CINECA IRIS Institutional Research Information System
IRIS è l’archivio della produzione scientifica della Fondazione Bruno Kessler.
EnglishThis report introduces a novel algorithm to learn the width of non-linear activation functions (of arbitrary analytical form) in layered networks. The algorithm is based on a steepest gradient-descent technique, and relies on the inductive proof of a theorem that involves the novel concept of expansion function of the activation associated to a given unit of the neural net. Experimental results obtained in a speaker nomalization task with a mixture of Multilayer Perceptron show a dramatic improvement of performance with respect to the standard Back-Propagation training
Scheda prodotto non validato
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte di FBK.
| Titolo: | Learning the Width of Activations in Neural Networks | |
| Autori: | ||
| Data di pubblicazione: | 1996 | |
| Abstract: | This report introduces a novel algorithm to learn the width of non-linear activation functions (of arbitrary analytical form) in layered networks. The algorithm is based on a steepest gradient-descent technique, and relies on the inductive proof of a theorem that involves the novel concept of expansion function of the activation associated to a given unit of the neural net. Experimental results obtained in a speaker nomalization task with a mixture of Multilayer Perceptron show a dramatic improvement of performance with respect to the standard Back-Propagation training | |
| Handle: | http://hdl.handle.net/11582/1296 | |
| Appare nelle tipologie: | 5.12 Altro |
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Utilizza questo identificativo per citare o creare un link a questo documento:
http://hdl.handle.net/11582/1296
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
Copyright © 2021