Associative Memories Using Interaction between Multilayer Perceptrons and Sparsely Interconnected Neural Networks

Takeshi KAMIO  Hisato FUJISAKA  Mititada MORISUE  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E85-A   No.6   pp.1220-1228
Publication Date: 2002/06/01
Online ISSN: 
DOI: 
Print ISSN: 0916-8508
Type of Manuscript: Special Section PAPER (Special Section on Papers Selected from 2001 International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC 2001))
Category: 
Keyword: 
associative memories,  sparsely interconnected neural networks,  multilayer perceptron,  global information,  

Full Text: PDF(958.9KB)>>
Buy this Article




Summary: 
Associative memories composed of sparsely interconnected neural networks (SINNs) are suitable for analog hardware implementation. However, the sparsely interconnected structure also gives rise to a decrease in the capability of SINNs for associative memories. Although this problem can be solved by increasing the number of interconnections, the hardware cost goes up rapidly. Therefore, we propose associative memories consisting of multilayer perceptrons (MLPs) with 3-valued weights and SINNs. It is expected that such MLPs can be realized at a lower cost than increasing interconnections in SINNs and can give each neuron in SINNs the global information of an input pattern to improve the storage capacity. Finally, it is confirmed by simulations that our proposed associative memories have good performance.