Optimization of MLP/BP for character recognition using a modified alopex algorithm

Article type: Research Article

Authors: Shintani, Hirohito^{a; *} | Akutagawa, Masatake^a | Nagashino, Hirofumi^b | Pandya, Abhijit S.^c | Kinouchi, Yohsuke^a

Affiliations: [a] Faculty of Engineering, The University of Tokushima, 2-1, Minami-josanjima, Tokushima, 770-8506, Japan | [b] School of health sciences, The University of Tokushima, 3-18-15, Kuramoto, Tokushima, 770-8509, Japan | [c] Department of Computer Science and Engineering, Florida Atlantic University, Boca Raton, Florida 33431, USA

Correspondence: [*] Corresponding author. Tel./Fax: +81 88 656 7475; E-mail: hsintani@ee.tokushima-u.ac.jp

Abstract: It is difficult to determine the recognition mechanism in the neurons of a neural network trained for pattern recognition due to the non-linear nature of neural networks. This paper describes a recognition mechanism of a four-layer back propagation neural network using Alopex algorithm. We have developed a small-scale, four-layered neural network model for simple character recognition, which can recognize the patterns transformed by affined conversion. Alopex algorithm is an iterative and stochastic processing method, which was proposed for optimization of a given cost function. In this case the receptive fields of the neurons in the output layers are obtained using the Alopex algorithm.

Keywords: Neural network, Alopex algorithm, character recognition, intelligent systems

DOI: 10.3233/KES-2007-11602

Journal: International Journal of Knowledge-based and Intelligent Engineering Systems, vol. 11, no. 6, pp. 371-379, 2007