Theory of Neuromorphic Computing by Waves: Machine Learning by Rogue Waves, Dispersive Shocks, and Solitons

We study artificial neural networks with nonlinear waves as a computing reservoir. We discuss universality and the conditions to learn a dataset in terms of output channels and nonlinearity. A feed-forward three-layered model, with an encoding input layer, a wave layer, and a decoding readout, behav...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Physical review letters Ročník 125; číslo 9; s. 1
Hlavní autoři:	Marcucci, Giulia, Pierangeli, Davide, Conti, Claudio
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	College Park American Physical Society 28.08.2020
Témata:	Accelerators Artificial neural networks Boolean algebra Bose-Einstein condensates Combinatorial analysis Computational fluid dynamics Datasets Fluid flow Hydrodynamics Interpolation Machine learning Mathematical analysis Mathematical functions Matrix methods Neural networks Nonlinear optics Nonlinear systems Nonlinearity Optical fibers Optimization Schrodinger equation Shock waves Solitary waves Training
ISSN:	0031-9007, 1079-7114, 1079-7114
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!