A Class of Neural Networks Based on Approximate Identity for Analog IC's Hardware Implementation

Massimo CONTI  Simone ORCIONI  Claudio TURCHETTI  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E77-A   No.6   pp.1069-1079
Publication Date: 1994/06/25
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks
neural network,  approximate identity,  analog integrated circuits,  learning,  

Full Text: PDF>>
Buy this Article

Artificial Neural Networks (ANN's) that are able to learn exhibit many interesting features making them suitable to be applied in several fields such as pattern recognition, computer vision and so forth. Learning a given input-output mapping can be regarded as a problem of approximating a multivariate function. In this paper we will report a theoretical framework for approximation, based on the well known sequences of functions named approximate identities. In particular, it is proven that such sequences are able to approximate a generally continuous function to any degree of accuracy. On the basis of these theoretical results, it is shown that the proposed approximation scheme maps into a class of networks which can efficiently be implemented with analog MOS VLSI or BJT integrated circuits. To prove the validity of the proposed approach a series of results is reported.