For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A Circularly Connected Synergetic Neural Network
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2000/05/25
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks and Bioengineering
group association, synergetic neurons, dynamics of associative memory,
Full Text: PDF(685.4KB)>>
In this paper we shall put forward a novel circularly connected synergetic neural network extending the previously studied auto-correlation or cross-correlation dynamics so as to realise a group memory retrieval. The present model is substantially based on a top-down approach of the dynamic rule of an analog neural network in the similar manner to the conventional synergetic dynamics early proposed by Haken. It will be proved that a complete association can be assured up to the same number of the embedded patterns as the minimal number of neurons of the linked synergetic neural networks. In addition, one finds that a searching process of a couple of embedded patterns can be also realised by means of controlling attraction parameters as was previously reported in the autoassociative synergetic models.