Title :
A new design method for the complex-valued multistate Hopfield associative memory
Author :
M.K. Muezzinoglu;C. Guzelis;J.M. Zurada
Author_Institution :
Dept. of Electr. Eng., Louisville Univ., KY, USA
Abstract :
A method to store each element of an integral memory set M /spl sub/ {1,2,...,K}/sup n/ as a fixed point into a complex-valued multistate Hopfield network is introduced. The method employs a set of inequalities to render each memory pattern as a strict local minimum of a quadratic energy landscape. Based on the solution of this system, it gives a recurrent network of n multistate neurons with complex and symmetric synaptic weights, which operates on the finite state space {1,2,...,K}/sup n/ to minimize this quadratic functional. Maximum number of integral vectors that can be embedded into the energy landscape of the network by this method is investigated by computer experiments. This paper also enlightens the performance of the proposed method in reconstructing noisy gray-scale images.
Keywords :
"Design methodology","Associative memory","Neurons","State-space methods","Gray-scale","Recurrent neural networks","Computational intelligence","Laboratories","Vectors","Computer networks"
Journal_Title :
IEEE Transactions on Neural Networks
DOI :
10.1109/TNN.2003.813844