TY - GEN

T1 - A Novel Learning Algorithm for Feedforward Networks using Lyapunov Function Approach

AU - Behera, Laxmidhar

AU - Kumar, Swagat

AU - Patnaik, Awhan

PY - 2004/5/4

Y1 - 2004/5/4

N2 - This paper investigates a new learning algorithm (LFI) based on Lyapunov function for the training of feedforward neural networks. The proposed algorithm has an interesting parallel with the popular back-propagation algorithm where the fixed learning rate of the back-propgation algorithm is replaced by an adaptive learning rate computed using convergence theorem based on Lyapunov stability theory. Next, the proposed algorithm is modified (LF II) to allow smooth search in the weight space. The performance of the proposed algorithms is compared with back-propagation algorithm and extended Kalman filtering(EKF) on two bench-mark function approximations, XOR and 3-bit Parity. The comparisons are made in terms of learning iterations and computational time required for convergence. It is found that the proposed alogorithms (LF I and II) are faster in convergence than other two algorithms to attain same accuracy. Finally the comparison is made on a system identification problem where it is shown that the proposed algorithms can achieve better function approximation accuracy.

AB - This paper investigates a new learning algorithm (LFI) based on Lyapunov function for the training of feedforward neural networks. The proposed algorithm has an interesting parallel with the popular back-propagation algorithm where the fixed learning rate of the back-propgation algorithm is replaced by an adaptive learning rate computed using convergence theorem based on Lyapunov stability theory. Next, the proposed algorithm is modified (LF II) to allow smooth search in the weight space. The performance of the proposed algorithms is compared with back-propagation algorithm and extended Kalman filtering(EKF) on two bench-mark function approximations, XOR and 3-bit Parity. The comparisons are made in terms of learning iterations and computational time required for convergence. It is found that the proposed alogorithms (LF I and II) are faster in convergence than other two algorithms to attain same accuracy. Finally the comparison is made on a system identification problem where it is shown that the proposed algorithms can achieve better function approximation accuracy.

UR - http://www.scopus.com/inward/record.url?scp=1942535809&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1942535809&partnerID=8YFLogxK

M3 - Conference proceeding (ISBN)

AN - SCOPUS:1942535809

SN - 0780382439

T3 - Proceedings of International Conference on Intelligent Sensing and Information Processing, ICISIP 2004

SP - 277

EP - 282

BT - Proceedings of International Conference on Intelligent Sensing and Information Processing, ICISIP 2004

A2 - Palaniswami, M.

A2 - Chandra Sekhar, C.

A2 - Venayagamoorthy, G.K.

A2 - Mohan, S.

A2 - Ghantasala, M.K.

T2 - Proceedings of International Conference on Intelligent Sensing and Information Processing, ICISIP 2004

Y2 - 4 January 2004 through 7 January 2004

ER -