Keywords
neural network, learning problems, implicit negatives, classification
Abstract
Classification problems with output class overlap create problems for standard neural network approaches. We present a modification of a simple feed-forward neural network that is capable of learning problems with output overlap, including problems exhibiting hierarchical class structures in the output. Our method of applying weakened implicit negatives to address overlap and ambiguity allows the algorithm to learn a large portion of the hierarchical structure from very incomplete data. Our results show an improvement of approximately 58% over a standard backpropagation network on the hierarchical problem.
Original Publication Citation
Stephen Whiting and Dan Ventura, "Learning Multiple Correct Classifications from Incomplete Data using Weakened Implicit Negatives", Proceedings of the International Joint Conference on Neural Networks, pp. 2953-2958, July 24.
BYU ScholarsArchive Citation
Ventura, Dan A. and Whiting, Stephen, "Learning Multiple Correct Classifications from Incomplete Data using Weakened Implicit Negatives" (2004). Faculty Publications. 433.
https://scholarsarchive.byu.edu/facpub/433
Document Type
Peer-Reviewed Article
Publication Date
2004-07-01
Permanent URL
http://hdl.lib.byu.edu/1877/2526
Publisher
IEEE
Language
English
College
Physical and Mathematical Sciences
Department
Computer Science
Copyright Status
© 2004 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Copyright Use Information
http://lib.byu.edu/about/copyright/