Agreement in Spiking Neural Networks.

Journal: Journal of computational biology : a journal of computational molecular cell biology
Published Date:

Abstract

We study the problem of binary agreement in a spiking neural network (SNN). We show that binary agreement on inputs can be achieved with of auxiliary neurons. Our simulation results suggest that agreement can be achieved in our network in time. We then describe a subclass of SNNs with a biologically plausible property, which we call size-independence. We prove that solving a class of problems, including agreement and Winner-Take-All, in this model requires auxiliary neurons, which makes our agreement network size-optimal.

Authors

  • Martin Kunev
    LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France.
  • Petr Kuznetsov
    LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France.
  • Denis Sheynikhovich
    Sorbonne Université, INSERM, CNRS, Institut de la Vision, 17 rue Moreau, F-75012 Paris, France. Electronic address: denis.sheynikhovich@upmc.fr.