Presentation 1997/3/17
Three dimensional Artificial Cellular Neural Networks for flexible judgment of circumstances
Daisuke HIRATSU, Tomoharu NAGAO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Artificial Cellular Neural Network(ACNN) is a kind of Neural Networks(NNs) whose connections of its each unit only exist between itself and its neighborhood units. Viewed from structure of network, ACNN includes layered NN, and recurrent NN includes ACNN. ACNN has several merits that layered NN or recurrent NN do not have. For example, ACNN can deal with signal processing which layered NN cannot do. Besides, amount of data which is required to represent ACNN is less than that of recurrent NN. In this paper, decision of chaser's action in a "chase game" is controlled by a three dimensional ACNN. We made the three dimensional ACNN which could flexibly judge circumstances, and demonstrated its ability. In addition, we used Genetic Algorithm(GA) in making three dimensional ACNN.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Artificial Cellular Neural Networks / Genetic Algorithm
Paper # NC96-149
Date of Issue

Conference Information
Committee NC
Conference Date 1997/3/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Three dimensional Artificial Cellular Neural Networks for flexible judgment of circumstances
Sub Title (in English)
Keyword(1) Artificial Cellular Neural Networks
Keyword(2) Genetic Algorithm
1st Author's Name Daisuke HIRATSU
1st Author's Affiliation Imaging Science and Engineering Laboratory, Tokyo Institute of Technology()
2nd Author's Name Tomoharu NAGAO
2nd Author's Affiliation Imaging Science and Engineering Laboratory, Tokyo Institute of Technology
Date 1997/3/17
Paper # NC96-149
Volume (vol) vol.96
Number (no) 583
Page pp.pp.-
#Pages 8
Date of Issue