Back Propagation and its variations are widely used as methods for training artificial neural networks. One such variation, Resilient Back Propagation (RPROP), has proven to be one of the best in terms of speed of convergence. Our SARPROP enhancement, based on Simulated Annealing, is described in this paper and is shown to increase the rate of convergence for some problems. The extension involv...

A recurrent neural network is considered that can retrieve a collection of patterns, as well as slightly perturbed versions of this ‘pure’ set of patterns via fixed points of its dynamics. By replacing the set of dynamical constraints, i.e., the fixed point equations, by an extended collection of fixed-point-like equations, analytical expressions are found for the weights wij(b) of the net, whi...

the expected revenue we obtain given that nest i is selected is Ri(wi) = P j∈N wij (κij−ηij logwij) P j∈N wij , where M = {1, . . . ,m}, N = {1, . . . , n} and γi ∈ [0, 1] measures product dissimilarity within nests. Due to a one-to-one relationship, control of the preference weights equates to control of the prices κij−ηij logwij , where 1/ηij represents product price sensitivity and κij/ηij r...

This paper discusses fuzzification of crisp domains into fuzzy classes providing fuzzy domains. Relationship between two fuzzy domains, Xi and Xj , is represented by a matrix, wij . If Xi and Xj have n and m elements of fuzzy data, respectively, then wij is n × m matrix. Our primary goal in this paper is to generate and provide some formulas for predicting interval probability in the relation t...

This paper discusses fuzzification of crisp domains into fuzzy classes providing fuzzy domains. Relationship between two fuzzy domains, Xi and Xj , is represented by a matrix, wij . If Xi and Xj have n and m elements of fuzzy data, respectively, then wij is n × m matrix. The primary goal of the paper is to generate and provide some formulas for predicting interval probability in the relation to...