On the generalization ability of diluted perceptrons

P. Kuhlmann, Klaus Muller

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

A linearly separable Boolean function is teamed by a diluted perceptron with optimal stability. A different level of dilution is allowed for teacher and student perceptron. The learning algorithms used were the optimal annealed dilution and Hebbian dilution. The generalization ability, i.e. the probability to recognize a pattern which has not been learned before, is calculated in replica symmetry.

Original languageEnglish
Article number026
Pages (from-to)3759-3774
Number of pages16
JournalJournal of Physics A: Mathematical and General
Volume27
Issue number11
DOIs
Publication statusPublished - 1994 Dec 1

Fingerprint

self organizing systems
Perceptron
Dilution
dilution
Neural networks
Boolean Functions
Replica
Boolean functions
Learning Algorithm
instructors
Linearly
replicas
Symmetry
students
Learning algorithms
learning
Students
symmetry
Generalization

ASJC Scopus subject areas

  • Statistical and Nonlinear Physics
  • Physics and Astronomy(all)
  • Mathematical Physics

Cite this

On the generalization ability of diluted perceptrons. / Kuhlmann, P.; Muller, Klaus.

In: Journal of Physics A: Mathematical and General, Vol. 27, No. 11, 026, 01.12.1994, p. 3759-3774.

Research output: Contribution to journalArticle

Kuhlmann, P. ; Muller, Klaus. / On the generalization ability of diluted perceptrons. In: Journal of Physics A: Mathematical and General. 1994 ; Vol. 27, No. 11. pp. 3759-3774.
@article{a165f4dab4f34514a6b0082a066355c7,
title = "On the generalization ability of diluted perceptrons",
abstract = "A linearly separable Boolean function is teamed by a diluted perceptron with optimal stability. A different level of dilution is allowed for teacher and student perceptron. The learning algorithms used were the optimal annealed dilution and Hebbian dilution. The generalization ability, i.e. the probability to recognize a pattern which has not been learned before, is calculated in replica symmetry.",
author = "P. Kuhlmann and Klaus Muller",
year = "1994",
month = "12",
day = "1",
doi = "10.1088/0305-4470/27/11/026",
language = "English",
volume = "27",
pages = "3759--3774",
journal = "Journal of Physics A: Mathematical and Theoretical",
issn = "1751-8113",
publisher = "IOP Publishing Ltd.",
number = "11",

}

TY - JOUR

T1 - On the generalization ability of diluted perceptrons

AU - Kuhlmann, P.

AU - Muller, Klaus

PY - 1994/12/1

Y1 - 1994/12/1

N2 - A linearly separable Boolean function is teamed by a diluted perceptron with optimal stability. A different level of dilution is allowed for teacher and student perceptron. The learning algorithms used were the optimal annealed dilution and Hebbian dilution. The generalization ability, i.e. the probability to recognize a pattern which has not been learned before, is calculated in replica symmetry.

AB - A linearly separable Boolean function is teamed by a diluted perceptron with optimal stability. A different level of dilution is allowed for teacher and student perceptron. The learning algorithms used were the optimal annealed dilution and Hebbian dilution. The generalization ability, i.e. the probability to recognize a pattern which has not been learned before, is calculated in replica symmetry.

UR - http://www.scopus.com/inward/record.url?scp=24644444558&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24644444558&partnerID=8YFLogxK

U2 - 10.1088/0305-4470/27/11/026

DO - 10.1088/0305-4470/27/11/026

M3 - Article

AN - SCOPUS:24644444558

VL - 27

SP - 3759

EP - 3774

JO - Journal of Physics A: Mathematical and Theoretical

JF - Journal of Physics A: Mathematical and Theoretical

SN - 1751-8113

IS - 11

M1 - 026

ER -