Simultaneous node pruning of input and hidden layers using genetic algorithms

In optimizing the neural network structure, there are two methods: the pruning scheme and the constructive scheme. This paper uses the pruning scheme to optimize neural network structure. The genetic algorithm is used to find out the optimum node pruning. In the conventional researches, the input and hidden layers were optimized separately. On the contrary we attempted to optimize the two layers simultaneously by encoding two layers in a chromosome. The offspring networks inherit the weights from the parent. For learning, we used the existing error back-propagation algorithm. In our experiment with various databases from UCI Machine Learning Repository, we could get the peak performance when the network size was reduced by about 8~25%. As a result of t-test the proposed method was shown to have a better performance, compared with other pruning or construction methods.