Projects funded by the NCN
Meta-learning in Deep Neural Networks
2023/49/B/ST6/01137
Keywords:
Meta-learning deep learning neural networks few-shot learning continual learning interpretability
Descriptors:
- ST6_07:
- ST6_11:
Panel:
ST6 - Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems
Host institution :
Uniwersytet Jagielloński, Wydział Matematyki i Informatyki
woj. małopolskie
Principal investigator (from the host institution):
Number of co-investigators in the project: 8
Call: OPUS 25 - announced on 2023-03-16
Amount awarded: 1 103 331 PLN
Project start date (Y-m-d): 2024-01-29
Project end date (Y-m-d): 2028-01-28
Project duration:: 48 months (the same as in the proposal)
Project status: Pending project
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 (1)
- Sparser, Better, Deeper, Stronger: Improving Static Sparse Training with Exact Orthogonal InitializationAuthors:Aleksandra Irena Nowak, Łukasz Gniecki, Filip Szatkowski, Jacek TaborConference:Proceedings of the 41st International Conference on Machine Learning (rok: 2024, tom: International Conference on Machine Learning (ICML), strony: 38474 - 38494), Wydawca: JMLR.orgData:konferencja Czerwiec 21 - 27, 2024Status:PublishedDOI:10.48550/arXiv.2406.01755 - link to the publication