A Node Pruning Algorithm Based on a Fourier Amplitude Sensitivity Test Method - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Neural Networks Année : 2006

A Node Pruning Algorithm Based on a Fourier Amplitude Sensitivity Test Method

Résumé

In this paper, we propose a new pruning algorithm to obtain the optimal number of hidden units of a single layer of a fully connected neural network (NN). The technique relies on a global sensitivity analysis of model output. The relevance of the hidden nodes is determined by analysing the Fourier decomposition of the variance of the model output. Each hidden unit is assigned a ratio (the fraction of variance which the unit accounts for) that gives their ranking. This quantitative information therefore leads to a suggestion of the most favorable units to eliminate. Experimental results suggest that the method can be seen as an effective tool available to the user in controlling the complexity in NNs.
Fichier principal
Vignette du fichier
New_paper_CE839.pdf (1.06 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01067339 , version 1 (23-09-2014)

Identifiants

  • HAL Id : hal-01067339 , version 1

Citer

Philippe Lauret, Eric Fock, Thierry A. Mara. A Node Pruning Algorithm Based on a Fourier Amplitude Sensitivity Test Method. IEEE Transactions on Neural Networks, 2006, 17 (2), pp.273-293. ⟨hal-01067339⟩
259 Consultations
500 Téléchargements

Partager

Gmail Facebook X LinkedIn More