A statistical mixture of Tanh and Swish activations with critical mixing fraction p_c induces a continuous phase transition to scale-invariant signal propagation in deep networks while preserving smoothness.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
GQPINNs add symmetry awareness to quantum PINNs via equivariant circuits, yielding lower mean absolute error and fewer parameters than standard QPINNs on linear and nonlinear PDE benchmarks.
A PINN-trained quasi-parton model reproduces lattice cumulants at vanishing chemical potentials and supplies a consistent four-dimensional QCD equation of state at finite densities.
PIC-Flow applies conditional flow matching with a real-valued U-Net and interface-masked Helmholtz residual loss to predict electromagnetic fields in photonic devices, generalizing to held-out device classes beyond its training set.
citing papers explorer
-
Competing nonlinearities, criticality, and order-to-chaos transition in deep networks
A statistical mixture of Tanh and Swish activations with critical mixing fraction p_c induces a continuous phase transition to scale-invariant signal propagation in deep networks while preserving smoothness.
-
Geometric Quantum Physics Informed Neural Network
GQPINNs add symmetry awareness to quantum PINNs via equivariant circuits, yielding lower mean absolute error and fewer parameters than standard QPINNs on linear and nonlinear PDE benchmarks.
-
Four-dimensional QCD equation of state from a quasi-parton model with physics-informed neural networks
A PINN-trained quasi-parton model reproduces lattice cumulants at vanishing chemical potentials and supplies a consistent four-dimensional QCD equation of state at finite densities.
-
Physics-Based Flow Matching for Full-Field Prediction of Silicon Photonic Devices
PIC-Flow applies conditional flow matching with a real-valued U-Net and interface-masked Helmholtz residual loss to predict electromagnetic fields in photonic devices, generalizing to held-out device classes beyond its training set.