Title :
Novel fast training algorithm for multilayer feedforward neural network
Author :
Park, D.-J. ; Jun, B.-E. ; Kim, Jung-Ho
Author_Institution :
Dept. of Electr. Eng., Korea Adv. Inst. of Sci. & Technol., Taejon, South Korea
fDate :
3/12/1992 12:00:00 AM
Abstract :
A new fast learning algorithm for a multilayer feedforward neural network is presented. The new algorithm, based on an innovative variable step size and gradient averaging, has excellent properties to overcome major drawbacks of the backpropagation algorithm and shows high convergence speed. The improved performance of new algorithm in comparison with other algorithms is verified via computer simulations.
Keywords :
convergence; learning systems; neural nets; backpropagation algorithm; computer simulations; convergence speed; fast learning algorithm; gradient averaging; multilayer feedforward neural network; variable step size;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19920343
