Minimal optimal topologies for invariant higher-order neural architectures using genetic algorithms

Panagiotis Liatsis; Yannis J.P. Goulermas

Minimal optimal topologies for invariant higher-order neural architectures using genetic algorithms

Panagiotis Liatsis, Yannis J.P. Goulermas

Electrical Engineering

University of Manchester

Research output: Contribution to conference › Paper › peer-review

11 Scopus citations

Abstract

Higher-order neural networks (HONNs) are successful in performing PRSI recognition. A major limitation of these networks is the combinatorial explosion of the higher-order terms, which increases the complexity of the network architecture. This work proposes a genetic optimisation scheme for determining the minimal optimal topology of a network for automated inspection of industrial parts.

Original language	British English
Pages	792-797
Number of pages	6
State	Published - 1995
Event	Proceedings of the 1995 IEEE International Symposium on Industrial Electronics, ISIE'95. Part 1 (of 2) - Athens, Greece Duration: 10 Jul 1995 → 14 Jul 1995

Conference

Conference	Proceedings of the 1995 IEEE International Symposium on Industrial Electronics, ISIE'95. Part 1 (of 2)
City	Athens, Greece
Period	10/07/95 → 14/07/95

Cite this

@conference{c44517ed2b6243bcadf5b76fbbc88a8c,

title = "Minimal optimal topologies for invariant higher-order neural architectures using genetic algorithms",

abstract = "Higher-order neural networks (HONNs) are successful in performing PRSI recognition. A major limitation of these networks is the combinatorial explosion of the higher-order terms, which increases the complexity of the network architecture. This work proposes a genetic optimisation scheme for determining the minimal optimal topology of a network for automated inspection of industrial parts.",

author = "Panagiotis Liatsis and Goulermas, {Yannis J.P.}",

year = "1995",

language = "British English",

pages = "792--797",

note = "Proceedings of the 1995 IEEE International Symposium on Industrial Electronics, ISIE'95. Part 1 (of 2) ; Conference date: 10-07-1995 Through 14-07-1995",

}

TY - CONF

T1 - Minimal optimal topologies for invariant higher-order neural architectures using genetic algorithms

AU - Liatsis, Panagiotis

AU - Goulermas, Yannis J.P.

PY - 1995

Y1 - 1995

N2 - Higher-order neural networks (HONNs) are successful in performing PRSI recognition. A major limitation of these networks is the combinatorial explosion of the higher-order terms, which increases the complexity of the network architecture. This work proposes a genetic optimisation scheme for determining the minimal optimal topology of a network for automated inspection of industrial parts.

AB - Higher-order neural networks (HONNs) are successful in performing PRSI recognition. A major limitation of these networks is the combinatorial explosion of the higher-order terms, which increases the complexity of the network architecture. This work proposes a genetic optimisation scheme for determining the minimal optimal topology of a network for automated inspection of industrial parts.

UR - http://www.scopus.com/inward/record.url?scp=0029518588&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029518588

SP - 792

EP - 797

T2 - Proceedings of the 1995 IEEE International Symposium on Industrial Electronics, ISIE'95. Part 1 (of 2)

Y2 - 10 July 1995 through 14 July 1995

ER -

Minimal optimal topologies for invariant higher-order neural architectures using genetic algorithms

Abstract

Conference

Other files and links

Fingerprint

Cite this