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)|
|Number of pages||8|
|Journal||Proceedings - IEEE Computer Society's International Computer Software & Applications Conference|
|State||Published - Dec 1 1989|
|Event||Proceedings of the Thirteenth Annual International Computer Software & Applications Conference - COMPSAC 89 - Orlando, FL, USA|
Duration: Sep 20 1989 → Sep 22 1989