Abstract
In this paper we consider four alternative approaches to complexity control in feed-forward networks based respectively on architecture selection, regularization, early stopping, and training with noise. We show that there are close similarities between these approaches and we argue that, for most practical applications, the technique of regularization should be the method of choice.
| Original language | English |
|---|---|
| Title of host publication | Proceedings International Conference on Artificial Neural Networks ICANN'95 |
| Publisher | EC2 et Cie |
| Pages | 141-148 |
| Number of pages | 8 |
| ISBN (Print) | 2-910085-19-8 |
| Publication status | Unpublished - 1995 |
Bibliographical note
International Conference on Artificial Neural Networks ICANN'95.Keywords
- NCRG complexity control feed-forward networks architecture selection regularization early stopping training with noise