High Performance Convolutional Neural Networks for Document Processing

Abstract : Convolutional neural networks (CNNs) are well known for producing state-of-the-art recognizers for document processing [1]. However, they can be difficult to implement and are usually slower than traditional multi-layer perceptrons (MLPs). We present three novel approaches to speeding up CNNs: a) unrolling convolution, b) using BLAS (basic linear algebra subroutines), and c) using GPUs (graphic processing units). Unrolled convolution converts the processing in each convolutional layer (both forward-propagation and back-propagation) into a matrix-matrix product. The matrix-matrix product representation of CNNs makes their implementation as easy as MLPs. BLAS is used to efficiently compute matrix products on the CPU. We also present a pixel shader based GPU implementation of CNNs. Results on character recognition problems indicate that unrolled convolution with BLAS produces a dramatic 2.4X−3.0X speedup. The GPU implementation is even faster and produces a 3.1X−4.1X speedup.
Type de document :
Communication dans un congrès
Guy Lorette. Tenth International Workshop on Frontiers in Handwriting Recognition, Oct 2006, La Baule (France), Suvisoft, 2006
Liste complète des métadonnées

Littérature citée [5 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00112631
Contributeur : Anne Jaigu <>
Soumis le : jeudi 9 novembre 2006 - 13:47:33
Dernière modification le : jeudi 9 novembre 2006 - 16:43:26
Document(s) archivé(s) le : mardi 6 avril 2010 - 21:59:52

Identifiants

  • HAL Id : inria-00112631, version 1

Collections

Citation

Kumar Chellapilla, Sidd Puri, Patrice Simard. High Performance Convolutional Neural Networks for Document Processing. Guy Lorette. Tenth International Workshop on Frontiers in Handwriting Recognition, Oct 2006, La Baule (France), Suvisoft, 2006. 〈inria-00112631〉

Partager

Métriques

Consultations de la notice

3462

Téléchargements de fichiers

17599