脉冲神经元脉冲序列学习方法综述

doi:10.11772/j.issn.1001-9081.2017112768

计算机应用 ›› 2018, Vol. 38 ›› Issue (6): 1527-1534.DOI: 10.11772/j.issn.1001-9081.2017112768

• 人工智能 • 下一篇

脉冲神经元脉冲序列学习方法综述

徐彦¹, 熊迎军¹, 杨静²

1. 南京农业大学信息科技学院, 南京 210095;
2. 北京师范大学珠海分校管理学院, 广东珠海 519087

收稿日期:2017-11-27 修回日期:2017-12-25 出版日期:2018-06-10 发布日期:2018-06-13
通讯作者: 徐彦
作者简介:徐彦(1979-),男,江苏扬州人,讲师,博士,CCF会员,主要研究方向:人工神经网络、模式识别;熊迎军(1984-),男,陕西咸阳人,讲师,博士,主要研究方向:检测技术、自动化装置;杨静(1980-),女,江西南昌人,讲师,博士,主要研究方向:人工神经网络、模式识别。
基金资助:
国家自然科学基金资助项目（61403205，61503031）；中央高校基本科研业务费专项资金项目（KYZ201754）。

Review of spike sequence learning methods for spiking neurons

XU Yan¹, XIONG Yingjun¹, YANG Jing²

1. College of Information Science and Technology, Nanjing Agricultural University, Nanjing Jiangsu 210095, China;
2. School of Management, Zhuhai Campus, Beijing Normal University, Zhuhai Guangdong 519087, China

Received:2017-11-27 Revised:2017-12-25 Online:2018-06-10 Published:2018-06-13
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61403205, 61503031), the Fundamental Research Funds for the Central Universities (KYZ201754).

摘要/Abstract

摘要： 脉冲神经元是一种新颖的人工神经元模型，其有监督学习的目的是通过学习使得神经元激发出一串通过精确时间编码来表达特定信息的脉冲序列，故称为脉冲序列学习。针对单神经元的脉冲序列学习应用价值显著、理论基础多样、影响因素众多的特点，对已有脉冲序列学习方法进行了综述对比。首先介绍了脉冲神经元模型与脉冲序列学习的基本概念；然后详细介绍了典型的脉冲序列学习方法，指出了每种方法的理论基础和突触权值调整方式；最后通过实验比较了这些学习方法的性能，系统总结了每种方法的特点，并且讨论了脉冲序列学习的研究现状和进一步的发展方向。该研究结果有助于脉冲序列学习方法的综合应用。

关键词: 脉冲神经元, 脉冲神经网络, 脉冲序列, 脉冲序列学习, 突触调整

Abstract: Spiking neuron is a novel artificial neuron model. The purpose of its supervised learning is to stimulate the neuron by learning to generate a series of spike sequences for expressing specific information through precise time coding, so it is called spike sequence learning. Because the spike sequence learning for single neuron has the characteristics of significant application value, various theoretical foundations and many influential factors, the existing spike sequence learning methods were reviewed and contrasted. Firstly, the basic concepts of spiking neuron models and spike sequence learning were introduced. Then, the typical learning methods of spike sequence learning were introduced in detail, the theoretical basis and synaptic weight adjustment way of each method were pointed out. Finally, the performance of these learning methods was compared through experiments, the characteristics of each method was systematically summarized, the current research situation of spike sequence learning was discussed, and the future direction of development was pointed out. The research results are helpful for the comprehensive application of spike sequence learning methods.

Key words: spiking neuron, spiking neural network, spike sequence, spike sequence learning, synaptic adjustment

中图分类号:

TP183

徐彦, 熊迎军, 杨静. 脉冲神经元脉冲序列学习方法综述[J]. 计算机应用, 2018, 38(6): 1527-1534.

XU Yan, XIONG Yingjun, YANG Jing. Review of spike sequence learning methods for spiking neurons[J]. Journal of Computer Applications, 2018, 38(6): 1527-1534.

参考文献

[1] MAASS W. Networks of spiking neurons:the third generation of neural network models[J]. Neural Networks, 1997, 10(9):1659-1671.
[2] MAASS W. Noisy spiking neurons with temporal coding have more computational power than sigmoidal neurons[EB/OL].[2017-10-16]. http://papers.nips.cc/paper/1307-noisy-spiking-neurons-with-temporal-coding-have-more-computational-power-than-sigmoidal-neurons.pdf.
[3] VANRULLEN R, GUYONNEAU R, THORPE S J. Spike times make sense[J]. Trends in Neurosciences, 2005, 28(1):1-4.
[4] GUTIG R, SOMPOLINSKY H. The tempotron:a neuron that learns spike timing-based decisions[J]. Nature Neuroscience, 2006, 9(3):420-428.
[5] SPOREA I, GRUNING A. Supervised learning in multilayer spiking neural networks[J]. Neural Computation, 2013, 25(2):473-509.
[6] PFISTER J P, TOYOIZUMI T, BARBER D, et al. Optimal spike-timing-dependent plasticity for precise action potential firing in supervised learning[J]. Neural Computation, 2006, 18(6):1318-1348.
[7] FLORIAN R V. Reinforcement learning through modulation of spike-timing-dependent synaptic plasticity[J]. Neural Computaion 2007, 19(6):1468-1502.
[8] CARNELL A, RICHARDSON D. Linear algebra for time series of spikes[EB/OL].[2017-10-16]. http://pdfs.semanticscholar.org/64a8/16098fb842313813aac6c9b92514ed34ba04.pdf.
[9] 蔺想红,王向文,张宁,等.脉冲神经网络的监督学习算法研究综述[J].电子学报,2015,43(3):577-586.(LIN X H, WANG X W, ZHANG N, et al. Supervised learning algorithms for spiking neural networks:a review[J]. Acta Electronica Sinica, 2015, 43(3):577-586.)
[10] GUTIG R. To spike, or when to spike?[J]. Current Opinion in Neurobiology, 2014, 25:134-139.
[11] FENG J F, BROWN D. Integrate-and-fire models with nonlinear leakage[J]. Bulletin of Mathematical Biology, 2000, 62(3):467-481.
[12] GERSTNER W, KISTLER M. Spiking neuron models. Single neurons, populations, plasticity[M]. Cambridge:Cambridge University Press, 2002:110-133.
[13] BOHTE S M, KOK J N, LA POUTRÉ H A. Error-backpropagation in temporally encoded networks of spiking neurons[J]. Neurocomputing, 2002, 48(1/2/3/4):17-37.
[14] MCKENNOCH S, LIU D D, BUSHNELL L H A. Fast modifications of the SpikeProp algorithm[C]//IJCNN 2006:Proceedings of the IEEE International Joint Conference on Neural Networks. Piscataway, NJ:IEEE, 2006:3970-3977.
[15] SILVA S M, RUANO A E. Application of Levenberg-Marquardt method to the training of spiking neural networks[C]//Proceedings of the 2006 International Joint Conference on Neural Networks. Piscataway, NJ:IEEE, 2006:3978-3982.
[16] SCHRAUWEN B, van CAMPENHOUT J. Extending SpikeProp[C]//Proceedings of the 2004 IEEE International Joint Conference on Neural Networks. Piscataway, NJ:IEEE, 2004:471-475.
[17] BOOIJ O, NGUYEN H T. A gradient descent rule for spiking neurons emitting multiple spikes[J]. Information Processing Letters, 2005, 95(6):552-558.
[18] GHOSH-DASTIDAR S, ADELI H. A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection[J]. Neural Networks, 2009, 22(10):1419-1431.
[19] XU Y, ZENG X Q, HAN L X, et al. A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks[J]. Neural Networks, 2013, 43(4):99-113.
[20] 徐彦.基于梯度下降的脉冲神经元在线学习方法[J].计算机工程,2015,41(12):150-155,166.(XU Y. Spiking neuron online learning method based on gradient descent[J]. Computer Engineering, 2015, 41(12):150-155, 166.)
[21] XU Y, YANG J, ZHONG S M. An online supervised learning method based on gradient descent for spiking neurons[J]. Neural Networks, 2017, 93:7-20.
[22] MARKRAM H, TSODYKS M. Redistribution of synaptic efficacy between neocortical pyramidal neurons[J]. Nature, 1996, 382(6594):807-810.
[23] PONULAK F, KASINSKI A. Supervised learning in spiking neural networks with ReSuMe:sequence learning, classification and spike shifting[J]. Neural Computation, 2010, 22(2):467-510.
[24] TAHERKHANI A, BELATRECHE A, LI Y H, et al. DL-ReSuMe:a delay learning-based remote supervised method for spiking neurons[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(12):3137-3149.
[25] MOHEMMED A, SCHLIEBS S, MATSUDA S, et al. Span:spike pattern association neuron for learning spatio-temoral spike patterns[J]. International Journal of Neural Systems, 2012, 22(4):1659-1685.
[26] MOHEMMED A, SCHLIEBS S, MATSUDA S, et al. Training spiking neural networks to associate spatio-temporal input-output spike patterns[J]. Neurocomputing, 2013, 107(4):3-10.
[27] YU Q, TANG H J, TAN K C, et al. Precise-spike-driven synaptic plasticity:learning hetero-association of spatiotemporal spike patterns[J]. PLoS One, 2013, 8(11):e78318.
[28] MEMMESHEIMER R M, RUBIN R, OLVECZKY B P, et al. Learning precisely timed spiks[J]. Neuron, 2014, 82(4):925-938.
[29] LIN X H, ZHANG N, WANG X W. An online supervised learning algorithm based on nonlinear spike train kernels[C]//ICIC 2015:Proceedings of the 2015 International Conference on Intelligent Computing, LNCS 9225. Cham:Springer, 2015:106-115.
[30] FLORIAN R V. The chronotron:a neuron that learns to fire temporally precise spike patterns[J]. PLoS One, 2012, 7(8), e40233.
[31] VICTOR J D, PURPURA K P. Nature and precision of temporal coding in visual cortex:a metric-space analysis[J]. Journal of Neurophysiology, 1996, 76(2):1310-1326.
[32] GARDNER B, GRUNING A. Supervised learning in spiking neural networks for precise temporal encoding[J]. PLoS One, 2016, 11(8):e0161335.
[33] XU Y, ZENG X Q, ZHONG S M. A new supervised learning algorithm for spiking neurons[J]. Neural Computation, 2013, 25(6):1472-1511.
[34] XIE X R, QU H, LIU G S. Efficient training of supervised spiking neural networks via the normalized perceptron based learning rule [J]. Neurocomputing, 2017, 241: 152-163.
[35] QU H, XIE X R, LIU Y S, et al. Improved perception-based spiking neuron learning rule for real-time user authentication [J]. Neurocomputing, 2015, 151: 310-318.
[36] 徐彦,杨静.脉冲神经元序列学习方法的影响因素研究[J].计算机工程,2015,41(11):194-201.(XU Y, YANG J. Research on affect factors of spiking neuron sequence learning method [J]. Computer Engineering, 2015, 41(11): 194-201.)
[37] ZHANG M L, QU H, XIE X R, et al. Supervised learning in spiking neural networks with noise-threshold [J]. Neurocomputing, 2017, 219: 333-349.
[38] SCHERIBER S, FELLOUS J M, WHITMER D, et al. A new correlation-based measure of spike timing reliability [J]. Neurocomputing, 2003, 52/53/54: 925-931.
[39] YU Q, TANG H J, TAN K C, et al. A brain-inspired spiking neural network model with temporal encoding and learning [J]. Neurocomputing, 2014, 138: 3-13.
[40] ZHANG M L, QU H, BELATRECHE A, et al. EMPD: an efficient membrane potential driven supervised learning algorithm for spiking neurons [J]. IEEE Transactions on Cognitive and Developmental Systems, 2017, PP(99):1-1.
[41] DORA S, SURESH S, SUNDARARAJAN N. A sequential learning algorithm for a spiking neural classifier [J]. Applied Soft Computing, 2015, 36: 255-268.
[42] IAKYMCHUK T, ROSADO-MUNOZ A, GUERRERO-MARTINEZ J F, et al. Simplified spiking neural network architecture and STDP learning algorithm applied to image classification [J]. EURASIP Journal on Image and Video Processing, 2015, 2015: 4.

脉冲神经元脉冲序列学习方法综述

Review of spike sequence learning methods for spiking neurons

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics