Simplifying ConvNets for Fast Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2012

Simplifying ConvNets for Fast Learning

Franck Mamalet

Résumé

In this paper, we propose different strategies for simplifying filters, used as feature extractors, to be learnt in convolutional neural networks (ConvNets) in order to modify the hypothesis space, and to speed-up learning and processing times. We study two kinds of filters that are known to be computationally efficient in feed-forward processing: fused convolution/sub-sampling filters, and separable filters. We compare the complexity of the back-propagation algorithm on ConvNets based on these different kinds of filters. We show that using these filters allows to reach the same level of recognition performance as with classical ConvNets for handwritten digit recognition, up to 3.3 times faster.
Fichier non déposé

Dates et versions

hal-01353039 , version 1 (10-08-2016)

Identifiants

Citer

Franck Mamalet, Christophe Garcia. Simplifying ConvNets for Fast Learning. International Conference on Artificial Neural Networks (ICANN 2012), Sep 2012, Lausanne, Switzerland, Switzerland. pp.58-65, ⟨10.1007/978-3-642-33266-1_8⟩. ⟨hal-01353039⟩
114 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More