Presentation 1995/11/24
A method of multiple simultaneous association of pattern with bidirectional data flow
Yutaka Kawabata, Yosimasa Daido, Shimmi Hattori,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a new modification of BAM which is capable of multiple association. For correspondence of one input data and 'n' output data, 'n' output, binary data are converted to a multileveled output data. Thus, network for one to one. correspondence can easily be extended to one to 'n' correspondence. Applying the conversion from binary to multileveled data to both input and output layer BAM is modified to attain association between 'n' input and 'm' output data.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Bidirectional Associative Memory (BAM) / Multilevel data / multiple association
Paper # NC95-66
Date of Issue

Conference Information
Committee NC
Conference Date 1995/11/24(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) A method of multiple simultaneous association of pattern with bidirectional data flow
Sub Title (in English)
Keyword(1) Bidirectional Associative Memory (BAM)
Keyword(2) Multilevel data
Keyword(3) multiple association
1st Author's Name Yutaka Kawabata
1st Author's Affiliation Department of Information Science Kanazawa institute of technology()
2nd Author's Name Yosimasa Daido
2nd Author's Affiliation Department of Information Science Kanazawa institute of technology
3rd Author's Name Shimmi Hattori
3rd Author's Affiliation Department of Information Science Kanazawa institute of technology
Date 1995/11/24
Paper # NC95-66
Volume (vol) vol.95
Number (no) 389
Page pp.pp.-
#Pages 6
Date of Issue