RepNN reparameterizes the first hidden layer of DNNs to enable adaptive frequency scaling, improving accuracy on oscillatory and multiscale functions with minimal extra cost.
Bharadwaj and Philipp Pfeffer and Katepalli R
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Second-order Carleman linearization recovers steady-state solutions for low-Re fluid flows, proved analytically for a logistic model and shown numerically for 2D Kolmogorov flow below Re ~10.
citing papers explorer
-
RepNN: Tackling spectral bias in deep neural networks via parameter reparameterization
RepNN reparameterizes the first hidden layer of DNNs to enable adaptive frequency scaling, improving accuracy on oscillatory and multiscale functions with minimal extra cost.
-
Lowest order Carleman linearization for low Reynolds long-term behaviour of fluid flow simulations
Second-order Carleman linearization recovers steady-state solutions for low-Re fluid flows, proved analytically for a logistic model and shown numerically for 2D Kolmogorov flow below Re ~10.