Supervised Learning in Spiking Neural Networks with Synaptic Delay Plasticity: An Overview

(E-pub Ahead of Print)

Author(s): Yawen Lan, Qiang Li*.

Journal Name: Current Bioinformatics

Become EABM
Become Reviewer

Abstract:

Throughout the central nervous system (CNS), the information communicated between neurons is mainly implemented by the action potentials (or spikes). Although the spike-timing based neuronal codes have significant computational advantages over rate encoding scheme, the exact spike timing-based learning mechanism in the brain remains an open question. To close this gap, many weight-based supervised learning algorithms have been proposed for spiking neural networks. However, it is insufficient to consider only synaptic weight plasticity, and biological evidences suggest that the synaptic delay plasticity also plays an important role in the learning progress in biological neural networks. Recently, there are many learning algorithms have been proposed to consider both the synaptic weight plasticity and synaptic delay plasticity. The goal of this paper is to give an overview of the existing synaptic delay-based learning algorithms in spiking neural networks. We describe the typical learning algorithms and report the experimental results. Finally, we discuss the properties and limitations of each algorithm and make a comparison among them.

Keywords: Action potentials, spike-timing, spiking neural networks, biological neural networks, supervised learning, synaptic delay plasticity

Rights & PermissionsPrintExport Cite as

Article Details

(E-pub Ahead of Print)
DOI: 10.2174/1574893615999200425230713
Price: $95