Presentation 1999/2/5
A Method for Sustaining Activities in Short-term Memory Model Using Recurrent Neural Network
Shuhei Okada, Jianting Cao, Shoji Tanaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A short-term memory modeled by recurrent neural network has a difficulty in sustaining the activities. They eventually converge to some constant values so called the attractors. In this paper, we will propose a short-term memory model which enables to sustain the multiple activities either in learning or testing process. Moreover, we will compare the dynamics property of proposed model with biological neurons and show the reality of proposed model.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Working Memory / Short-term Memory / Attractor / Dynamics / Learning
Paper # NC98-89
Date of Issue

Conference Information
Committee NC
Conference Date 1999/2/5(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 for Sustaining Activities in Short-term Memory Model Using Recurrent Neural Network
Sub Title (in English)
Keyword(1) Working Memory
Keyword(2) Short-term Memory
Keyword(3) Attractor
Keyword(4) Dynamics
Keyword(5) Learning
1st Author's Name Shuhei Okada
1st Author's Affiliation Department of Electrical and Electronics Engineering, Sophia University()
2nd Author's Name Jianting Cao
2nd Author's Affiliation Department of Electrical and Electronics Engineering, Sophia University:Brain Science Institute,RIKEN
3rd Author's Name Shoji Tanaka
3rd Author's Affiliation Department of Electrical and Electronics Engineering, Sophia University
Date 1999/2/5
Paper # NC98-89
Volume (vol) vol.98
Number (no) 577
Page pp.pp.-
#Pages 8
Date of Issue