High Performance Convolutional Neural Networks for Document Processing - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2006

High Performance Convolutional Neural Networks for Document Processing

Kumar Chellapilla
  • Function : Author
  • PersonId : 836517
Sidd Puri
  • Function : Author
  • PersonId : 836518
Patrice Simard
  • Function : Author
  • PersonId : 836519


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.
Fichier principal
Vignette du fichier
p1038112283956.pdf (133.55 Ko) Télécharger le fichier

Dates and versions

inria-00112631 , version 1 (09-11-2006)


  • HAL Id : inria-00112631 , version 1


Kumar Chellapilla, Sidd Puri, Patrice Simard. High Performance Convolutional Neural Networks for Document Processing. Tenth International Workshop on Frontiers in Handwriting Recognition, Université de Rennes 1, Oct 2006, La Baule (France). ⟨inria-00112631⟩


7267 View
32813 Download


Gmail Facebook X LinkedIn More