Implementing fuzzy reasoning on a spiking neural network

C. Glackin; L. McDaid; L. Maguire; H. Sayers

doi:10.1007/978-3-540-87559-8_27

Implementing fuzzy reasoning on a spiking neural network

C. Glackin, L. McDaid, L. Maguire, H. Sayers

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 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 frequencies. The receptive fields behave in a similar manner as fuzzy membership functions. The network is supervised but learning only occurs locally as in the biological case. The connectivity of the hidden and output layers is representative of a fuzzy rule base. The advantages and disadvantages of the network topology for the IRIS classification task are demonstrated and directions of current and future work are discussed

Original language	English
Title of host publication	Artificial Neural Networks - ICANN 2008
Subtitle of host publication	Proceedings, Part II
Publisher	Springer Nature
Pages	258-267
Number of pages	10
ISBN (Electronic)	978-3-540-87559-8
ISBN (Print)	978-3-540-87559-8
DOIs	https://doi.org/10.1007/978-3-540-87559-8_27
Publication status	Published - 2008

Publication series

Name	Lecture Notes in Computer Science
Volume	5164

Access to Document

10.1007/978-3-540-87559-8_27

Cite this

@inproceedings{6d090fe933c749748cbbd6f57bb2eafe,

title = "Implementing fuzzy reasoning on a 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 frequencies. The receptive fields behave in a similar manner as fuzzy membership functions. The network is supervised but learning only occurs locally as in the biological case. The connectivity of the hidden and output layers is representative of a fuzzy rule base. The advantages and disadvantages of the network topology for the IRIS classification task are demonstrated and directions of current and future work are discussed",

author = "C. Glackin and L. McDaid and L. Maguire and H. Sayers",

year = "2008",

doi = "10.1007/978-3-540-87559-8_27",

language = "English",

isbn = "978-3-540-87559-8",

series = "Lecture Notes in Computer Science",

publisher = "Springer Nature",

pages = "258--267",

booktitle = "Artificial Neural Networks - ICANN 2008",

address = "Netherlands",

}

TY - GEN

T1 - Implementing fuzzy reasoning on a spiking neural network

AU - Glackin, C.

AU - McDaid, L.

AU - Maguire, L.

AU - Sayers, H.

PY - 2008

Y1 - 2008

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 frequencies. The receptive fields behave in a similar manner as fuzzy membership functions. The network is supervised but learning only occurs locally as in the biological case. The connectivity of the hidden and output layers is representative of a fuzzy rule base. The advantages and disadvantages of the network topology for the IRIS classification task 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 frequencies. The receptive fields behave in a similar manner as fuzzy membership functions. The network is supervised but learning only occurs locally as in the biological case. The connectivity of the hidden and output layers is representative of a fuzzy rule base. The advantages and disadvantages of the network topology for the IRIS classification task are demonstrated and directions of current and future work are discussed

U2 - 10.1007/978-3-540-87559-8_27

DO - 10.1007/978-3-540-87559-8_27

M3 - Conference contribution

SN - 978-3-540-87559-8

T3 - Lecture Notes in Computer Science

SP - 258

EP - 267

BT - Artificial Neural Networks - ICANN 2008

PB - Springer Nature

ER -

Implementing fuzzy reasoning on a spiking neural network

Abstract

Publication series

Access to Document

Fingerprint

Cite this