|
This article is cited in 5 scientific papers (total in 5 papers)
REVIEWS OF TOPICAL PROBLEMS
Nonlinear dynamics and machine learning of recurrent spiking neural networks
O. V. Maslennikov, M. M. Pugavko, D. S. Shchapin, V. I. Nekorkin Federal Research Center Institute of Applied Physics, Russian Academy of Sciences, Nizhny Novgorod
Abstract:
Major achievements in designing and analyzing recurrent spiking neural networks intended for modeling functional brain networks are reviewed. Key terms and definitions employed in machine learning are introduced. The main approaches to the development and exploration of spiking and rate neural networks trained to perform specific cognitive functions are presented. State-of-the-art neuromorphic hardware systems simulating information processing by the brain are described. Concepts of nonlinear dynamics are discussed, which enable identification of the mechanisms used by neural networks to perform target tasks.
Received: June 1, 2021 Revised: August 13, 2021 Accepted: August 13, 2021
Citation:
O. V. Maslennikov, M. M. Pugavko, D. S. Shchapin, V. I. Nekorkin, “Nonlinear dynamics and machine learning of recurrent spiking neural networks”, UFN, 192:10 (2022), 1089–1109; Phys. Usp., 65:10 (2022), 1020–1038
Linking options:
https://www.mathnet.ru/eng/ufn7092 https://www.mathnet.ru/eng/ufn/v192/i10/p1089
|
Statistics & downloads: |
Abstract page: | 213 | Full-text PDF : | 22 | References: | 18 | First page: | 12 |
|