Supervised learning on large redundant training sets
Related Experiment Videos
1Computer Science Department, Arhus University, Denmark.
International Journal of Neural Systems
|March 1, 1993
Abstract:
Efficient supervised learning on large redundant training sets requires algorithms where the amount of computation involved in preparing each weight update is independent of the training set size. Offline algorithms like the standard conjugate gradient algorithms do not have this property while on-line algorithms like the stochastic backpropagation algorithm do. A new algorithm combining the good properties of off-line and on-line algorithms is introduced.
