Abstract
The performance of seven minimization algorithms are compared on five neural network problems. These include a variable-step-size algorithm, conjugate gradient, and several methods with explicit analytic or numerical approximations to the Hessian.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the conference on Advances in neural information processing systems 3 |
| Editors | R. Lippmann, J. Moody, D. Touretzky |
| Place of Publication | San Francisco, CA, USA |
| Publisher | Morgan Kaufmann |
| Pages | 977-983 |
| Number of pages | 7 |
| Volume | 3 |
| ISBN (Print) | 1-55860-184-8 |
| Publication status | Published - 1990 |
| Event | Advances in Neural Information Processing Systems 3 - Duration: 1 Jan 1990 → 1 Jan 1990 |
Conference
| Conference | Advances in Neural Information Processing Systems 3 |
|---|---|
| Period | 1/01/90 → 1/01/90 |
Bibliographical note
© The AuthorKeywords
- minimization algorithms
- neural network
- Hessian
Fingerprint
Dive into the research topics of 'Time trials on second-order and variable-learning-rate algorithms'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver