Optimization of neural network topology and information content using Boltzmann methods

A method for optimizing networks that focuses on network topology and information content is presented. The authors have studied change in the network topology and its effects on information content dynamically during the optimization of the network. The changes in the network topology were achieved by altering the number of weights. The primary optimization was scaled by the conjugate gradient method and the secondary technique of optimization was a Boltzmann method. The findings demonstrate that for a difficult character recognition problem the number of weights in a fully connected network can be reduced by 90.3% with a temperature of 0.55 while achieving training and testing of identical accuracies