Active Learning with Neural Networks

Schöner, Holger

by Holger Schöner

Abstract:

This paper is a survey over the area of active learning algorithms for supervised Neural Networks. These algorithms are concerned with the selection of informative examples to be included into the training set used for learning. After an introduction into the field and the motives for its development, three practical algorithms will be introduced. These are a network function inversion algorithm, one which searches for separating hyperplanes in input space, and the “Query by Committee” algorithm, which accepts new examples only if they provide new information. The last part of this paper explains a theoretical framework to deal with active learning algorithms, deriving results about their behavior from two examples.

Reference:

Active Learning with Neural Networks (Holger Schöner), Technical report, University of Colorado at Boulder, Department of Computer Science, 1998. (Masters Comprehensive Examination)

Bibtex Entry:

@techreport{schoner_active_1998,
	address = {Boulder, {CO}, {USA}},
	type = {Masters Comprehensive Examination},
	title = {Active Learning with Neural Networks},
	abstract = {This paper is a survey over the area of active learning algorithms for supervised Neural Networks. These algorithms
are concerned with the selection of informative examples to be included into the training set used for learning.
After an introduction into the field and the motives for its development, three practical algorithms will be introduced.
These are a network function inversion algorithm, one which searches for separating hyperplanes in input space, and
the “Query by Committee” algorithm, which accepts new examples only if they provide new information. The last
part of this paper explains a theoretical framework to deal with active learning algorithms, deriving results about
their behavior from two examples.},
	institution = {University of Colorado at Boulder, Department of Computer Science},
	author = {Schöner, Holger},
	month = feb,
	year = {1998},
	note = {Masters Comprehensive Examination},
	keywords = {active learning},
	pages = {20},
	xfile = {download/publications/}
}