Presentation 1998/10/22
Unlearning for Bilayer Associative Memories
Takatoshi Sakaue, Takenori YAMASE, Masachika MIYATA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper discribes about the properties of a bilayer neural associative memory in which neurons having mid-step nonlinearity are used for the mid-layer to suppress the spurious memories. In order to improve its performance, we carried out simulation to see the effects of unlearning. According to simulation results, unlearing is not effective as expected.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural network / associative memory / spurious memory
Paper # NLP98-59
Date of Issue

Conference Information
Committee NLP
Conference Date 1998/10/22(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 Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Unlearning for Bilayer Associative Memories
Sub Title (in English)
Keyword(1) Neural network
Keyword(2) associative memory
Keyword(3) spurious memory
1st Author's Name Takatoshi Sakaue
1st Author's Affiliation Kanazawa Institute of Tecnology()
2nd Author's Name Takenori YAMASE
2nd Author's Affiliation Kanazawa Institute of Tecnology
3rd Author's Name Masachika MIYATA
3rd Author's Affiliation Kanazawa Institute of Tecnology
Date 1998/10/22
Paper # NLP98-59
Volume (vol) vol.98
Number (no) 343
Page pp.pp.-
#Pages 4
Date of Issue