Presentation	1997/10/20 On the Principle of Hierarchical Sequence Encoding and Short-Term Memory in the Brain Ryoko Futami, Nozomu Hoshimiya,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	It is shown by the computer simulations that arbitrary temporal sequences can be roughly encoded into neural memory traces by the principle of hierarchical transition detection and integration. The neural sequence encoders based on this principle can be self-organized wtithout teachers. It is also shown that the mapping from sequence into memory trace has good continuity. For the evaluation of the encoding scheme, generalization abilities are examined on neural netwrork models which were trained to reproduce the encoded sequences.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Neural network / Sequence / Encoding / Short-term memory / Reproduction
Paper #	NC97-38
Date of Issue

Conference Information
Committee	NC
Conference Date	1997/10/20(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)	On the Principle of Hierarchical Sequence Encoding and Short-Term Memory in the Brain
Sub Title (in English)
Keyword(1)	Neural network
Keyword(2)	Sequence
Keyword(3)	Encoding
Keyword(4)	Short-term memory
Keyword(5)	Reproduction
1st Author's Name	Ryoko Futami
1st Author's Affiliation	Dept. of Electronic Engineering, Tohoku University()
2nd Author's Name	Nozomu Hoshimiya
2nd Author's Affiliation	Dept. of Electronic Engineering, Tohoku University
Date	1997/10/20
Paper #	NC97-38
Volume (vol)	vol.97
Number (no)	332
Page	pp.pp.-
#Pages	6
Date of Issue