Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Yamamoto, Kakei"'
In this paper, we extend mean-field Langevin dynamics to minimax optimization over probability distributions for the first time with symmetric and provably convergent updates. We propose mean-field Langevin averaged gradient (MFL-AG), a single-loop a
Externí odkaz:
http://arxiv.org/abs/2312.01127
The training of multilayer spiking neural networks (SNNs) using the error backpropagation algorithm has made significant progress in recent years. Among the various training schemes, the error backpropagation method that directly uses the firing time
Externí odkaz:
http://arxiv.org/abs/2307.13007
We propose a novel backpropagation algorithm for training spiking neural networks (SNNs) that encodes information in the relative multiple spike timing of individual neurons without single-spike restrictions. The proposed algorithm inherits the advan
Externí odkaz:
http://arxiv.org/abs/2211.16113
Autor:
Sakemi Y; Research Center for Mathematical Engineering, Chiba Institute of Technology, Narashino, Japan. yusuke.sakemi@p.chibakoudai.jp.; International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo, Tokyo, Japan. yusuke.sakemi@p.chibakoudai.jp., Yamamoto K; Massachusetts Institute of Technology, Cambridge, USA., Hosomi T; NEC Corporation, Kawasaki, Japan., Aihara K; Research Center for Mathematical Engineering, Chiba Institute of Technology, Narashino, Japan.; International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo, Tokyo, Japan.
Publikováno v:
Scientific reports [Sci Rep] 2023 Dec 21; Vol. 13 (1), pp. 22897. Date of Electronic Publication: 2023 Dec 21.
