Title :
Simple adaptive momentum: new algorithm for training multilayer perceptrons
Author :
Bishop, J.M. ; Mitchell, R.J.
fDate :
9/1/1994 12:00:00 AM
Abstract :
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
Keywords :
convergence of numerical methods; feedforward neural nets; iterative methods; learning (artificial intelligence); adaptive momentum; iterations; multilayer perceptrons; neural nets; speed of convergence; training algorithm; training time;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19941014