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.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
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.