Improved ANN Algorithm Based on the Change of Search Direction

The essence of traditional ANN algorithm is to transfer the input-output problem of a group sample into a nonlinear programming problem. And it is a learning method to use iteration to work out weight problem along the negative gradient direction, but its convergence rate is slow and it is easy to fall into local minimum. Previously, there are many improved methods to solve the above-mentioned drawbacks by modifying the searching step size but there are few modified ANN algorithms by modifying the searching direction. In this paper, by studying the characteristics of the search direction of ANN Algorithm, there raises a new search direction, then an improved ANN algorithm based on the change of search direction is formed. The convergence rate of this new algorithm is much faster than the traditional ANN algorithm.