CINECA IRIS Institutional Research Information System
IRIS è la soluzione IT che facilita la raccolta e la gestione dei dati relativi alle attività e ai prodotti della ricerca. Fornisce a ricercatori, amministratori e valutatori gli strumenti per monitorare i risultati della ricerca, aumentarne la visibilità e allocare in modo efficace le risorse disponibili.
EnglishGradient descent learning algorithms (namely backpropagation and weight perturbation) can significantly increase their classification performances by adopting a local and adaptive learning rate management approach. We present the results of the comparison of the classification performance of the two algorithms in a tough application: quality control analysis in the steel industry. The feedforward network is hierarchically organized (i.e. tree of multilayer perceptrons). The comparison has been performed starting from the same operating conditions (i.e. network topology, stopping criterion, etc.): the results show that the probability of correct classification is significantly better for the weight perturbation algorithm
Scheda prodotto non validato
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo
| Titolo: | Evaluation of gradient descent learning alghorithm with an Adaptive Local Rate Technique for Hierarchical Feed Forward Architectures | |
| Autori: | ||
| Data di pubblicazione: | 2000 | |
| Abstract: | Gradient descent learning algorithms (namely backpropagation and weight perturbation) can significantly increase their classification performances by adopting a local and adaptive learning rate management approach. We present the results of the comparison of the classification performance of the two algorithms in a tough application: quality control analysis in the steel industry. The feedforward network is hierarchically organized (i.e. tree of multilayer perceptrons). The comparison has been performed starting from the same operating conditions (i.e. network topology, stopping criterion, etc.): the results show that the probability of correct classification is significantly better for the weight perturbation algorithm | |
| Handle: | http://hdl.handle.net/11567/201475 | |
| ISBN: | 9780769506197 | |
| Appare nelle tipologie: | 04.01 - Contributo in atti di convegno |
File in questo prodotto:
http://hdl.handle.net/11567/201475
Copyright © 2022