Presentation 1998/3/19
Neural Networks Memorizing Sequential Patterns
Taiga Yamasaki, Yoshinori Kataoka, Katsuro Kameyama, kaoru Nakano,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is necessary to retain information of the past for handling inputs varying with time. So, we introduce the concept "stimuli accumulation effect" that each unit accumulates accepted stimuli when it is not excited. Each unit gets excited by the influence of not only current input but also past inputs. Using this effect, we made neural networks scanning all through the memory space, and associating a temporal sequence with a static pattern.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural network / Stimuli accumulation effect / Association / Temporal sequence
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 1998/3/19(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) Neural Networks Memorizing Sequential Patterns
Sub Title (in English)
Keyword(1) Neural network
Keyword(2) Stimuli accumulation effect
Keyword(3) Association
Keyword(4) Temporal sequence
1st Author's Name Taiga Yamasaki
1st Author's Affiliation Graduate School of Engineering Science Osaka University()
2nd Author's Name Yoshinori Kataoka
2nd Author's Affiliation Graduate School of Engineering Science Osaka University
3rd Author's Name Katsuro Kameyama
3rd Author's Affiliation Graduate School of Engineering Science Osaka University
4th Author's Name kaoru Nakano
4th Author's Affiliation Graduate School of Engineering Science Osaka University
Date 1998/3/19
Paper #
Volume (vol) vol.97
Number (no) 623
Page pp.pp.-
#Pages 8
Date of Issue