Learning in low-rank RNNs reduces to an exact low-dimensional ODE system in overlap space, where loss-invisible overlaps encode training history without affecting function.
Chaos in random neural networks.Physical review letters, 61(3):259
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Derives via two-site cavity method that nonlinear RNN covariance matrix equals that of linear equivalent network at large N for typical random couplings.
citing papers explorer
-
Learning reveals invisible structure in low-rank RNNs
Learning in low-rank RNNs reduces to an exact low-dimensional ODE system in overlap space, where loss-invisible overlaps encode training history without affecting function.
-
Linear equivalence of nonlinear recurrent neural networks
Derives via two-site cavity method that nonlinear RNN covariance matrix equals that of linear equivalent network at large N for typical random couplings.