Changes of Problem Representation
Theory and Experiments
Résumé
The performance of all reasoning systems crucially depends on problem representation: the same problem may be easy or difficult, depending on the way we describe it. Researchers in psychology and artificial intelligence have accumulated much evidence on the importance of appropriate representations for both human and artificial intelligence systems. The book proposes techniques for automatic improvement of problem representation, which are based on integration of multiple learning and problem-solving algorithms. It gives theoretical foundations of the proposed techniques, describes their implementation, and discusses empirical evidence of their utility.
Contents- Introduction
- Motivation
- Prodigy search
Description changers - Primary effects
- Abstraction
- Summary and extensions
Top-level control - Multiple representations
- Statistical selection
- Statistical extensions
- Summary and extensions
Empirical results - Machining Domains
- Sokoban Domain
- Extended Strips Domain
- Logistics Domain
- Concluding remarks
- References
L'auteur - Eugene Fink
Fink, Eugene, University of South Florida, Tampa, FL, USA
Caractéristiques techniques
| PAPIER | |
| Éditeur(s) | Springer |
| Auteur(s) | Eugene Fink |
| Parution | 07/11/2002 |
| Nb. de pages | 356 |
| Format | 16 x 24 |
| Couverture | Relié |
| Poids | 685g |
| Intérieur | Noir et Blanc |
| EAN13 | 9783790815238 |
Avantages Eyrolles.com
Consultez aussi
- Les meilleures ventes en Graphisme & Photo
- Les meilleures ventes en Informatique
- Les meilleures ventes en Construction
- Les meilleures ventes en Entreprise & Droit
- Les meilleures ventes en Sciences
- Les meilleures ventes en Littérature
- Les meilleures ventes en Arts & Loisirs
- Les meilleures ventes en Vie pratique
- Les meilleures ventes en Voyage et Tourisme
- Les meilleures ventes en BD et Jeunesse
