AAAI 2023technical1 citations
The Analysis of Deep Neural Networks by Information Theory: From Explainability to Generalization
Abstract
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.
BibTeX
@article{Yu_2024, title={The Analysis of Deep Neural Networks by Information Theory: From Explainability to Generalization}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/26829}, DOI={10.1609/aaai.v37i13.26829}, abstractNote={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.}, number={13}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Yu, Shujian}, year={2024}, month={Jul.}, pages={15462-15462} }