Neftci E, Chicca E, Indiveri G, Slotine J-J, Douglas R. Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons. Presented at the Advances in Neural Information Processing Systems 20 (NIPS), Vancouver, British Columbia, Canada. ; A non–linear dynamic system is called contracting if initial conditions are forgotten exponentially fast, so that all trajectories converge to a single trajectory. We use contraction theory to derive an upper bound for the strength of recurrent connections that guarantees contraction for complex neural networks. Specifically, we apply this theory to a special class of recurrent networks, often called Cooperative Competitive Networks (CCNs), which are an abstract representation of the cooperative-competitive connectivity observed in cortex. This specific type of network is believed to play a major role in shaping cortical responses and selecting the relevant signal among distractors and noise. In this paper, we analyze contraction of combined CCNs of linear threshold units and verify the results of our analysis in a hybrid analog/digital VLSI CCN comprising spiking neurons and dynamic synapses.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Contraction Properties of VLSI Cooperative Competitive Neural Networks of Spiking Neurons


    Beteiligte:
    Neftci, E. (Autor:in) / Chicca, Elisabetta (Autor:in) / Indiveri, G. (Autor:in) / Slotine, J.-J. (Autor:in) / Douglas, R. (Autor:in) / Platt, J.C. (Autor:in) / Koller, D. (Autor:in) / Singer, Y. (Autor:in) / Roweis, S. (Autor:in)

    Erscheinungsdatum :

    2008-01-01


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Schlagwörter :

    Klassifikation :

    DDC:    006 / 629




    Cognitive processing using spiking neural networks

    Allen, Jacob N. / Abdel-Aty-Zohdy, Hoda S. / Ewing, Robert L. | IEEE | 2009


    Dilute Combustion Control Using Spiking Neural Networks

    Kaul, Brian C. / Maldonado, Bryan P. / Schuman, Catherine D. et al. | SAE Technical Papers | 2021


    Neural Networks Of VLSI Components

    Eberhardt, Silvio P. | NTRS | 1991


    Exploring Lottery Ticket Hypothesis in Spiking Neural Networks

    Kim, Youngeun / Li, Yuhang / Park, Hyoungseob et al. | British Library Conference Proceedings | 2022