The Analysis of Deep Neural Networks by Information Theory: From Explainability to Generalization
DOI:
https://doi.org/10.1609/aaai.v37i13.26829Keywords:
New Faculty HighlightsAbstract
Despite their great success in many artificial intelligence tasks, deep neural networks (DNNs) still suffer from a few limitations, such as poor generalization behavior for out-of-distribution (OOD) data and the "black-box" nature. Information theory offers fresh insights to solve these challenges. In this short paper, we briefly review the recent developments in this area, and highlight our contributions.Downloads
Published
2023-09-06
How to Cite
Yu, S. (2023). The Analysis of Deep Neural Networks by Information Theory: From Explainability to Generalization. Proceedings of the AAAI Conference on Artificial Intelligence, 37(13), 15462-15462. https://doi.org/10.1609/aaai.v37i13.26829
Issue
Section
New Faculty Highlights