Gating in RNNs couples state time-scales with parameter gradients to produce lag- and direction-dependent effective learning rates, shown via exact Jacobians and first-order expansion.
Backpropagation through time: what it does and how to do it
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
SemiDANSE uses limited labeled measurement-state pairs plus abundant unlabeled data to achieve competitive state estimation from compressed measurements in model-free chaotic dynamical systems.
citing papers explorer
-
Time-Scale Coupling Between States and Parameters in Recurrent Neural Networks
Gating in RNNs couples state time-scales with parameter gradients to produce lag- and direction-dependent effective learning rates, shown via exact Jacobians and first-order expansion.
-
Semi-Supervised Model-Free Bayesian State Estimation from Compressed Measurements
SemiDANSE uses limited labeled measurement-state pairs plus abundant unlabeled data to achieve competitive state estimation from compressed measurements in model-free chaotic dynamical systems.