Combining Multilayer Networks to Combine Learning

Bax, Eric (1997) Combining Multilayer Networks to Combine Learning. Technical Report. California Institute of Technology. [CaltechCSTR:1997.cs-tr-98-01]

Full text available as:

	Postscript - Requires a viewer, such as GhostView
	Other (Adobe PDF (4.24MB))

Abstract

This paper explores methods to combine networks, implementations of network combination on multicomputers, and applications of network combination. We divide the network combination process into two steps. First, a matching algorithm rearranges the networks so that corresponding weights in the networks being combined play corresponding roles in the networks' functions. Then a proportioning algorithm chooses a convex combination of the matched networks. The combination network is a weight-by-weight convex combination of the matched networks. This paper begins by examining combinations of pairs of networks. Matching and proportioning algorithms are developed, analyzed, implemented, and tested. Next, algorithms are developed to combine several networks. Then the combination process is poked and prodded to explore its nature, its utility, and its limits.

EPrint Type:	Monograph (Technical Report)
Subjects:	All Records
ID Code:	181
Deposited By:	Caltech Library System
Deposited On:	30 April 2001
Record Number:	CaltechCSTR:1997.cs-tr-98-01
Official Persistent URL:	http://resolver.caltech.edu/CaltechCSTR:1997.cs-tr-98-01
Usage Policy:	You are granted permission for individual, educational, research and non-commercial reproduction, distribution, display and performance of this work in any format.

Archive Staff Only: edit this record