N-learners problem: Fusion of concepts

PDF Version Also Available for Download.

Description

We are given N learners each capable of learning concepts (subsets) of a domain set X in the sense of Valiant, i.e. for any c {element of} C {improper subset} 2{sup X}, given a finite set of examples of the form < x{sub 1}, M{sub c}(x{sub 1}) >; < x{sub 2}, M{sub c}(x{sub 2}) >;...;< x{sub 1}, M{sub c}(x{sub 1}) > generated according to an unknown probability distribution P{sub X} on X, each learner produces a close approximation to c with a high probability. We are interested in combining the N learners using a single fuser or consolidator. We consider ... continued below

Physical Description

Pages: (33 p)

Creation Information

Rao, N.S.V.; Oblow, E.M.; Glover, C.W. & liepins, G.E. (Old Dominion Univ., Norfolk, VA (United States). Dept. of Computer Science) September 1, 1991.

Context

This report is part of the collection entitled: Office of Scientific & Technical Information Technical Reports and was provided by UNT Libraries Government Documents Department to Digital Library, a digital repository hosted by the UNT Libraries. More information about this report can be viewed below.

Who

People and organizations associated with either the creation of this report or its content.

Provided By

UNT Libraries Government Documents Department

Serving as both a federal and a state depository library, the UNT Libraries Government Documents Department maintains millions of items in a variety of formats. The department is a member of the FDLP Content Partnerships Program and an Affiliated Archive of the National Archives.

Contact Us

What

Descriptive information to help identify this report. Follow the links below to find similar items on the Digital Library.

Description

We are given N learners each capable of learning concepts (subsets) of a domain set X in the sense of Valiant, i.e. for any c {element of} C {improper subset} 2{sup X}, given a finite set of examples of the form < x{sub 1}, M{sub c}(x{sub 1}) >; < x{sub 2}, M{sub c}(x{sub 2}) >;...;< x{sub 1}, M{sub c}(x{sub 1}) > generated according to an unknown probability distribution P{sub X} on X, each learner produces a close approximation to c with a high probability. We are interested in combining the N learners using a single fuser or consolidator. We consider the paradigm of passive fusion, where each learner is first trained with the sample without the influence of the consolidator. The composite system is constituted by the fuser and the individual learners. We consider two cases: open and closed fusion. In open fusion the fuser is given the sample and the hypotheses of the individual learners; we show that the fusion rule can be obtained by formulating this problem as another learning problem. For the case all individual learners are trained with the same sample, we show sufficiency conditions that ensure the composite system to be better than the best of the individual: the hypothesis space of the consolidator (a) satisfies the isolation property of degree at least N, and (b) has Vapnik-Chervonenkis dimension less than or equal to that of every individual learner. If individual learners are trained by independently generated samples, we obtain a much weaker bound on the VC-dimension of the hypothesis space of the fuser. Second, in closed fusion the fuser does not have an access to either the training sample or the hypotheses of the individual learners. By suitable designing a linear threshold function of the outputs of individual learners, we show that the composite system can be made better than the best of the learners.

Physical Description

Pages: (33 p)

Notes

OSTI; NTIS; GPO Dep.

Language

Item Type

Identifier

Unique identifying numbers for this report in the Digital Library or other systems.

  • Other: DE92000452
  • Report No.: ORNL/TM-11904
  • Report No.: CESAR--91/23
  • Grant Number: AC05-84OR21400
  • DOI: 10.2172/5241320 | External Link
  • Office of Scientific & Technical Information Report Number: 5241320
  • Archival Resource Key: ark:/67531/metadc1072127

Collections

This report is part of the following collection of related materials.

Office of Scientific & Technical Information Technical Reports

Reports, articles and other documents harvested from the Office of Scientific and Technical Information.

Office of Scientific and Technical Information (OSTI) is the Department of Energy (DOE) office that collects, preserves, and disseminates DOE-sponsored research and development (R&D) results that are the outcomes of R&D projects or other funded activities at DOE labs and facilities nationwide and grantees at universities and other institutions.

What responsibilities do I have when using this report?

When

Dates and time periods associated with this report.

Creation Date

  • September 1, 1991

Added to The UNT Digital Library

  • Feb. 4, 2018, 10:51 a.m.

Description Last Updated

  • Feb. 15, 2018, 8:33 p.m.

Usage Statistics

When was this report last used?

Congratulations! It looks like you are the first person to view this item online.

Interact With This Report

Here are some suggestions for what to do next.

Start Reading

PDF Version Also Available for Download.

International Image Interoperability Framework

IIF Logo

We support the IIIF Presentation API

Rao, N.S.V.; Oblow, E.M.; Glover, C.W. & liepins, G.E. (Old Dominion Univ., Norfolk, VA (United States). Dept. of Computer Science). N-learners problem: Fusion of concepts, report, September 1, 1991; Tennessee. (digital.library.unt.edu/ark:/67531/metadc1072127/: accessed December 13, 2018), University of North Texas Libraries, Digital Library, digital.library.unt.edu; crediting UNT Libraries Government Documents Department.