CONVERGENCE OF POTENTIAL FUNCTION TYPE LEARNING ALGORITHMS.

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Convergence theorems for some learning algorithms generated by a potential function are dealt with. The kernel function of a reproducing kernel Hilbert space (RKHS) as a potential function is used. The problem of how one may use ″teaching″ several times during the algorithm is considered, along with the case of noisy ″teaching″ . Algorithms are discussed which turned out to be particularly efficient in learning in unambiguous models by potential function type learning algorithms.

Original languageEnglish
Title of host publicationProbl Control Inf Theory
Pages247-265
Number of pages19
Volume1
Edition3-4
Publication statusPublished - 1972

Fingerprint

Learning algorithms
Teaching
Hilbert spaces

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Györfi, L. (1972). CONVERGENCE OF POTENTIAL FUNCTION TYPE LEARNING ALGORITHMS. In Probl Control Inf Theory (3-4 ed., Vol. 1, pp. 247-265)

CONVERGENCE OF POTENTIAL FUNCTION TYPE LEARNING ALGORITHMS. / Györfi, L.

Probl Control Inf Theory. Vol. 1 3-4. ed. 1972. p. 247-265.

Research output: Chapter in Book/Report/Conference proceedingChapter

Györfi, L 1972, CONVERGENCE OF POTENTIAL FUNCTION TYPE LEARNING ALGORITHMS. in Probl Control Inf Theory. 3-4 edn, vol. 1, pp. 247-265.
Györfi L. CONVERGENCE OF POTENTIAL FUNCTION TYPE LEARNING ALGORITHMS. In Probl Control Inf Theory. 3-4 ed. Vol. 1. 1972. p. 247-265
Györfi, L. / CONVERGENCE OF POTENTIAL FUNCTION TYPE LEARNING ALGORITHMS. Probl Control Inf Theory. Vol. 1 3-4. ed. 1972. pp. 247-265
@inbook{0bfa6b46cf06461c848fba19a58a52f0,
title = "CONVERGENCE OF POTENTIAL FUNCTION TYPE LEARNING ALGORITHMS.",
abstract = "Convergence theorems for some learning algorithms generated by a potential function are dealt with. The kernel function of a reproducing kernel Hilbert space (RKHS) as a potential function is used. The problem of how one may use ″teaching″ several times during the algorithm is considered, along with the case of noisy ″teaching″ . Algorithms are discussed which turned out to be particularly efficient in learning in unambiguous models by potential function type learning algorithms.",
author = "L. Gy{\"o}rfi",
year = "1972",
language = "English",
volume = "1",
pages = "247--265",
booktitle = "Probl Control Inf Theory",
edition = "3-4",

}

TY - CHAP

T1 - CONVERGENCE OF POTENTIAL FUNCTION TYPE LEARNING ALGORITHMS.

AU - Györfi, L.

PY - 1972

Y1 - 1972

N2 - Convergence theorems for some learning algorithms generated by a potential function are dealt with. The kernel function of a reproducing kernel Hilbert space (RKHS) as a potential function is used. The problem of how one may use ″teaching″ several times during the algorithm is considered, along with the case of noisy ″teaching″ . Algorithms are discussed which turned out to be particularly efficient in learning in unambiguous models by potential function type learning algorithms.

AB - Convergence theorems for some learning algorithms generated by a potential function are dealt with. The kernel function of a reproducing kernel Hilbert space (RKHS) as a potential function is used. The problem of how one may use ″teaching″ several times during the algorithm is considered, along with the case of noisy ″teaching″ . Algorithms are discussed which turned out to be particularly efficient in learning in unambiguous models by potential function type learning algorithms.

UR - http://www.scopus.com/inward/record.url?scp=0015457917&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0015457917&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:0015457917

VL - 1

SP - 247

EP - 265

BT - Probl Control Inf Theory

ER -