Renewed interest in cognitive information processing has identified the need for novel computing architectures that can efficiently and dynamically support reasoning and learning with emphasis on memory structures. A large number of cognitive processing methods have been implemented in software on conventional computing architectures. This paper describes detailed execution profiling of a particular cognitive method for analogical reasoning called SAGE™. SAGE™ is a symbolic-connectionist, performance oriented analogical reasoner. The primary contribution of the work is to identify the deficiencies and bottlenecks of SAGE™ to inform the development of improved architectures for cognitive information processing, and especially for analogical reasoning.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Performance analysis of a cognitive analogical reasoner


    Beteiligte:
    Daily, Mike (Autor:in) / Isdale, Jerry (Autor:in) / Neely, Howard (Autor:in) / Bogdanowicz, Julius (Autor:in)


    Erscheinungsdatum :

    01.03.2009


    Format / Umfang :

    1265473 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Symbolic Probabilistic Cognitive Reasoner on Neuromorphic Hardware

    Fan, David / DeMange, Ashley / Jenkins, Todd et al. | IEEE | 2021


    TRAFFIC REASONER

    TUDORAN RADU / HASSAN MOHAMAD / BORTOLI STEFANO et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    RAPSODI Adversarial Reasoner

    Howard, Mike / Huang, Eric / Leung, Ken et al. | IEEE | 2007


    MISSION REASONER SYSTEM AND METHOD

    DUNLAY ANGELA N / LORCH MATTHEW M / CHAKRAVARTY SUBHASHISH et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Mission Reasoner System and Method

    DUNLAY ANGELA N / LORCH MATTHEW M / CHAKRAVARTY SUBHASHISH et al. | Europäisches Patentamt | 2022

    Freier Zugriff