ML Anthology

Feature Extraction Using an Unsupervised Neural Network

Nathan Intrator
NeCo 1992 pp. 98-107
doi:10.1162/NECO.1992.4.1.98 /neco/1992/intrator1992neco-feature/

Abstract

A novel unsupervised neural network for dimensionality reduction that seeks directions emphasizing multimodality is presented, and its connection to exploratory projection pursuit methods is discussed. This leads to a new statistical insight into the synaptic modification equations governing learning in Bienenstock, Cooper, and Munro (BCM) neurons (1982). The importance of a dimensionality reduction principle based solely on distinguishing features is demonstrated using a phoneme recognition experiment. The extracted features are compared with features extracted using a backpropagation network.

NeCo Semantic Scholar

Cite

Text

Intrator. "Feature Extraction Using an Unsupervised Neural Network." Neural Computation, 1992. doi:10.1162/NECO.1992.4.1.98

Markdown

[Intrator. "Feature Extraction Using an Unsupervised Neural Network." Neural Computation, 1992.](https://mlanthology.org/neco/1992/intrator1992neco-feature/) doi:10.1162/NECO.1992.4.1.98

BibTeX

@article{intrator1992neco-feature,
  title     = {{Feature Extraction Using an Unsupervised Neural Network}},
  author    = {Intrator, Nathan},
  journal   = {Neural Computation},
  year      = {1992},
  pages     = {98-107},
  doi       = {10.1162/NECO.1992.4.1.98},
  volume    = {4},
  url       = {https://mlanthology.org/neco/1992/intrator1992neco-feature/}
}