A Hybrid Learning Algorithm Fusing STDP with GA based Explicit Delay Learning for Spiking Neurons

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

4 Citations (Scopus)

Abstract

This paper presents a hybrid learning algorithmfor spiking neural networks (SNNs), referred to as an evolvablespiking neural network (ESNN) paradigm. The algorithmintegrates a supervised and unsupervised learning approach.The unsupervised approach exploits a Spike Timing DependentPlasticity (STDP) mechanism with explicit delay learningfor multiple connections between neurons. Supervision of thesynaptic delays and the excitatory/inhibitory connections isgoverned by a genetic algorithm (GA), while the STDP rule isfree to operate in its normal unsupervised manner. A spike trainencoding/decoding scheme is developed for the algorithm. Theapproach is validated by application to the Iris classificationproblem.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages632-637
Number of pages6
DOIs
Publication statusPublished - Sep 2006
Event3rd IEEE International conference on Intelligent Systems, Westminster, London, September 06 -
Duration: 1 Sep 2006 → …

Conference

Conference3rd IEEE International conference on Intelligent Systems, Westminster, London, September 06
Period1/09/06 → …

Fingerprint

Learning algorithms
Neurons
Genetic algorithms
Neural networks
Unsupervised learning
Supervised learning
Decoding

Cite this

@inproceedings{4c120b047ab04de6909f992f6c709f60,
title = "A Hybrid Learning Algorithm Fusing STDP with GA based Explicit Delay Learning for Spiking Neurons",
abstract = "This paper presents a hybrid learning algorithmfor spiking neural networks (SNNs), referred to as an evolvablespiking neural network (ESNN) paradigm. The algorithmintegrates a supervised and unsupervised learning approach.The unsupervised approach exploits a Spike Timing DependentPlasticity (STDP) mechanism with explicit delay learningfor multiple connections between neurons. Supervision of thesynaptic delays and the excitatory/inhibitory connections isgoverned by a genetic algorithm (GA), while the STDP rule isfree to operate in its normal unsupervised manner. A spike trainencoding/decoding scheme is developed for the algorithm. Theapproach is validated by application to the Iris classificationproblem.",
author = "SP Johnston and G Prasad and Liam Maguire and TM McGinnity",
year = "2006",
month = "9",
doi = "10.1109/IS.2006.348493",
language = "English",
pages = "632--637",
booktitle = "Unknown Host Publication",

}

Johnston, SP, Prasad, G, Maguire, L & McGinnity, TM 2006, A Hybrid Learning Algorithm Fusing STDP with GA based Explicit Delay Learning for Spiking Neurons. in Unknown Host Publication. pp. 632-637, 3rd IEEE International conference on Intelligent Systems, Westminster, London, September 06, 1/09/06. https://doi.org/10.1109/IS.2006.348493

A Hybrid Learning Algorithm Fusing STDP with GA based Explicit Delay Learning for Spiking Neurons. / Johnston, SP; Prasad, G; Maguire, Liam; McGinnity, TM.

Unknown Host Publication. 2006. p. 632-637.

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

TY - GEN

T1 - A Hybrid Learning Algorithm Fusing STDP with GA based Explicit Delay Learning for Spiking Neurons

AU - Johnston, SP

AU - Prasad, G

AU - Maguire, Liam

AU - McGinnity, TM

PY - 2006/9

Y1 - 2006/9

N2 - This paper presents a hybrid learning algorithmfor spiking neural networks (SNNs), referred to as an evolvablespiking neural network (ESNN) paradigm. The algorithmintegrates a supervised and unsupervised learning approach.The unsupervised approach exploits a Spike Timing DependentPlasticity (STDP) mechanism with explicit delay learningfor multiple connections between neurons. Supervision of thesynaptic delays and the excitatory/inhibitory connections isgoverned by a genetic algorithm (GA), while the STDP rule isfree to operate in its normal unsupervised manner. A spike trainencoding/decoding scheme is developed for the algorithm. Theapproach is validated by application to the Iris classificationproblem.

AB - This paper presents a hybrid learning algorithmfor spiking neural networks (SNNs), referred to as an evolvablespiking neural network (ESNN) paradigm. The algorithmintegrates a supervised and unsupervised learning approach.The unsupervised approach exploits a Spike Timing DependentPlasticity (STDP) mechanism with explicit delay learningfor multiple connections between neurons. Supervision of thesynaptic delays and the excitatory/inhibitory connections isgoverned by a genetic algorithm (GA), while the STDP rule isfree to operate in its normal unsupervised manner. A spike trainencoding/decoding scheme is developed for the algorithm. Theapproach is validated by application to the Iris classificationproblem.

U2 - 10.1109/IS.2006.348493

DO - 10.1109/IS.2006.348493

M3 - Conference contribution

SP - 632

EP - 637

BT - Unknown Host Publication

ER -