A thin film with magnetic impurities and dipole-dipole interactions functions as a reservoir computer, achieving high accuracy on digit recognition from spatially averaged readouts.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Derives a random-matrix criterion for the critical initialization gain g_c in gated RNN reservoirs that closely tracks peak performance on chaotic forecasting tasks.
citing papers explorer
-
Reservoir computing by thin film embedded with magnetic impurities
A thin film with magnetic impurities and dipole-dipole interactions functions as a reservoir computer, achieving high accuracy on digit recognition from spatially averaged readouts.
-
A Random-Matrix Criterion for Initializing Gated Recurrent Neural Networks
Derives a random-matrix criterion for the critical initialization gain g_c in gated RNN reservoirs that closely tracks peak performance on chaotic forecasting tasks.