Agreement in Spiking Neural Networks
| Autor: | Martin Kunev, Petr Kuznetsov, Denis Sheynikhovich |
|---|---|
| Přispěvatelé: | Laboratoire Traitement et Communication de l'Information (LTCI), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Institut Polytechnique de Paris (IP Paris), Département Informatique et Réseaux (INFRES), Télécom ParisTech, Autonomic and Critical Embedded Systems (LTCI - ACES), Institut Mines-Télécom [Paris] (IMT)-Télécom Paris-Institut Mines-Télécom [Paris] (IMT)-Télécom Paris, Institut de la Vision, Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Sheynikhovich, Denis |
| Rok vydání: | 2022 |
| Předmět: |
Neurons
[SCCO.COMP]Cognitive science/Computer science spiking neural network Computational Mathematics Computational Theory and Mathematics consensus [SCCO.COMP] Cognitive science/Computer science Modeling and Simulation Genetics Computer Simulation Neural Networks Computer complexity binary agreement Molecular Biology winner-take-all |
| Zdroj: | Journal of Computational Biology Journal of Computational Biology, 2022, 29 (4), pp.358-369. ⟨10.1089/cmb.2021.0365⟩ |
| ISSN: | 1557-8666 1066-5277 |
| Popis: | International audience; We study the problem of binary agreement in a spiking neural network (SNN). We show that binary agreement on n inputs can be achieved with O(n) of auxiliary neurons. Our simulation results suggest that agreement can be achieved in our network in O(log n) 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 O(n) auxiliary neurons, which makes our agreement network size-optimal. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|