Learning Theory and Experiments with Competitive Networks
Abstract
We apply the theory of Tishby, Levin, and Sol1a (TLS) to two problems. First we analyze an elementary problem for which we find the predictions consistent with conventional statistical results. Second we numerically examine the more realistic problem of training a competitive net to learn a probability density from samples. We find TLS useful for predicting average training behavior.
Cite
Text
Bilbro and van den Bout. "Learning Theory and Experiments with Competitive Networks." Neural Information Processing Systems, 1990.Markdown
[Bilbro and van den Bout. "Learning Theory and Experiments with Competitive Networks." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/bilbro1990neurips-learning/)BibTeX
@inproceedings{bilbro1990neurips-learning,
title = {{Learning Theory and Experiments with Competitive Networks}},
author = {Bilbro, Griff L. and van den Bout, David E.},
booktitle = {Neural Information Processing Systems},
year = {1990},
pages = {846-852},
url = {https://mlanthology.org/neurips/1990/bilbro1990neurips-learning/}
}