A Framework for the Cooperation of Learning Algorithms
Abstract
We introduce a framework for training architectures composed of several modules. This framework, which uses a statistical formulation of learning systems, provides a unique formalism for describing many classical connectionist algorithms as well as complex systems where several algorithms interact. It allows to design hybrid systems which combine the advantages of connectionist algorithms as well as other learning algorithms.
Cite
Text
Bottou and Gallinari. "A Framework for the Cooperation of Learning Algorithms." Neural Information Processing Systems, 1990.Markdown
[Bottou and Gallinari. "A Framework for the Cooperation of Learning Algorithms." Neural Information Processing Systems, 1990.](https://mlanthology.org/neurips/1990/bottou1990neurips-framework/)BibTeX
@inproceedings{bottou1990neurips-framework,
title = {{A Framework for the Cooperation of Learning Algorithms}},
author = {Bottou, Léon and Gallinari, Patrick},
booktitle = {Neural Information Processing Systems},
year = {1990},
pages = {781-788},
url = {https://mlanthology.org/neurips/1990/bottou1990neurips-framework/}
}