ML Anthology

Effective Training of a Neural Network Character Classifier for Word Recognition

Larry S. Yaeger, Richard F. Lyon, Brandyn J. Webb
NeurIPS 1996 pp. 807-816
/neurips/1996/yaeger1996neurips-effective/

Abstract

We have combined an artificial neural network (ANN) character classifier with context-driven search over character segmentation, word segmentation, and word recognition hypotheses to provide robust recognition of hand-printed English text in new models of Apple Computer's Newton MessagePad. We present some innovations in the training and use of ANNs al; character classifiers for word recognition, including normalized output error, frequency balancing, error emphasis, negative training, and stroke warping. A recurring theme of reducing a priori biases emerges and is discussed.

PDF NeurIPS Semantic Scholar

Cite

Text

Yaeger et al. "Effective Training of a Neural Network Character Classifier for Word Recognition." Neural Information Processing Systems, 1996.

Markdown

[Yaeger et al. "Effective Training of a Neural Network Character Classifier for Word Recognition." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/yaeger1996neurips-effective/)

BibTeX

@inproceedings{yaeger1996neurips-effective,
  title     = {{Effective Training of a Neural Network Character Classifier for Word Recognition}},
  author    = {Yaeger, Larry S. and Lyon, Richard F. and Webb, Brandyn J.},
  booktitle = {Neural Information Processing Systems},
  year      = {1996},
  pages     = {807-816},
  url       = {https://mlanthology.org/neurips/1996/yaeger1996neurips-effective/}
}