Projects funded by the NCN
How to learn faster: towards better adaptation in Meta-Learning.
2022/45/N/ST6/03374
Keywords:
machine learning deep learning meta-learning fast adaptation fine-tuning continual learning catastrophic forgetting few-shot learning
Descriptors:
- ST6_011:
- ST6_007:
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: 3
Call: PRELUDIUM 21 - announced on 2022-03-28
Amount awarded: 139 471 PLN
Project start date (Y-m-d): 2023-02-07
Project end date (Y-m-d): 2025-08-06
Project duration:: 30 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
- Publication in academic press/journals (2)
- Articles in post-conference publications (1)
- The general framework for few-shot learning by kernel HyperNetworksAuthors:Marcin Sendera, Marcin Przewięźlikowski, Jan Miksa, Mateusz Rajski, Konrad Karanowski, Maciej Zięba, Jacek Tabor, Przemysław SpurekAcademic press:Machine Vision and Applications (rok: 2023, tom: 34, strony: 56-72), Wydawca: SpringerStatus:PublishedDOI:10.1007/s00138-023-01403-4 - link to the publication
- The general framework for few-shot learning by kernel HyperNetworksAuthors:Marcin Sendera, Marcin Przewięźlikowski, Jan Miksa, Mateusz Rajski, Konrad Karanowski, Maciej Zięba, Jacek Tabor, Przemysław SpurekAcademic press:Machine Vision and Applications (rok: 2023, tom: 34, strony: 56-72), Wydawca: SpringerStatus:PublishedDOI:10.1007/s00138-023-01403-4 - link to the publication
- Improved off-policy training of diffusion samplersAuthors:Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, Nikolay MalkinConference:Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, NeurIPS 2024 (rok: 2025, tom: 38th Conference on Neural Information Processing Systems (NeurIPS 2024), strony: 81016-81045), Wydawca: ACMData:konferencja 10.12.2024 - 15.12.2024Status:PublishedDOI:10.48550/arXiv.2402.05098 - link to the publication