Learning And Structuring Of Neural Networks Using Genetic Algorithm And Linear Programming

摘要

In this paper, we propose a method for generating neural networks using genetic algorithm and linear programming; the genetic algorithm is used to decide the structure of neural net, while the linear programming for learning. This method holds a feature that there is no parameter sensitive toAhe speed and the precision of learning unlike the usual backpropagation. The effectiveness of the method will be shown on the basis of several examples.