Internal World Models and Supervised Learning
Abstract
Internal models of the environment have an important role to play in adaptive systems in general and are of particular importance for the supervised learning paradigm. In this paper we demonstrate that certain classical problems associated with the notion of the “teacher― in supervised learning can be solved by judicious use of learned internal models as components of the adaptive system. In particular, we show how supervised learning algorithms can be utilized in cases in which an unknown dynamical system intervenes between actions and desired outcomes.
Cite
Text
Jordan and Rumelhart. "Internal World Models and Supervised Learning." International Conference on Machine Learning, 1991. doi:10.1016/B978-1-55860-200-7.50018-0Markdown
[Jordan and Rumelhart. "Internal World Models and Supervised Learning." International Conference on Machine Learning, 1991.](https://mlanthology.org/icml/1991/jordan1991icml-internal/) doi:10.1016/B978-1-55860-200-7.50018-0BibTeX
@inproceedings{jordan1991icml-internal,
title = {{Internal World Models and Supervised Learning}},
author = {Jordan, Michael I. and Rumelhart, David E.},
booktitle = {International Conference on Machine Learning},
year = {1991},
pages = {70-74},
doi = {10.1016/B978-1-55860-200-7.50018-0},
url = {https://mlanthology.org/icml/1991/jordan1991icml-internal/}
}