脉冲神经网络的监督学习算法研究综述
Supervised Learning Algorithms for Spiking Neural Networks:A Review
查看参考文献60篇
|
文摘
|
脉冲神经网络是进行复杂时空信息处理的有效工具,但由于其内在的不连续和非线性机制,构建高效的脉冲神经网络监督学习算法非常困难,同时也是该研究领域的重要问题.本文介绍了脉冲神经网络监督学习算法的基本框架,以及性能评价原则,包括脉冲序列学习能力、离线与在线处理性能、学习规则的局部特性和对神经网络结构的适用性.此外,对脉冲神经网络监督学习算法的梯度下降学习规则、突触可塑性学习规则和脉冲序列卷积学习规则进行了详细的讨论,通过对比分析指出现有算法存在的优缺点,并展望了该领域未来的研究方向. |
|
其他语种文摘
|
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 is an important problem in the research area.In this paper,we introduce the general framework of supervised learning algorithms for spiking neural networks,and analyze their performance evaluations including spike trains learning ability,offline and online processing ability,the locality of learning mechanism and the applicability to network structure.Furthermore,we survey the advance of the research on supervised learning algorithms,which can be divided into three categories according to their differences:gradient descent rule,synaptic plasticity rule,and spike trains convolution rule.Finally,we discuss the advantages and disadvantages of these algorithms,and prospect the problems in current research and some future research directions in this area. |
|
来源
|
电子学报
,2015,43(3):577-586 【核心库】
|
|
DOI
|
10.3969/j.issn.0372-2112.2015.03.024
|
|
关键词
|
脉冲神经网络
;
监督学习
;
反向传播
;
突触可塑性
;
卷积
|
|
地址
|
西北师范大学计算机科学与工程学院, 甘肃, 兰州, 730070
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
0372-2112 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
国家自然科学基金
;
甘肃省自然科学基金
;
甘肃省青年科技基金
|
|
文献收藏号
|
CSCD:5442830
|
参考文献 共
60
共3页
|
|
1.
Haykin S S.
Neural Networks and Learning Machines,2009
|
CSCD被引
18
次
|
|
|
|
|
2.
Izhikevich E M. Which model to use for cortical spiking neurons?.
IEEE Transactions on Neural Networks,2004,15(5):1063-1070
|
CSCD被引
56
次
|
|
|
|
|
3.
Bohte S M. The evidence for neural information processing with precise spike-times:A survey.
Natural Computing,2004,3(2):195-206
|
CSCD被引
8
次
|
|
|
|
|
4.
Ghosh-Dastidar S. Spiking neural networks.
International Journal of Neural Systems,2009,19(4):295-308
|
CSCD被引
24
次
|
|
|
|
|
5.
Knudsen E I. Supervised learning in the brain.
Journal of Neuroscience,1994,14(7):3985-3997
|
CSCD被引
2
次
|
|
|
|
|
6.
Kasinski A. Comparison of supervised learning methods for spike time coding in spiking neural networks.
International Journal of Applied Mathematics and Computer Science,2006,16(1):101-113
|
CSCD被引
3
次
|
|
|
|
|
7.
Quiroga R Q.
Principles of Neural Coding,2013
|
CSCD被引
4
次
|
|
|
|
|
8.
蔺想红. 分段线性脉冲神经元模型的动力学特性分析.
电子学报,2009,37(6):1270-1276
|
CSCD被引
5
次
|
|
|
|
|
9.
Brette R. Simulation of networks of spiking neurons:A review of tools and strategies.
Journal of Computational Neuroscience,2007,23(3):349-398
|
CSCD被引
12
次
|
|
|
|
|
10.
Naud R. Improved similarity measures for small sets of spike trains.
Neural Computation,2011,23(12):3016-3069
|
CSCD被引
1
次
|
|
|
|
|
11.
Wang J. Online versus offline learning for spiking neural networks:A review and new strategies.
Proceedings of the 9th International Conference on Cybernetic Intelligent Systems,2010:1-6
|
CSCD被引
1
次
|
|
|
|
|
12.
Kasabov N K. Neu Cube:A spiking neural network architecture for mapping,learning and understanding of spatio-temporal brain data.
Neural Networks,2014,52:62-76
|
CSCD被引
8
次
|
|
|
|
|
13.
Oniz Y. Variable-structure-systems based approach for online learning of spiking neural networks and its experimental evaluation.
Journal of the Franklin Institute,2014,351(6):3269-3285
|
CSCD被引
2
次
|
|
|
|
|
14.
Rumelhart D E. Learning representations by back-propagating errors.
Nature,1986,323(9):533-536
|
CSCD被引
1023
次
|
|
|
|
|
15.
Bohte S M. Error-backpropagation in temporally encoded networks of spiking neurons.
Neurocomputing,2002,48(1/4):17-37
|
CSCD被引
37
次
|
|
|
|
|
16.
Gerstner W.
Spiking Neuron Models:Single Neurons, Populations,Plasticity,2002
|
CSCD被引
2
次
|
|
|
|
|
17.
Xin J. Supervised learning with spiking neuron networks.
Proceedings of the International Joint Conference on Neural Networks,2001:1772-1777
|
CSCD被引
1
次
|
|
|
|
|
18.
Schrauwen B. Extending SpikeProp.
Proceedings of the International Joint Conference on Neural Networks,2004:471-475
|
CSCD被引
3
次
|
|
|
|
|
19.
Mc Kennoch S. Fast modifications of the SpikeProp algorithm.
Proceedings of the International Joint Conference on Neural Networks,2006:3970-3977
|
CSCD被引
1
次
|
|
|
|
|
20.
Mc Kennoch S. Spike-timing error backpropagation in theta neuron networks.
Neural Computation,2009,21(1):9-45
|
CSCD被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问