NEIGHBOR-LAYER UPDATING IN MBDS FOR THE RECALL OF PURE BIPOLAR PATTERNS IN GRAY-SCALE NOISE

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > journal & Dissertation > Item 987654321/29228

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/29228

Title:	NEIGHBOR-LAYER UPDATING IN MBDS FOR THE RECALL OF PURE BIPOLAR PATTERNS IN GRAY-SCALE NOISE
Authors:	LEE,DL;WANG,WJ
Contributors:	資訊工程研究所
Keywords:	BIDIRECTIONAL ASSOCIATIVE MEMORIES;NEURAL NETWORKS
Date:	1995
Issue Date:	2010-06-29 20:16:55 (UTC+8)
Publisher:	中央大學
Abstract:	To improve bidirectional associative memory (BAM), a modified bidirectional decoding strategy (MBDS) network has been proposed, The former is a two-layer structure in which stored associations are recalled by directionally updating the neuron state through the connecting weights M and M(T). The latter is an extension of the former in which two hidden layers are augmented and the corresponding extra connection weights-Mx, My, Ta, and Ty-are encoded. We introduce a new updating rule for MBDS networks, called neighbor-layer updating (NLU), which gathers all weighted activations of all neighbor layers, The neighbor layers are defined as the layers in which there are direct synaptic weights connected to each other, Because of modification of the connection weights-Mx, My, Tx, and Ty-and the constant bias inputs of MBDS, all stored associations are guaranteed to be recalled using NLU, Furthermore, with the aid of the Cohen-Grossberg theorem, all discrete MBDS results can be extended to continuous MBDS (we name it CMBDS), We also give stability proofs of both discrete MBDS and CMBDS. Computer simulations demonstrate that the proposed CMBDS can be applied to recall pure bipolar patterns in the presence of gray-scale noise, We show that by removing BAM connections (matrix M) from the MBDS structure, a bidirectional holographic memory (BHM) is obtained. Both derivation and simulation indicate that we can remove the matrix ii from the MBDS structure if the dimension of the training associations is larger than 16.
Relation:	IEEE TRANSACTIONS ON NEURAL NETWORKS
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] journal & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	451	View/Open

社群 sharing

Loading...