ML Anthology

Learning to Categorize Objects Using Temporal Coherence

Suzanna Becker
NeurIPS 1992 pp. 361-368
/neurips/1992/becker1992neurips-learning/

Abstract

The invariance of an objects' identity as it transformed over time provides a powerful cue for perceptual learning. We present an un(cid:173) supervised learning procedure which maximizes the mutual infor(cid:173) mation between the representations adopted by a feed-forward net(cid:173) work at consecutive time steps. We demonstrate that the network can learn, entirely unsupervised, to classify an ensemble of several patterns by observing pattern trajectories, even though there are abrupt transitions from one object to another between trajecto(cid:173) ries. The same learning procedure should be widely applicable to a variety of perceptual learning tasks.

PDF NeurIPS Semantic Scholar

Cite

Text

Becker. "Learning to Categorize Objects Using Temporal Coherence." Neural Information Processing Systems, 1992.

Markdown

[Becker. "Learning to Categorize Objects Using Temporal Coherence." Neural Information Processing Systems, 1992.](https://mlanthology.org/neurips/1992/becker1992neurips-learning/)

BibTeX

@inproceedings{becker1992neurips-learning,
  title     = {{Learning to Categorize Objects Using Temporal Coherence}},
  author    = {Becker, Suzanna},
  booktitle = {Neural Information Processing Systems},
  year      = {1992},
  pages     = {361-368},
  url       = {https://mlanthology.org/neurips/1992/becker1992neurips-learning/}
}