Rejection strategy for Convolutional Neural Network by adaptive topology applied to handwritten digits recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2005

Rejection strategy for Convolutional Neural Network by adaptive topology applied to handwritten digits recognition

Hubert Cecotti
  • Function : Author
  • PersonId : 830534
Abdel Belaïd
  • Function : Author

Abstract

In this paper, we propose a rejection strategy for convolutional neural network models. The purpose of this work is to adapt the network's topology in function of the geometrical error. A self-organizing map is used to change the links between the layers leading to a geometric image transformation occurring directly inside the network. Instead of learning all the possible deformation of a pattern, ambiguous patterns are rejected and the network's topology is modified in function of their geometric errors thanks to a specialized self-organizing map. Our objective is to show how an adaptive topology, without a new learning, can improve the recognition of rejected patterns in the case of handwritten digits.
No file

Dates and versions

inria-00000362 , version 1 (27-09-2005)

Identifiers

  • HAL Id : inria-00000362 , version 1

Cite

Hubert Cecotti, Abdel Belaïd. Rejection strategy for Convolutional Neural Network by adaptive topology applied to handwritten digits recognition. 8th International Conference in Document Analysis and Recognition - ICDAR'05, Aug 2005, Seoul, Korea, pp.765-769. ⟨inria-00000362⟩
181 View
0 Download

Share

Gmail Facebook X LinkedIn More