Combined Neural Network and Rule-Based Framework for Probabilistic Pattern Recognition and Discovery

Abstract

A combined neural network and rule-based approach is suggested as a general framework for pattern recognition. This approach enables unsu(cid:173) pervised and supervised learning, respectively, while providing probability estimates for the output classes. The probability maps are utilized for higher level analysis such as a feedback for smoothing over the output la(cid:173) bel maps and the identification of unknown patterns (pattern "discovery"). The suggested approach is presented and demonstrated in the texture - analysis task. A correct classification rate in the 90 percentile is achieved for both unstructured and structured natural texture mosaics. The advan(cid:173) tages of the probabilistic approach to pattern analysis are demonstrated.

Cite

Text

Greenspan et al. "Combined Neural Network and Rule-Based Framework for Probabilistic Pattern Recognition and Discovery." Neural Information Processing Systems, 1991.

Markdown

[Greenspan et al. "Combined Neural Network and Rule-Based Framework for Probabilistic Pattern Recognition and Discovery." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/greenspan1991neurips-combined/)

BibTeX

@inproceedings{greenspan1991neurips-combined,
  title     = {{Combined Neural Network and Rule-Based Framework for Probabilistic Pattern Recognition and Discovery}},
  author    = {Greenspan, Hayit K. and Goodman, Rodney and Chellappa, Rama},
  booktitle = {Neural Information Processing Systems},
  year      = {1991},
  pages     = {444-451},
  url       = {https://mlanthology.org/neurips/1991/greenspan1991neurips-combined/}
}