Improving learning algorithm performance for spiking neural networks

Qiang Fu, Yuling Luo, Junxiu Liu, Jinjie Bi, Senhui Qiu, Yi Cao, Xuemei Ding

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes three methods to improve the learning algorithm for spiking neural networks (SNNs). The aim is to improve learning performance in SNNs where neurons are allowed to fire multiple times. The performance is analyzed based on the convergence rate, the concussion condition in the training period and the error between actual output and desired output. The exclusive-or (XOR) and Wisconsin breast cancer (WBC) classification tasks are employed to validate the proposed optimized methods. Experimental results demonstrate that compared to original learning algorithm, all three methods have less iterations, higher accuracy, and more stable in the training period.

Original languageEnglish
Title of host publication2017 17th IEEE International Conference on Communication Technology, ICCT 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1916-1919
Number of pages4
ISBN (Electronic)9781509039432
DOIs
Publication statusPublished - 17 May 2018
Event17th IEEE International Conference on Communication Technology, ICCT 2017 - Chengdu, China
Duration: 27 Oct 201730 Oct 2017

Publication series

NameInternational Conference on Communication Technology Proceedings, ICCT
Volume2017-October

Conference

Conference17th IEEE International Conference on Communication Technology, ICCT 2017
Country/TerritoryChina
CityChengdu
Period27/10/1730/10/17

Keywords

  • learning performance
  • optimization method
  • Spiking Neural Network

Fingerprint

Dive into the research topics of 'Improving learning algorithm performance for spiking neural networks'. Together they form a unique fingerprint.

Cite this