A Modified Conjugate Gradient Formula for Back Propagation Neural Network Algorithm
Abbas Y. Al Bayati, Najmaddin A. Sulaiman and Gulnar W. Sadiq
DOI : 10.3844/jcssp.2009.849.856
Journal of Computer Science
Volume 5, Issue 11
Problem statement: The Conjugate Gradient (CG) algorithm which usually used for solving nonlinear functions is presented and is combined with the modified Back Propagation (BP) algorithm yielding a new fast training multilayer algorithm. Approach: This study consisted of determination of new search directions by exploiting the information calculated by gradient descent as well as the previous search direction. The proposed algorithm improved the training efficiency of BP algorithm by adaptively modifying the initial search direction. Results: Performance of the proposed algorithm was demonstrated by comparing it with the Neural Network (NN) algorithm for the chosen test functions. Conclusion: The numerical results showed that number of iterations required by the proposed algorithm to converge was less than the both standard CG and NN algorithms. The proposed algorithm improved the training efficiency of BP-NN algorithms by adaptively modifying the initial search direction.
© 2009 Abbas Y. Al Bayati, Najmaddin A. Sulaiman and Gulnar W. Sadiq. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.