Receptive Field Optimisation and Supervision of a Fuzzy Spiking Neural Network

Neil Glackin, LP Maguire, Liam McDaid, Heather Sayers

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

This paper presents a supervised training algorithm that implements fuzzy reasoning on a spiking neural network. Neuron selectivity is facilitated using receptive fields that enable individual neurons to be responsive to certain spike train firing rates and behave in a similar manner as fuzzy membership functions. The connectivity of the hidden and output layers in the fuzzy spiking neural network (FSNN) is representative of a fuzzy rule base. Fuzzy C-Means clustering is utilised to produce clusters that represent the antecedent part of the fuzzy rule base that aid classification of the feature data. Suitable cluster widths are determined using two strategies; subjective thresholding and evolutionary thresholding respectively. The former technique typically results in compact solutions in terms of the number of neurons, and is shown to be particularly suited to small data sets. In the latter technique a pool of cluster candidates is generated using Fuzzy C-Means clustering and then a genetic algorithm is employed to select the most suitable clusters and to specify cluster widths. In both scenarios, the network is supervised but learning only occurs locally as in the biological case. The advantages and disadvantages of the network topology for the Fisher Iris and Wisconsin Breast Cancer benchmark classification tasks are demonstrated and directions of current and future work are discussed.
LanguageEnglish
Pages247-256
JournalNeural Networks
Volume24
Issue number3
DOIs
Publication statusPublished - Apr 2011

Fingerprint

Fuzzy neural networks
Neurons
Fuzzy rules
Supervised learning
Membership functions
Genetic algorithms
Topology
Neural networks

Cite this

@article{ff74ee55c3cc49f5aabce84450233bee,
title = "Receptive Field Optimisation and Supervision of a Fuzzy Spiking Neural Network",
abstract = "This paper presents a supervised training algorithm that implements fuzzy reasoning on a spiking neural network. Neuron selectivity is facilitated using receptive fields that enable individual neurons to be responsive to certain spike train firing rates and behave in a similar manner as fuzzy membership functions. The connectivity of the hidden and output layers in the fuzzy spiking neural network (FSNN) is representative of a fuzzy rule base. Fuzzy C-Means clustering is utilised to produce clusters that represent the antecedent part of the fuzzy rule base that aid classification of the feature data. Suitable cluster widths are determined using two strategies; subjective thresholding and evolutionary thresholding respectively. The former technique typically results in compact solutions in terms of the number of neurons, and is shown to be particularly suited to small data sets. In the latter technique a pool of cluster candidates is generated using Fuzzy C-Means clustering and then a genetic algorithm is employed to select the most suitable clusters and to specify cluster widths. In both scenarios, the network is supervised but learning only occurs locally as in the biological case. The advantages and disadvantages of the network topology for the Fisher Iris and Wisconsin Breast Cancer benchmark classification tasks are demonstrated and directions of current and future work are discussed.",
author = "Neil Glackin and LP Maguire and Liam McDaid and Heather Sayers",
year = "2011",
month = "4",
doi = "10.1016/j.neunet.2010.11.008",
language = "English",
volume = "24",
pages = "247--256",
journal = "Neural Networks",
issn = "0893-6080",
publisher = "Elsevier",
number = "3",

}

Receptive Field Optimisation and Supervision of a Fuzzy Spiking Neural Network. / Glackin, Neil; Maguire, LP; McDaid, Liam; Sayers, Heather.

In: Neural Networks, Vol. 24, No. 3, 04.2011, p. 247-256.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Receptive Field Optimisation and Supervision of a Fuzzy Spiking Neural Network

AU - Glackin, Neil

AU - Maguire, LP

AU - McDaid, Liam

AU - Sayers, Heather

PY - 2011/4

Y1 - 2011/4

N2 - This paper presents a supervised training algorithm that implements fuzzy reasoning on a spiking neural network. Neuron selectivity is facilitated using receptive fields that enable individual neurons to be responsive to certain spike train firing rates and behave in a similar manner as fuzzy membership functions. The connectivity of the hidden and output layers in the fuzzy spiking neural network (FSNN) is representative of a fuzzy rule base. Fuzzy C-Means clustering is utilised to produce clusters that represent the antecedent part of the fuzzy rule base that aid classification of the feature data. Suitable cluster widths are determined using two strategies; subjective thresholding and evolutionary thresholding respectively. The former technique typically results in compact solutions in terms of the number of neurons, and is shown to be particularly suited to small data sets. In the latter technique a pool of cluster candidates is generated using Fuzzy C-Means clustering and then a genetic algorithm is employed to select the most suitable clusters and to specify cluster widths. In both scenarios, the network is supervised but learning only occurs locally as in the biological case. The advantages and disadvantages of the network topology for the Fisher Iris and Wisconsin Breast Cancer benchmark classification tasks are demonstrated and directions of current and future work are discussed.

AB - This paper presents a supervised training algorithm that implements fuzzy reasoning on a spiking neural network. Neuron selectivity is facilitated using receptive fields that enable individual neurons to be responsive to certain spike train firing rates and behave in a similar manner as fuzzy membership functions. The connectivity of the hidden and output layers in the fuzzy spiking neural network (FSNN) is representative of a fuzzy rule base. Fuzzy C-Means clustering is utilised to produce clusters that represent the antecedent part of the fuzzy rule base that aid classification of the feature data. Suitable cluster widths are determined using two strategies; subjective thresholding and evolutionary thresholding respectively. The former technique typically results in compact solutions in terms of the number of neurons, and is shown to be particularly suited to small data sets. In the latter technique a pool of cluster candidates is generated using Fuzzy C-Means clustering and then a genetic algorithm is employed to select the most suitable clusters and to specify cluster widths. In both scenarios, the network is supervised but learning only occurs locally as in the biological case. The advantages and disadvantages of the network topology for the Fisher Iris and Wisconsin Breast Cancer benchmark classification tasks are demonstrated and directions of current and future work are discussed.

U2 - 10.1016/j.neunet.2010.11.008

DO - 10.1016/j.neunet.2010.11.008

M3 - Article

VL - 24

SP - 247

EP - 256

JO - Neural Networks

T2 - Neural Networks

JF - Neural Networks

SN - 0893-6080

IS - 3

ER -