INFORMATION-THEORETIC LIMITS FOR DEEP NEURAL NETWORKS

Project Information

IT-DNN

Grant agreement ID: 893082

DOI

10.3030/893082

Project closed

EC signature date 23 March 2020

Start date 1 April 2020

End date 31 March 2022

Funded under

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Total cost

€ 203 852,16

EU contribution

€ 203 852,16

Coordinated by

CHALMERS TEKNISKA HOGSKOLA AB
Sweden

CORDIS provides links to public deliverables and publications of HORIZON projects.

Links to deliverables and publications from FP7 projects, as well as links to some specific result types such as dataset and software, are dynamically retrieved from OpenAIRE .

Publications

Conference proceedings (2)

A Unified View on PAC-Bayes Bounds for Meta-Learnin

Author(s): Arezou Rezazadeh
Published in: 39th International Conference on Machine Learning (ICML 2022), Issue 17-23 July 2022, 2022, Page(s) https://research.chalmers.se/en/publication/532756, ISSN 16218576-18595
Publisher: Proceedings of the 39 th International Conference on Machine Learning

Conditional Mutual Information-Based Generalization Bound for Meta Learning

Author(s): Arezou Rezazadeh, Sharu Theresa Jose, Giuseppe Durisi, Osvaldo Simeone
Published in: 2021 IEEE International Symposium on Information Theory (ISIT), Issue 12-20 July 2021, 2021, Page(s) https://research.chalmers.se/publication/526178/file/526178_Fulltext.pdf, ISBN 978-1-5386-8210-4
Publisher: IEEE
DOI: 10.1109/isit45174.2021.9518020