Unification neural networks: unification by error-correction learning

E. Komendantskaya

doi:10.1093/jigpal/jzq012

Unification neural networks: unification by error-correction learning

E. Komendantskaya

Research output: Contribution to journal › Article › peer-review

8 Citations (Scopus)

Abstract

We show that the conventional first-order algorithm of unification can be simulated by finite artificial neural networks with one layer of neurons. In these unification neural networks, the unification algorithm is performed by error-correction learning. Each time-step of adaptation of the network corresponds to a single iteration of the unification algorithm. We present this result together with the library of learning functions and examples fully formalised in MATLAB Neural Network Toolbox. © The Author 2010. Published by Oxford University Press. All rights reserved.

Original language	English
Pages (from-to)	821-847
Number of pages	27
Journal	Logic Journal of the Interest Group in Pure and Applied Logic (IGPL) (Logic Journal of the IGPL)
Volume	19
Issue number	6
DOIs	https://doi.org/10.1093/jigpal/jzq012
Publication status	Published - Dec 2011

Keywords

Unification
Neuro-Symbolic Networks
Neural Network Learning
Error-correction Learning
Hybrid Networks
Connectionism
PROGRAMS

Access to Document

10.1093/jigpal/jzq012

Cite this

@article{b7a74ac0d7074ed6b78ab0561aca06ec,

title = "Unification neural networks: unification by error-correction learning",

abstract = "We show that the conventional first-order algorithm of unification can be simulated by finite artificial neural networks with one layer of neurons. In these unification neural networks, the unification algorithm is performed by error-correction learning. Each time-step of adaptation of the network corresponds to a single iteration of the unification algorithm. We present this result together with the library of learning functions and examples fully formalised in MATLAB Neural Network Toolbox. {\textcopyright} The Author 2010. Published by Oxford University Press. All rights reserved.",

keywords = "Unification, Neuro-Symbolic Networks, Neural Network Learning, Error-correction Learning, Hybrid Networks, Connectionism, PROGRAMS",

author = "E. Komendantskaya",

year = "2011",

month = dec,

doi = "10.1093/jigpal/jzq012",

language = "English",

volume = "19",

pages = "821--847",

journal = "Logic Journal of the Interest Group in Pure and Applied Logic (IGPL) (Logic Journal of the IGPL)",

issn = "1367-0751",

publisher = "Oxford University Press",

number = "6",

}

TY - JOUR

T1 - Unification neural networks

T2 - unification by error-correction learning

AU - Komendantskaya, E.

PY - 2011/12

Y1 - 2011/12

N2 - We show that the conventional first-order algorithm of unification can be simulated by finite artificial neural networks with one layer of neurons. In these unification neural networks, the unification algorithm is performed by error-correction learning. Each time-step of adaptation of the network corresponds to a single iteration of the unification algorithm. We present this result together with the library of learning functions and examples fully formalised in MATLAB Neural Network Toolbox. © The Author 2010. Published by Oxford University Press. All rights reserved.

AB - We show that the conventional first-order algorithm of unification can be simulated by finite artificial neural networks with one layer of neurons. In these unification neural networks, the unification algorithm is performed by error-correction learning. Each time-step of adaptation of the network corresponds to a single iteration of the unification algorithm. We present this result together with the library of learning functions and examples fully formalised in MATLAB Neural Network Toolbox. © The Author 2010. Published by Oxford University Press. All rights reserved.

KW - Unification

KW - Neuro-Symbolic Networks

KW - Neural Network Learning

KW - Error-correction Learning

KW - Hybrid Networks

KW - Connectionism

KW - PROGRAMS

UR - http://www.scopus.com/inward/record.url?scp=80054760691&partnerID=8YFLogxK

U2 - 10.1093/jigpal/jzq012

DO - 10.1093/jigpal/jzq012

M3 - Article

SN - 1367-0751

VL - 19

SP - 821

EP - 847

JO - Logic Journal of the Interest Group in Pure and Applied Logic (IGPL) (Logic Journal of the IGPL)

JF - Logic Journal of the Interest Group in Pure and Applied Logic (IGPL) (Logic Journal of the IGPL)

IS - 6

ER -

Unification neural networks: unification by error-correction learning

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this