This paper deals with achieving chaotic Pattern Recognition (PR) using the Adachi Neural Network (AdNN), where the Neural Network (NN) has been modified in a random manner. The Adachi Neural Network is a fascinating NN which has been shown to possess chaotic properties, and to also demonstrate Associative Memory (AM) and Pattern Recognition (PR) characteristics. Variants of the AdNN have also been used to obtain other PR phenomena, and even blurring. An unsur-mountable problem associated with the AdNN and the variants referred to above, is that all of them require a quadratic number of computations. Earlier, in [1], we managed to reduce the computational cost significantly by merely using a linear number of computations by enforcing a Maximum Spanning Tree topology, and a gradient search method. However, in the sense of a NNs structure, very few networks possess a linearly connected topology. Instead, most of the “physical” networks including biological NNs and Internet networks have the properties of a complex network such as a random network, small-world network or a scale-free network. In this paper, we mainly consider the issue of how the network topology can be modified by involving randomized connections so as to render the new network much closer to “real” NNs. On the other hand, the newly obtained network still possesses strong PR characteristics. To achieves this, we first construct a random network by means of the E-R model and then address the problem of computing the weights for the new network. This is done in such a manner that the modified random connection-based NN has approximately the same input-output characteristics, and thus the new weights are themselves calculated using a gradient-based algorithm. Through a detailed experimental analysis, we show that the new random AdNN-like network possesses PR properties for appropriate settings. As far as we know, such a random AdNN has not been reported, and our present results are novel.

, , ,
6th International Conference on Chaotic Modeling and Simulation, CHAOS 2013
School of Computer Science

Qin, K. (Ke), & Oommen, J. (2013). Chaotic pattern recognition using the Adachi neural network modified in a random manner. In CHAOS 2013 - 6th Chaotic Modeling and Simulation International Conference, Proceedings (pp. 483–490).