Playing tic-tac-toe using a modified neural network and an improved genetic algorithm

H. K. Lam; S. H. Ling; Hung Fat Frank Leung; P. K.S. Tam; Y. S. Lee

doi:10.1109/IECON.2002.1185276

Playing tic-tac-toe using a modified neural network and an improved genetic algorithm

H. K. Lam, S. H. Ling, Hung Fat Frank Leung, P. K.S. Tam, Y. S. Lee

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

1 Citation (Scopus)

Abstract

This paper presents an algorithm of playing game tic-tac-loc. This algorithm is learned by a modified neural network (NN), which is trained by an improved genetic algorithm (CA). In the proposed NN, the neuron has two activation functions and exhibits a node-to-node relationship in the hidden layer that enhances the learning ability of the network. It will be shown that the proposed NN and GA provide a better performance than the traditional approach.

Original language	English
Title of host publication	IECON Proceedings (Industrial Electronics Conference)
Pages	1984-1989
Number of pages	6
DOIs	https://doi.org/10.1109/IECON.2002.1185276
Publication status	Published - 1 Dec 2002
Event	Proceedings of the 2002 28th Annual Conference of the IEEE Industrial Electronics Society - Sevilla, Spain Duration: 5 Nov 2002 → 8 Nov 2002

Conference

Conference	Proceedings of the 2002 28th Annual Conference of the IEEE Industrial Electronics Society
Country/Territory	Spain
City	Sevilla
Period	5/11/02 → 8/11/02

ASJC Scopus subject areas

Control and Systems Engineering
Electrical and Electronic Engineering

More information

10.1109/IECON.2002.1185276

http://hdl.handle.net/10397/1364

Cite this

@inproceedings{f6280829326e40d0b663753200f58bd3,

title = "Playing tic-tac-toe using a modified neural network and an improved genetic algorithm",

abstract = "This paper presents an algorithm of playing game tic-tac-loc. This algorithm is learned by a modified neural network (NN), which is trained by an improved genetic algorithm (CA). In the proposed NN, the neuron has two activation functions and exhibits a node-to-node relationship in the hidden layer that enhances the learning ability of the network. It will be shown that the proposed NN and GA provide a better performance than the traditional approach.",

author = "Lam, {H. K.} and Ling, {S. H.} and Leung, {Hung Fat Frank} and Tam, {P. K.S.} and Lee, {Y. S.}",

year = "2002",

month = dec,

day = "1",

doi = "10.1109/IECON.2002.1185276",

language = "English",

pages = "1984--1989",

booktitle = "IECON Proceedings (Industrial Electronics Conference)",

note = "Proceedings of the 2002 28th Annual Conference of the IEEE Industrial Electronics Society ; Conference date: 05-11-2002 Through 08-11-2002",

}

Lam, HK, Ling, SH, Leung, HFF, Tam, PKS & Lee, YS 2002, Playing tic-tac-toe using a modified neural network and an improved genetic algorithm. in IECON Proceedings (Industrial Electronics Conference). pp. 1984-1989, Proceedings of the 2002 28th Annual Conference of the IEEE Industrial Electronics Society, Sevilla, Spain, 5/11/02. https://doi.org/10.1109/IECON.2002.1185276

TY - GEN

T1 - Playing tic-tac-toe using a modified neural network and an improved genetic algorithm

AU - Lam, H. K.

AU - Ling, S. H.

AU - Leung, Hung Fat Frank

AU - Tam, P. K.S.

AU - Lee, Y. S.

PY - 2002/12/1

Y1 - 2002/12/1

N2 - This paper presents an algorithm of playing game tic-tac-loc. This algorithm is learned by a modified neural network (NN), which is trained by an improved genetic algorithm (CA). In the proposed NN, the neuron has two activation functions and exhibits a node-to-node relationship in the hidden layer that enhances the learning ability of the network. It will be shown that the proposed NN and GA provide a better performance than the traditional approach.

AB - This paper presents an algorithm of playing game tic-tac-loc. This algorithm is learned by a modified neural network (NN), which is trained by an improved genetic algorithm (CA). In the proposed NN, the neuron has two activation functions and exhibits a node-to-node relationship in the hidden layer that enhances the learning ability of the network. It will be shown that the proposed NN and GA provide a better performance than the traditional approach.

UR - http://www.scopus.com/inward/record.url?scp=0036948888&partnerID=8YFLogxK

U2 - 10.1109/IECON.2002.1185276

DO - 10.1109/IECON.2002.1185276

M3 - Conference article published in proceeding or book

SP - 1984

EP - 1989

BT - IECON Proceedings (Industrial Electronics Conference)

T2 - Proceedings of the 2002 28th Annual Conference of the IEEE Industrial Electronics Society

Y2 - 5 November 2002 through 8 November 2002

ER -

Playing tic-tac-toe using a modified neural network and an improved genetic algorithm

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this