In this paper a new procedure for the selection of pruning threshold in feedforward artificial neural networks (FANN) is presented. It is based on an evaluation of a local sensitivity index which has been previously calculated with respect to any single output of the network. Special emphasis has been given to a particular class of neural networks with multiple heterogeneous outputs. The effectiveness of the proposed method will be shown by the development of a neural architecture devoted to a specific multi-output inversion system. The proposed pruning technique provides criteria in deciding ‘‘when’’ and ‘‘how much’’ to prune the designed neural network.
Automatic generation of the optimum threshold for parameter weighted pruning in multiple heterogeneous output neural networks / A.Luchetta. - In: NEUROCOMPUTING. - ISSN 0925-2312. - STAMPA. - 71:(2008), pp. 3553-3560. [10.1016/j.neucom.2007.08.028]
Automatic generation of the optimum threshold for parameter weighted pruning in multiple heterogeneous output neural networks
LUCHETTA, ANTONIO
2008
Abstract
In this paper a new procedure for the selection of pruning threshold in feedforward artificial neural networks (FANN) is presented. It is based on an evaluation of a local sensitivity index which has been previously calculated with respect to any single output of the network. Special emphasis has been given to a particular class of neural networks with multiple heterogeneous outputs. The effectiveness of the proposed method will be shown by the development of a neural architecture devoted to a specific multi-output inversion system. The proposed pruning technique provides criteria in deciding ‘‘when’’ and ‘‘how much’’ to prune the designed neural network.File | Dimensione | Formato | |
---|---|---|---|
NC_luchetta_definitivo.pdf
Accesso chiuso
Tipologia:
Versione finale referata (Postprint, Accepted manuscript)
Licenza:
Tutti i diritti riservati
Dimensione
311.93 kB
Formato
Adobe PDF
|
311.93 kB | Adobe PDF | Richiedi una copia |
I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.