Simple adaptive momentum: new algorithm for training multilayer perceptrons

Swanston, D. J., Bishop, J. M. and Mitchell, R. J. (1994) Simple adaptive momentum: new algorithm for training multilayer perceptrons. Electronics Letters, 30 (18). pp. 1498-1500. ISSN 0013-5194 doi: 10.1049/el:19941014

Abstract/Summary

The speed of convergence while training is an important consideration in the use of neural nets. The authors outline a new training algorithm which reduces both the number of iterations and training time required for convergence of multilayer perceptrons, compared to standard back-propagation and conjugate gradient descent algorithms.

Item Type	Article
URI	https://reading-clone.eprints-hosting.org/id/eprint/18869
Item Type	Article
Refereed	Yes
Divisions	Science > School of Mathematical, Physical and Computational Sciences > Department of Computer Science
Uncontrolled Keywords	adaptive momentum, iterations, multilayer perceptrons, neural nets, speed of convergence, training algorithm, training time
Publisher	Institution of Engineering and Technology (IET)
Download/View statistics	View download statistics for this item