Neural Network-Based Chaotic Pattern Recognition — Part 2: Stability and Algorithmic Issues

Abstract

Traditional Pattern Recognition (PR) systems work with the model that the object to be recognized is characterized by a set of features, which are treated as the inputs. In this paper, we propose a new model for Pattern Recognition (PR), namely, one that involves Chaotic Neural Networks (CNNs). To achieve this, we enhance the basic model proposed by Adachi [1], referred to as Adachi’s Chaotic Neural Network (ACNN). Although the ACNN has been shown to be chaotic, we prove that it also has the property that the degree of “chaos” can be controlled; decreasing the multiplicity of the eigenvalues of the underlying control system, we can effectively decrease the degree of chaos, and conversely increase the periodicity. We then show that such a Modified ACNN (M-ACNN) has the desirable property that it recognizes various input patterns. The way that this PR is achieved is by the system essentially sympathetically “resonating” with a finite periodicity whenever these samples are presented. In this paper, which follows its companion paper [2], we analyze the M-ACNN for its stability and algorithmic issues. This paper also includes more comprehensive experimental results.