Balancing priors and learning biases to improve Bayesian Neural Networks
2022/45/P/ST6/02969
Keywords
Descriptors
- ST6_007: Sztuczna inteligencja, systemy inteligentne i wieloagentowe
- ST6_011: Uczenie maszynowe, statystyczne przetwarzanie danych i zastosowania w przetwarzaniu sygnałów (np. mowy, obrazów, filmów)
Panel
ST6 – Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems
Host institution
Uniwersytet Jagielloński, Wydział Matematyki i Informatyki
Voivodeship: małopolskie
Principal investigator (from the host institution)
Number of co-investigators in the project: 5
Call
POLONEZ BIS 2 – announced on 2022-03-28
- Amount awarded
- 1 078 901 PLN
- Project start date
- 2024-04-01
- Project end date
- 2026-03-31
- Project duration
- 24 months (the same as in the proposal)
- Project status
- Project completed
Project description
Download the project description in a pdf file
Note — project descriptions were prepared by the authors of the applications themselves and placed in the system in an unchanged form.
Information in the final report
Articles in post-conference publications (3)
-
Hypernetwork Approach to Bayesian MAML
- Authors:
- Piotr Borycki, Piotr Kubacki, Marcin Przewięźlikowski, Tomasz Kuśmierczyk, Jacek Tabor, Przemysław Spurek
- Conference:
- Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39 No. 28: IAAI-25, EAAI-25, AAAI-25 Student Abstracts, Undergraduate Consortium and Demonstrations (year: 2025, volume: The Thirty-Ninth AAAI Conference on Artificial Intelligence (AAAI-25), pages: 29325-29327), Publisher: AAAI Press
- Date:
- conference February 27 – March 4, 2025
- Status:
- Published
- DOI:
- 10.1609/aaai.v39i28.35239 – link to the publication
-
Hi-fi functional priors by learning activations
- Authors:
- Marcin Sendera, Amin Sorkhei, Tomasz Kuśmierczyk
- Conference:
- Workshop publications are not included in the offical proceedings of the NeurIPS conference, but are published online through OpenReview (year: 2024, volume: NeurIPS 2024 Workshop on Bayesian Decision-making and Uncertainty, pages: -), Publisher: Online at OpenReview
- Date:
- conference 45640
- Status:
- Published
- DOI:
- link to the publication
-
Revisiting the Equivalence of Bayesian Neural Networks and Gaussian Processes: On the Importance of Learning Activations
- Authors:
- Marcin Sendera, Amin Sorkhei, Tomasz Kuśmierczyk
- Conference:
- Proceedings of Machine Learning Research (PMLR) (year: 2025, volume: 41st Conference on Conference on Uncertainty in Artificial Intelligence, pages: To be assigned), Publisher: Machine Learning Research Press
- Status:
- Accepted for publication
This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 665778.