From the 1 of 4 linked papers with an AI index.
4 papers
Symmetrized Sinkhorn-Gibbs Inference for Oscillatory Inverse Problems
Gabriel Huerta, Mohammad Motamed
The paper proposes a symmetrized Sinkhorn‑Gibbs inference method that normalizes signed oscillatory signals and uses a symmetrized Sinkhorn loss within a Gibbs posterior to improve…
Non-degenerate Marginal-Likelihood Calibration with Application to Quantum Characterization
Mohammad Motamed, N. Anders Petersson
We propose a marginal likelihood strategy within the Kennedy-O'Hagan (KOH) Bayesian framework, where a Gaussian process (GP) models the discrepancy between a physical system and it…
Residual Multi-Fidelity Neural Network Computing
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. Motivated by error-complexity estimates for ReLU ne…
Approximation Power of Deep Neural Networks: an explanatory mathematical survey
Owen Davis, Mohammad Motamed
This survey provides an in-depth and explanatory review of the approximation properties of deep neural networks, with a focus on feed-forward and residual architectures. The primar…