Adaptive Mixtures of Local Experts

Adaptive Mixtures of Local Experts. Jacobs, R. A., Jordan, M. I., Nowlan, S. J., & Hinton, G. E. Neural Computation, 3(1):79–87, February, 1991.

Paper doi abstract bibtex

We present a new supervised learning procedure for systems composed of many separate networks, each of which learns to handle a subset of the complete set of training cases. The new procedure can be viewed either as a modular version of a multilayer supervised network, or as an associative version of competitive learning. It therefore provides a new link between these two apparently different approaches. We demonstrate that the learning procedure divides up a vowel discrimination task into appropriate subtasks, each of which can be solved by a very simple expert network.

@article{jacobs_adaptive_1991,
	title = {Adaptive {Mixtures} of {Local} {Experts}},
	volume = {3},
	issn = {0899-7667, 1530-888X},
	url = {https://direct.mit.edu/neco/article/3/1/79-87/5560},
	doi = {10.1162/neco.1991.3.1.79},
	abstract = {We present a new supervised learning procedure for systems composed of many separate networks, each of which learns to handle a subset of the complete set of training cases. The new procedure can be viewed either as a modular version of a multilayer supervised network, or as an associative version of competitive learning. It therefore provides a new link between these two apparently different approaches. We demonstrate that the learning procedure divides up a vowel discrimination task into appropriate subtasks, each of which can be solved by a very simple expert network.},
	language = {en},
	number = {1},
	urldate = {2025-01-25},
	journal = {Neural Computation},
	author = {Jacobs, Robert A. and Jordan, Michael I. and Nowlan, Steven J. and Hinton, Geoffrey E.},
	month = feb,
	year = {1991},
	pages = {79--87},
}

Downloads: 0