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

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.

Spiking neural networks are shown to be suitable tools for the processing of spatio-temporal information.Howev- er, due to their intricately discontinuous and implicit nonlinear mechanisms, the formulation of efficient supervised learning algo- rithms 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 includ- ing spike trains learning ability, offline and online processing ability, the locality of learning mechanism and the applicability to net- work 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. Final- ly, we discuss the advantages and disadvantages of these algorithms,and prospect the problems in current research and some future research directions in this area.