Changes in synapse weights due to circuit drifts suppressed. Proposed fully parallel analog version of electronic neural-network processor based on delta-back-propagation algorithm. Processor able to "learn" when provided with suitable combinations of inputs and enforced outputs. Includes programmable resistive memory elements (corresponding to synapses), conductances (synapse weights) adjusted during learning. Buffer amplifiers, summing circuits, and sample-and-hold circuits arranged in layers of electronic neurons in accordance with delta-back-propagation algorithm.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen


    Exportieren, teilen und zitieren



    Titel :

    Analog Delta-Back-Propagation Neural-Network Circuitry


    Beteiligte:

    Erschienen in:

    Erscheinungsdatum :

    01.06.1990



    Medientyp :

    Sonstige


    Format :

    Keine Angabe


    Sprache :

    Englisch




    Biomorphic Analog Neural Circuitry

    Thomas, T. | NTRS | 2000


    Biomorphic Analog Neural Circuitry

    Thomas, T. | NTRS | 2000


    Built-In Hardware for Analog Circuitry Testing

    Assaf, Mansour H. / Fathi, Maryam | IEEE | 2008


    Back Propagation Neural Network Model for Railway Risk Warning

    Duan, Baofu / Yang, Yunqian / Jing, Zhe et al. | IEEE | 2024


    Fault Diagnosis of Rotating Machinery Using Back Propagation Neural Network

    Liu, Z. et al | British Library Online Contents | 1997