An application of genetic algorithms to evolve Hopfield type optimum network architectures for object extraction

Genetic Algorithms (GAs) have been used to evolve Hopfield type optimum neural network architectures for object background classification. Each chromosome of the GA represents an architecture. The initial population is set randomly. The energy value at the converged state of each network is taken as its fitness. The best chromosome of the final generation is taken to be the optimum network configuration. The evolved networks are found to have less (compared to the corresponding fixed fully connected version) connectivity for providing comparable outputs