HMM based Viterbi paths for rejection correction in a convolutional neural network classifier - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2005

HMM based Viterbi paths for rejection correction in a convolutional neural network classifier

Hubert Cecotti
  • Function : Author
  • PersonId : 830534
Szilárd Vajda
  • Function : Author
  • PersonId : 830136
Abdel Belaïd
  • Function : Author

Abstract

This paper presents a rejection strategy for a convolutional neural network. The method is based on Viterbi paths generated by a context based 2D stochastic model for rejected image correction. The rejection strategy is an important issue in neural network theory. The challenge is to find rules, which determine if an image is correctly classified or not. Applying strong rules leads to the rejection of many well-recognized patterns whereas weak rules do not always involve a strong decrease of erroneous patterns. We propose to use in several ways the knowledge of an external stochastic model so called NSHP-HMM (Non Symmetric Half-Plane Hidden Markov Model) for re-evaluating the rejected patterns.
No file

Dates and versions

inria-00000367 , version 1 (27-09-2005)

Identifiers

  • HAL Id : inria-00000367 , version 1

Cite

Hubert Cecotti, Szilárd Vajda, Abdel Belaïd. HMM based Viterbi paths for rejection correction in a convolutional neural network classifier. IAPR - TC3 International Workshop on Neural Networks and Learning in Document Recognition - NNLDAR 2005, Aug 2005, Seoul, Korea, pp.23-27. ⟨inria-00000367⟩
81 View
0 Download

Share

Gmail Facebook X LinkedIn More