Supervised Learning Algorithms for Spiking Neural Networks: A Review
Supervised Learning Algorithms for Spiking Neural Networks: A Review
复制标题
DOI：
--
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Lin Xiang-hon
中科院分区：
文献类型：
--
作者：
Lin Xiang-hon
Spiking neural netw orks are show n to be suitable tools for the processing of spatio-temporal information.How ever,due to their intricately discontinuous and implicit nonlinear mechanisms,the formulation of efficient supervised learning algorithms for spiking neural netw orks is difficult,w hich is an important problem in the research area. In this paper,w e introduce the general framew ork of supervised learning algorithms for spiking neural netw orks,and analyze their performance evaluations including spike trains learning ability,offline and online processing ability,the locality of learning mechanism and the applicability to netw ork structure. Furthermore,w e survey the advance of the research on supervised learning algorithms,w hich can be divided into three categories according to their differences: gradient descent rule,synaptic plasticity rule,and spike trains convolution rule. Finally,w e discuss the advantages and disadvantages of these algorithms,and prospect the problems in current research and some future research directions in this area.
