3 papers
math.NA2023
Bi-orthogonal fPINN: A physics-informed neural network method for solving time-dependent stochastic fractional PDEs
Lei Ma, Rong xin Li, Fanhai Zeng +2
Fractional partial differential equations (FPDEs) can effectively represent anomalous transport and nonlocal interactions. However, inherent uncertainties arise naturally in real a…
cs.LG2022
Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
Apostolos F Psaros, Xuhui Meng, Zongren Zou +2
Neural networks (NNs) are currently changing the computational paradigm on how to combine data with mathematical laws in physics and engineering in a profound way, tackling challen…
cs.LG2019
Frivolous Units: Wider Networks Are Not Really That Wide
Stephen Casper, Xavier Boix, Vanessa D'Amario +4
A remarkable characteristic of overparameterized deep neural networks (DNNs) is that their accuracy does not degrade when the network's width is increased. Recent evidence suggests…