Strange properties of linear reservoirs in the infinitely large limit for prediction of continuous-time signals

DOI10.1007/s10955-022-03040-zzbMath1505.82047OpenAlexW4311878244MaRDI QIDQ2106521

Alexander Hsu, Sarah E. Marzen

Publication date: 16 December 2022

Published in: Journal of Statistical Physics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10955-022-03040-z

zbMATH Keywords

neural networksGaussian noiserandom matrix theoryprediction of signals

Mathematics Subject Classification ID

Gaussian processes (60G15) Central limit and other weak theorems (60F05) Artificial neural networks and deep learning (68T07) Random matrices (probabilistic aspects) (60B20) Neural nets applied to problems in time-dependent statistical mechanics (82C32) Random matrices (algebraic aspects) (15B52)

Cites Work

• Unnamed Item
• Unnamed Item
• Are biological systems poised at criticality?
• On the computational power of circuits of spiking neurons
• Random matrices: universality of ESDs and the circular law
• Do reservoir computers work best at the edge of chaos?
• On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrast to VAR and DMD
• Statistical Physics of Particles

This page was built for publication: Strange properties of linear reservoirs in the infinitely large limit for prediction of continuous-time signals