Statistical Pattern Recognition Problems and the Multiple Classes Random Neural Network Model

The purpose of this paper is to describe the use of the multiple classes random neural network model to learn various statistical patterns. We propose a pattern recognition algorithm for the recognition of statistical patterns based upon the non-linear equations of the multiple classes random neural network model using gradient descent of a quadratic error function. In this case the classification errors are considered.

[1]  Erol Gelenbe,et al.  The Random Neural Network Model for Texture Generation , 1992, Int. J. Pattern Recognit. Artif. Intell..

[2]  José Aguilar.  An energy function for the random neural network , 2004, Neural Processing Letters.

[3]  Erol Gelenbe,et al.  G-Networks with Multiple Classes of Negative and Positive Customers , 1996, Theor. Comput. Sci..

[4]  Aguilar Jose.  Definition of an energy function for the random neural to solve optimization problems. , 1998, Neural networks : the official journal of the International Neural Network Society.

[5]  José Aguilar,et al.  Resolution of pattern recognition problems using a hybrid Genetic/Random Neural Network learning algorithm , 2005, Pattern Analysis and Applications.

[6]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Robert P. W. Duin,et al.  Handwritten digit recognition by combined classifiers , 1998, Kybernetika.

[8]  Erol Gelenbe,et al.  Learning in the Recurrent Random Neural Network , 1992, Neural Computation.

[9]  Erol Gelenbe,et al.  Stability of the Random Neural Network Model , 1990, Neural Computation.

[10]  Erol Gelenbe,et al.  Random Neural Networks with Negative and Positive Signals and Product Form Solution , 1989, Neural Computation.