Parallel rewriting in neural networks

Ekaterina Komendantskaya

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Rewriting systems are used in various areas of computer science, and especially in lambda-calculus, higher-order logics and functional programming. We show that the unsupervised learning networks can implement parallel rewriting. We show how this general correspondence can be refined in order to perform parallel term rewriting in neural networks, for any given first-order term. We simulate these neural networks in the MATLAB Neural Network Toolbox and present the complete library of functions written in the MATLAB Neural Network Toolbox.

    Original languageEnglish
    Title of host publicationIJCCI 2009: Proceedings of the International Joint Conference on Computational Intelligence
    EditorsA Dourado, A Rosa, K Madani
    Place of PublicationSetubal
    PublisherInstitute for Systems and Technologies of Information, Control and Communication
    Pages452-458
    Number of pages7
    ISBN (Print)978-989-674-014-6
    Publication statusPublished - 2009
    Event1st International Joint Conference on Computational Intelligence - Funchal, Portugal
    Duration: 5 Oct 20097 Oct 2009

    Conference

    Conference1st International Joint Conference on Computational Intelligence
    Abbreviated titleIJCCI 2009
    CountryPortugal
    CityFunchal
    Period5/10/097/10/09

    Keywords

    • Computational logic in neural networks
    • Neuro-symbolic networks
    • Abstract rewriting
    • Parallel term-rewriting
    • Unsupervised learning
    • Computer simulation of neural networks

    Cite this

    Komendantskaya, E. (2009). Parallel rewriting in neural networks. In A. Dourado, A. Rosa, & K. Madani (Eds.), IJCCI 2009: Proceedings of the International Joint Conference on Computational Intelligence (pp. 452-458). Institute for Systems and Technologies of Information, Control and Communication.