An Information Theoretic Approach to Validate Deep Learning-Based Algorithms

Gitta Kutyniok
Technische Universität Berlin
Program in Applied and Computational Mathematics

In this talk, we provide a theoretical framework for interpreting neural network decisions by formalizing the problem in a rate-distortion framework. The solver of the associated
optimization, which we coin Rate-Distortion Explanation (RDE), is then accessible to a mathematical analysis. We will discuss theoretical results as well as present numerical experiments showing that our algorithmic approach outperforms established methods, in particular, for sparse explanations of neural network decisions.

Presentation (PDF File)

Back to Workshop III: Validation and Guarantees in Learning Physical Models: from Patterns to Governing Equations to Laws of Nature