Abstract
Neural networks have traditionally been applied to recognition problems, and most learning algorithms are tailored to those problems. The authors discuss the requirements of learning for generalization, which is NP-complete and cannot be approached by traditional methods based on gradient descent. They present a stochastic learning algorithm based on simulated annealing in weight space. The convergence properties and feasibility of the algorithm are verified.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 664-671 |
| Number of pages | 8 |
| Journal | Proceedings - IEEE Computer Society's International Computer Software & Applications Conference |
| State | Published - 1989 |
| Event | Proceedings of the Thirteenth Annual International Computer Software & Applications Conference - COMPSAC 89 - Orlando, FL, USA Duration: Sep 20 1989 → Sep 22 1989 |