A dual-head PINN couples H(z) and fσ8(z) through the GR growth ODE; with SH0ES or H0dN priors, fσ8 is systematically suppressed relative to ΛCDM while Om(z) is non-flat.
Inferring Cosmological Parameters with Evidential Physics-Informed Neural Networks.Universe, 11(12):403, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
Ensemble-based method of moments on softmax outputs produces stable Dirichlet predictive distributions that improve uncertainty-guided tasks like selective classification over evidential deep learning.
citing papers explorer
-
Joint reconstruction of $H(z)$ and $f\sigma_8(z)$ with physics informed neural networks
A dual-head PINN couples H(z) and fσ8(z) through the GR growth ODE; with SH0ES or H0dN priors, fσ8 is systematically suppressed relative to ΛCDM while Om(z) is non-flat.
-
Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classification
Ensemble-based method of moments on softmax outputs produces stable Dirichlet predictive distributions that improve uncertainty-guided tasks like selective classification over evidential deep learning.