Presentation 1998/3/20
Self-Consistent Signal-to-Noise Analysis of the Statistical Behavior of Feed-Forward Chains of Recurrent Attractor Neural Networks
Tatsuto MURAYAMA, Masatoshi SHIINO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We perform the Self-Consistent Signal-to-Noise Analysis for a layered network of Ising spin neurons, with recurrent Hebbian interactions within each layer, in combination with strictly feed-forward Hebbian interactions between successive layers. We show the phase diagram obtained by the SCSNA.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) associative memory / asymmetric couplings / layered attractor networks / TAP equation / replica method / SCSNA
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 1998/3/20(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) Self-Consistent Signal-to-Noise Analysis of the Statistical Behavior of Feed-Forward Chains of Recurrent Attractor Neural Networks
Sub Title (in English)
Keyword(1) associative memory
Keyword(2) asymmetric couplings
Keyword(3) layered attractor networks
Keyword(4) TAP equation
Keyword(5) replica method
Keyword(6) SCSNA
1st Author's Name Tatsuto MURAYAMA
1st Author's Affiliation Department of Computational Intelligence and Systems Science, Interdisciplinary Graduate School of Science and Engineering, Tokyo Institute of Technology()
2nd Author's Name Masatoshi SHIINO
2nd Author's Affiliation Department of Applied Physics, Tokyo Institute of Technology
Date 1998/3/20
Paper #
Volume (vol) vol.97
Number (no) 624
Page pp.pp.-
#Pages 8
Date of Issue