Temporal learning in multilayer spiking neural networks through construction of causal connections

Qiang Yu, Huajin Tang, Jun Hu, Kay Chen Tan

Research output: Chapter in book / Conference proceedingChapter in an edited book (as author)Academic researchpeer-review

4 Citations (Scopus)

Abstract

This chapter presents a new supervised temporal learning rule for multilayer spiking neural networks. We present and analyze the mechanisms utilized in the network for the construction of causal connections. Synaptic efficacies are finely tuned for resulting in a desired post-synaptic firing status. Both the PSD rule and the tempotron rule are extended to multiple layers, leading to new rules of multilayer PSD (MutPSD) and multilayer tempotron (MutTmptr). The algorithms are applied successfully to classic linearly non-separable benchmarks like the XOR and the Iris problems.

Original languageEnglish
Title of host publicationIntelligent Systems Reference Library
PublisherSpringer Science and Business Media Deutschland GmbH
Pages115-129
Number of pages15
DOIs
Publication statusPublished - 2017
Externally publishedYes

Publication series

NameIntelligent Systems Reference Library
Volume126
ISSN (Print)1868-4394
ISSN (Electronic)1868-4408

ASJC Scopus subject areas

  • General Computer Science
  • Information Systems and Management
  • Library and Information Sciences

Fingerprint

Dive into the research topics of 'Temporal learning in multilayer spiking neural networks through construction of causal connections'. Together they form a unique fingerprint.

Cite this