Kim Weon Ook, Cho Yong Hyun, Kim Young Il, Kang In Ku

The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 4, No. 11, pp. 2769-2779, Nov. 1997
10.3745/KIPSTE.1997.4.11.2769,   PDF Download:

Abstract

This paper proposes an efficient method for improving the training performance of the neural networks using a hybrid of conjugate gradient backpropagation algorithm and dynamic tunneling backpropagation algorithm. The conjugate gradient backpropagation algorithm, which is the fast gradient algorithm, is applied for high speed optimization. The dynamic tunneling backpropagation algorithm, which is the deteministic method with tunneling phenomenon, is applied for global optimization. Converging to the local minima by using the conjugate gradient backpropagation algorithm, the new initial point for escaping the local minima is estimated by dynamic tunneling backpropagation algorithm. The proposed method has been applied to the parity check and to pattern classfication. The simulation results show that the performance of proposed method is superior to those of gradient descent backpropagation algorithm and a hybrid of gradient descent and dynamic thunneling backpropagation algorithm, and the new algorithm converges more often to the global minima than gradient descent backpropagation algorithm.

Statistics
Cite this article