A Novel Learning Algorithm for Feedforward Networks using Lyapunov Function Approach

Laxmidhar Behera*, Swagat Kumar, Awhan Patnaik

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference proceeding (ISBN)

1 Citation (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings of International Conference on Intelligent Sensing and Information Processing, ICISIP 2004
EditorsM. Palaniswami, C. Chandra Sekhar, G.K. Venayagamoorthy, S. Mohan, M.K. Ghantasala
Pages277-282
Number of pages6
Publication statusPublished - 4 May 2004
EventProceedings of International Conference on Intelligent Sensing and Information Processing, ICISIP 2004 - Chennai, India
Duration: 4 Jan 20047 Jan 2004

Publication series

NameProceedings of International Conference on Intelligent Sensing and Information Processing, ICISIP 2004

Conference

ConferenceProceedings of International Conference on Intelligent Sensing and Information Processing, ICISIP 2004
CountryIndia
CityChennai
Period4/01/047/01/04

Fingerprint Dive into the research topics of 'A Novel Learning Algorithm for Feedforward Networks using Lyapunov Function Approach'. Together they form a unique fingerprint.

Cite this