Sparsely Interconnected Neural Networks for Associative Memories Applying Discrete Walsh Transform

Takeshi KAMIO  Hideki ASAI  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E82-A    No.3    pp.495-499
Publication Date: 1999/03/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8508
Type of Manuscript: Special Section LETTER (Special Section on Selected Papers from the 11th Workshop on Circuits and Systems in Karuizawa)
Category: 
Keyword: 
sparsely interconnected neural network,  associative memory,  2-dimensional discrete Walsh transform,  isolated cells problem,  

Full Text: PDF(212.6KB)>>
Buy this Article



Summary: 
The conventional synthesis procedure of discrete time sparsely interconnected neural networks (DTSINNs) for associative memories may generate the cells with only self-feedback due to the sparsely interconnected structure. Although this problem is solved by increasing the number of interconnections, hardware implementation becomes very difficult. In this letter, we propose the DTSINN system which stores the 2-dimensional discrete Walsh transforms (DWTs) of memory patterns. As each element of DWT involves the information of whole sample data, our system can associate the desired memory patterns, which the conventional DTSINN fails to do.