Beyond hebb

Exclusive-OR and biological learning

Konstantin Klemm, Stefan Bornholdt, Heinz Georg Schuster

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

A learning algorithm for multilayer neural networks based on biologically plausible mechanisms is studied. Motivated by findings in experimental neurobiology, we consider synaptic averaging in the induction of plasticity changes, which happen on a slower time scale than firing dynamics. This mechanism is shown to enable learning of the exclusive-OR (XOR) problem without the aid of error backpropagation, as well as to increase robustness of learning in the presence of noise.

Original languageEnglish
Article number3013
JournalPhysical Review Letters
Volume84
Issue number13
DOIs
Publication statusPublished - Mar 27 2000
Externally publishedYes

Fingerprint

learning
Learning
Neurobiology
plastic properties
Noise
induction

ASJC Scopus subject areas

  • Physics and Astronomy(all)
  • Medicine(all)

Cite this

Beyond hebb : Exclusive-OR and biological learning. / Klemm, Konstantin; Bornholdt, Stefan; Schuster, Heinz Georg.

In: Physical Review Letters, Vol. 84, No. 13, 3013, 27.03.2000.

Research output: Contribution to journalArticle

Klemm, Konstantin ; Bornholdt, Stefan ; Schuster, Heinz Georg. / Beyond hebb : Exclusive-OR and biological learning. In: Physical Review Letters. 2000 ; Vol. 84, No. 13.
@article{f4ac7f83cbd84113b350734332d1f569,
title = "Beyond hebb: Exclusive-OR and biological learning",
abstract = "A learning algorithm for multilayer neural networks based on biologically plausible mechanisms is studied. Motivated by findings in experimental neurobiology, we consider synaptic averaging in the induction of plasticity changes, which happen on a slower time scale than firing dynamics. This mechanism is shown to enable learning of the exclusive-OR (XOR) problem without the aid of error backpropagation, as well as to increase robustness of learning in the presence of noise.",
author = "Konstantin Klemm and Stefan Bornholdt and Schuster, {Heinz Georg}",
year = "2000",
month = "3",
day = "27",
doi = "10.1103/PhysRevLett.84.3013",
language = "English",
volume = "84",
journal = "Physical Review Letters",
issn = "0031-9007",
publisher = "American Physical Society",
number = "13",

}

TY - JOUR

T1 - Beyond hebb

T2 - Exclusive-OR and biological learning

AU - Klemm, Konstantin

AU - Bornholdt, Stefan

AU - Schuster, Heinz Georg

PY - 2000/3/27

Y1 - 2000/3/27

N2 - A learning algorithm for multilayer neural networks based on biologically plausible mechanisms is studied. Motivated by findings in experimental neurobiology, we consider synaptic averaging in the induction of plasticity changes, which happen on a slower time scale than firing dynamics. This mechanism is shown to enable learning of the exclusive-OR (XOR) problem without the aid of error backpropagation, as well as to increase robustness of learning in the presence of noise.

AB - A learning algorithm for multilayer neural networks based on biologically plausible mechanisms is studied. Motivated by findings in experimental neurobiology, we consider synaptic averaging in the induction of plasticity changes, which happen on a slower time scale than firing dynamics. This mechanism is shown to enable learning of the exclusive-OR (XOR) problem without the aid of error backpropagation, as well as to increase robustness of learning in the presence of noise.

UR - http://www.scopus.com/inward/record.url?scp=17744402943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=17744402943&partnerID=8YFLogxK

U2 - 10.1103/PhysRevLett.84.3013

DO - 10.1103/PhysRevLett.84.3013

M3 - Article

VL - 84

JO - Physical Review Letters

JF - Physical Review Letters

SN - 0031-9007

IS - 13

M1 - 3013

ER -