Pairwise Neural Network Classifiers with Probabilistic Outputs

Abstract

Multi-class classification problems can be efficiently solved by partitioning the original problem into sub-problems involving only two classes: for each pair of classes, a (potentially small) neural network is trained using only the data of these two classes. We show how to combine the outputs of the two-class neural networks in order to obtain posterior probabilities for the class decisions. The resulting probabilistic pairwise classifier is part of a handwriting recognition system which is currently applied to check reading. We present results on real world data bases and show that, from a practical point of view, these results compare favorably to other neural network approaches.

Cite

Text

Price et al. "Pairwise Neural Network Classifiers with Probabilistic Outputs." Neural Information Processing Systems, 1994.

Markdown

[Price et al. "Pairwise Neural Network Classifiers with Probabilistic Outputs." Neural Information Processing Systems, 1994.](https://mlanthology.org/neurips/1994/price1994neurips-pairwise/)

BibTeX

@inproceedings{price1994neurips-pairwise,
  title     = {{Pairwise Neural Network Classifiers with Probabilistic Outputs}},
  author    = {Price, David and Knerr, Stefan and Personnaz, Léon and Dreyfus, Gérard},
  booktitle = {Neural Information Processing Systems},
  year      = {1994},
  pages     = {1109-1116},
  url       = {https://mlanthology.org/neurips/1994/price1994neurips-pairwise/}
}