ML Anthology

Robust Classifiers Without Robust Features

Alan J. Katz, Michael T. Gately, Dean R. Collins
NeCo 1990 pp. 472-479
doi:10.1162/NECO.1990.2.4.472 /neco/1990/katz1990neco-robust/

Abstract

We develop a two-stage, modular neural network classifier and apply it to an automatic target recognition problem. The data are features extracted from infrared and TV images. We discuss the problem of robust classification in terms of a family of decision surfaces, the members of which are functions of a set of global variables. The global variables characterize how the feature space changes from one image to the next. We obtain rapid training times and robust classification with this modular neural network approach.

NeCo Semantic Scholar

Cite

Text

Katz et al. "Robust Classifiers Without Robust Features." Neural Computation, 1990. doi:10.1162/NECO.1990.2.4.472

Markdown

[Katz et al. "Robust Classifiers Without Robust Features." Neural Computation, 1990.](https://mlanthology.org/neco/1990/katz1990neco-robust/) doi:10.1162/NECO.1990.2.4.472

BibTeX

@article{katz1990neco-robust,
  title     = {{Robust Classifiers Without Robust Features}},
  author    = {Katz, Alan J. and Gately, Michael T. and Collins, Dean R.},
  journal   = {Neural Computation},
  year      = {1990},
  pages     = {472-479},
  doi       = {10.1162/NECO.1990.2.4.472},
  volume    = {2},
  url       = {https://mlanthology.org/neco/1990/katz1990neco-robust/}
}