This paper argues that Continuous Time Recurrent Neural Networks (CTRNNs) provide a particularly attractive paradigm under which to evolve analog electrical circuits for use as device controllers. It will make these arguments both by appeal to existing literature and by the example of a successful project in the control of an autonomous robot. The paper will conclude with a discussion of future work and goals.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Continuous time recurrent neural networks: a paradigm for evolvable analog controller circuits


    Beteiligte:
    Gallacher, J.C. (Autor:in) / Fiore, J.M. (Autor:in)


    Erscheinungsdatum :

    2000-01-01


    Format / Umfang :

    566773 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Continuous Time Recurrent Neural Networks: A Paradigm for Evolvable Analog Controller Circuits

    Gallagher, J. / IEEE | British Library Conference Proceedings | 2000


    Evolvable hardware: on the automatic synthesis of analog control systems

    Zebulum, R.S. / Vellasco, M. / Pacheco, M.A. et al. | IEEE | 2000


    Evolvable Hardware: On the Automatic Synthesis of Analog Control Systems

    Zebulum, R. S. / Vellasco, M. / Pacheco, M. A. et al. | British Library Conference Proceedings | 2000


    Evolvable Space Systems

    Stocia, A. / Thakoor, A. | NTRS | 1998


    Evolvable Electronic Systems

    Stoica, A. / Salazar-Lazaro, C. / Tawel, R. | NTRS | 1998