRef
  19.Park, I.M., Seth, S., Rao, M., et al.: Strictly positive-definite spike train kernels for point-process divergences. Neural Comput. 24(8), 2223–2250 (2012)MathSciNet CrossRef MATH
  20.Paiva, A.R.C., Park, I., Principe, J.C.: Inner products for representation and learning in the spike train domain. In: Statistical Signal Processing for Neuroscience and Neurotechnology, vol. 8 (2010)
  21.Gütig, R., Aharonov, R., Rotter, S., et al.: Learning input correlations through nonlinear temporally asymmetric Hebbian plasticity. J. Neurosci. 23(9), 3697–3714 (2003)
  22.Schreiber, S., Fellous, J.M., Whitmer, D., et al.: A new correlation-based measure of spike timing reliability. Neurocomputing 52, 925–931 (2003)CrossRef
  
• 作者单位：Xiangwen Wang (15)
  Xianghong Lin (15)
  Jichang Zhao (15)
  Huifang Ma (15)
  
  15. School of Computer Science and Engineering, Northwest Normal University, Lanzhou, 730070, China
  
• 丛书名：Intelligent Computing Theories and Application
• ISBN：978-3-319-42294-7
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9772

文摘

Spiking neural networks are shown to be suitable tools for the processing of spatio-temporal information. However, due to their intricately discontinuous and implicit nonlinear mechanisms, the formulation of efficient supervised learning algorithms for spiking neural networks is difficult, which has become an important problem in the research area. This paper presents a new supervised, multi-spike learning algorithm for spiking neurons, which can implement the complex spatio-temporal pattern learning of spike trains. The proposed algorithm firstly defines nonlinear inner products operators to mathematically describe and manipulate spike trains, and then derive the learning rule from the common Widrow-Hoff rule with the nonlinear inner products of spike trains. The algorithm is successfully applied to learn sequences of spikes. The experimental results show that the proposed algorithm is effective for solving complex spatio-temporal pattern learning problems.