N-Learners Problem: Fusion of Concepts

Nageswara S.V. Rao, E. M. Oblow, Charles W. Glover, Gunar E. Liepins

Research output: Contribution to journalArticlepeer-review

18 Scopus citations

Abstract

Given N learners each capable of learning concepts (subsets) in the sense of Valiant, we are interested in combining them using a single fuser, We consider two cases. In open fusion the fuser is given the sample and the hypotheses of the individual learners; we show that a fusion rule can be obtained by formulating this problem as another learning problem. We show sufficiency conditions that ensure the composite system to be better than the best of the individual. Second, in closed fusion the fuser does not have an access to either the training sample or the hypotheses of the individual learners. By using a linear threshold fusion function (of the outputs of individual learners) we show that the composite system can be made better than the best of the statistically independent learners.

Original languageEnglish
Pages (from-to)319-327
Number of pages9
JournalIEEE Transactions on Systems, Man, and Cybernetics
Volume24
Issue number2
DOIs
StatePublished - Feb 1994

Funding

Consider a system of N learners LI, Lz. . . . . LN,where L, learns concepts (subsets) of a domain X in the sense of Valiant [29]; Le., given a sufficiently large sample of examples of c E C C 2x, a hypothesis h close to c will be produced with a high Manuscript received October 17, 1991; revised May 3, 1993. A preliminary version of this paper was presented at the 1992 IEEE International Conference on Intelligent Robots and Systems, July 7-10, 1992. The authors gratefully acknowledge the continuing financial support of this learning research by Oscar Manley of the Basic Energy Sciences Program in the Department of Energy and Teresa McMullen in the Intelligent Systems Program of the Office of Naval Research in the Department of Defense. In addition, N. S. V. Rao is partially funded by National Science Foundation under grant #IRI-9 10861 0, Old Dominion University Summer Faculty Fellowship for 1991. and Virginia’s Center for Innovative Technology under contract # INF-90-015.

Fingerprint

Dive into the research topics of 'N-Learners Problem: Fusion of Concepts'. Together they form a unique fingerprint.

Cite this