Evolutionary strategy for learning multiple-valued logic functions

Alioune Ngom; Dan A. Simovici; Ivan Stojmenović

Evolutionary strategy for learning multiple-valued logic functions

Alioune Ngom
, Dan A. Simovici
, Ivan Stojmenović

Computer Science

University of Windsor
University of Ottawa

Research output: Contribution to journal › Article › peer-review

Abstract

We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V ⊆ Kⁿ is described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.

Original language	English
Pages (from-to)	459-489
Number of pages	31
Journal	Journal of Multiple-Valued Logic and Soft Computing
Volume	12
Issue number	5-6
State	Published - 2006

ASJC Scopus Subject Areas

Software
Theoretical Computer Science
Logic

Keywords

Constructive algorithm
Evolution strategy
Multiple-threshold perceptron
Multiple-valued logic
Neural network
Partitioning method

Cite this

@article{6f5fa8e40b7c4685828258a357b6e9f2,

title = "Evolutionary strategy for learning multiple-valued logic functions",

abstract = "We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V ⊆ Kn is described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.",

keywords = "Constructive algorithm, Evolution strategy, Multiple-threshold perceptron, Multiple-valued logic, Neural network, Partitioning method",

author = "Alioune Ngom and Simovici, \{Dan A.\} and Ivan Stojmenovi{\'c}",

year = "2006",

language = "English",

volume = "12",

pages = "459--489",

journal = "Journal of Multiple-Valued Logic and Soft Computing",

issn = "1542-3980",

publisher = "Old City Publishing",

number = "5-6",

}

TY - JOUR

T1 - Evolutionary strategy for learning multiple-valued logic functions

AU - Ngom, Alioune

AU - Simovici, Dan A.

AU - Stojmenović, Ivan

PY - 2006

Y1 - 2006

N2 - We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V ⊆ Kn is described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.

AB - We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V ⊆ Kn is described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.

KW - Constructive algorithm

KW - Evolution strategy

KW - Multiple-threshold perceptron

KW - Multiple-valued logic

KW - Neural network

KW - Partitioning method

UR - https://www.scopus.com/pages/publications/33846398124

UR - https://www.scopus.com/pages/publications/33846398124#tab=citedBy

M3 - Article

AN - SCOPUS:33846398124

SN - 1542-3980

VL - 12

SP - 459

EP - 489

JO - Journal of Multiple-Valued Logic and Soft Computing

JF - Journal of Multiple-Valued Logic and Soft Computing

IS - 5-6

ER -

Evolutionary strategy for learning multiple-valued logic functions

Abstract

ASJC Scopus Subject Areas

Keywords

Other files and links

Fingerprint

Cite this