Unification neural networks: unification by error-correction learning

Research output: Contribution to journalArticle

4 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.
Original languageEnglish
Pages (from-to)821-847
Number of pages27
JournalLogic Journal of the IGPL
Volume19
Issue number6
DOIs
Publication statusPublished - Dec 2011

Keywords

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

Fingerprint Dive into the research topics of 'Unification neural networks: unification by error-correction learning'. Together they form a unique fingerprint.

  • Cite this