Claudia Schillings, Vladimir Spokoiny
01.01.2023 − 31.12.2024
Uncertainty quantification (UQ) and reliability of deep neuronal networks is an important research question. This project aims at developing of novel numerically efficient methods for inference and UQ analysis of DNN with theoretical guarantees. Particular issues to address are high parameter dimension and nonconvexity of the objective function. We propose a new insight on the problem using the recent progress in high dimensional Laplace approximation. A further goal is to apply the proposed methods to various application problems.