Improving neural net convergence
Alder, M., Lim, S.G., Hadingham, P. and Attikiouzel, Y. (1992) Improving neural net convergence. Pattern Recognition Letters, 13 (5). pp. 331-338.
*Subscription may be required
This paper shows a certain equivalence between the 3-layer feed forward back-propagation neural net of Rumelhart et al. and the committee net of Nilsson. This is used to produce an improvement in the performance of the former. It is found that (a) the number of epochs taken is reduced by a factor of between 6 and 10, (b) the same taken is reduced by a factor of about 20, and (c) the net converges under conditions when the back-propagation algorithm is trapped in local minima and fails to converge.
|Publication Type:||Journal Article|
|Copyright:||© 1992 Published by Elsevier B.V.|
|Item Control Page|