| Titre : | Combining artificial neural nets : ensemble and modular multi-net systems |
| Auteurs : | A. Sharkey |
| Type de document : | texte imprimé |
| Editeur : | London : Springer-Verlag, 1999 |
| Collection : | Perspectives in neural computing |
| ISBN/ISSN/EAN : | 978-1-85233-004-0 |
| Format : | 1 vol. (298 p.) / 24 cm |
| Langues originales: | |
| Index. décimale : | 006.32 (Réseaux neuronaux) |
| Catégories : |
Ouvrages > Généralités (ouvrages généraux), information, informatique > Informatique |
| Mots-clés: | Réseaux de neurones (Informatique) Neural networks (Computer science) |
| Résumé : |
This volume, written by leading researchers, presents methods of combining neural nets to improve their performance. The techniques include ensemble-based approaches, where a variety of methods are used to create a set of different nets trained on the same task, and modular approaches, where a task is decomposed into simpler problems. The techniques are also accompanied by an evaluation of their relative effectiveness and their application to a variety of problems. |
| Note de contenu : |
Sommaire: 1- Multi-net systems. 2- Combining predictors. 3- Boosting using neural networks. 4- A genetic algorithm approach for creating neural network ensembles. 5- Treating harmful collinearity in neural network ensembles. 6- Linear and order statistics combiners for pattern classification. 7- Variance reduction via noise and bias constraints. 8- A comparison of visual cue combination models. 9- Model selection of combined neural nets for speech recognition. 10- Self-organised modular neural networks for encoding data. 11- Mixtures of X. |
| Côte titre : |
S8/49961-49963 |
Exemplaires (3)
| Cote | Support | Localisation | Disponibilité |
|---|---|---|---|
| S8/49961 | Livre | Bibliothèque centrale | Disponible |
| S8/49962 | Livre | Bibliothèque centrale | Disponible |
| S8/49963 | Livre | Bibliothèque centrale | Disponible |
Accueil
