Abstract
We study the effect of two types of noise, data noise and model noise, in an on-line gradient-descent learning scenario for general two-layer student network with an arbitrary number of hidden units. Training examples are randomly drawn input vectors labeled by a two-layer teacher network with an arbitrary number of hidden units. Data is then corrupted by Gaussian noise affecting either the output or the model itself. We examine the effect of both types of noise on the evolution of order parameters and the generalization error in various phases of the learning process.
| Original language | English |
|---|---|
| Pages (from-to) | 260-266 |
| Number of pages | 7 |
| Journal | Advances in Neural Information Processing Systems |
| Volume | 9 |
| Publication status | Published - 1996 |
| Event | 10th Annual Conference on Neural Information Processing Systems, NIPS 1996 - Denver, CO, United Kingdom Duration: 2 Dec 1996 → 5 Dec 1996 |
Bibliographical note
Copiright of Massachusetts Institute of Technology Press (MIT Press)Keywords
- noise
- data noise
- model noise
- gradient-descent learning
- vectors
- gaussian noise
- error