Approximation Error and Complexity Bounds for ReLU Networks on Low-Regular Function Spaces

no code implementations • 10 May 2024 • Owen Davis, Gianluca Geraci, Mohammad Motamed

In this work, we consider the approximation of a large class of bounded functions, with minimal regularity assumptions, by ReLU neural networks.

Residual Multi-Fidelity Neural Network Computing

no code implementations • 5 Oct 2023 • Owen Davis, Mohammad Motamed, Raul Tempone

In this work, we consider the general problem of constructing a neural network surrogate model using multi-fidelity information.