Presentation 1994/5/19
Dynamic Analysis of Associative Memories and Effects of Threshold Control
Kyoko Miyake, Keiko Kido, Keisuke Ikehara, Kenji Nakayama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Associative memories,which can perform additional learning and human like associative functions,are discussed.The conventional models include the instance unit model,the activation spread model and the constraint satisfaction model.They can perform fundamental association.However,it is rather difficult to perform complicated association.Human like association functions are also difficult to be done.One of the reasons is inhibitory connections.In the third model,it is difficult to estimate the optimum sampling point.On the other hand,the proposed NN model can provide more wide range of associative functions.Furthermore,relation between the variable threshold and association is discussed.As a result,it becomes possible to estimate the optimum sampling point.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Associative memory / Additional learning / Psychology / Threshold
Paper # NC94-13
Date of Issue

Conference Information
Committee NC
Conference Date 1994/5/19(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) Dynamic Analysis of Associative Memories and Effects of Threshold Control
Sub Title (in English)
Keyword(1) Associative memory
Keyword(2) Additional learning
Keyword(3) Psychology
Keyword(4) Threshold
1st Author's Name Kyoko Miyake
1st Author's Affiliation Kanazawa University()
2nd Author's Name Keiko Kido
2nd Author's Affiliation Hokuriku NEC Software
3rd Author's Name Keisuke Ikehara
3rd Author's Affiliation NTT
4th Author's Name Kenji Nakayama
4th Author's Affiliation Kanazawa University
Date 1994/5/19
Paper # NC94-13
Volume (vol) vol.94
Number (no) 40
Page pp.pp.-
#Pages 8
Date of Issue