Zobrazeno 1 - 10
of 53 437
pro vyhledávání: '"A. Egeland"'
Autor:
Jezierski, Kamil
Publikováno v:
Psychologia Rozwojowa / Developmental Psychology. 26(4):105-111
Externí odkaz:
https://www.ceeol.com/search/article-detail?id=1067360
Publikováno v:
BMJ: British Medical Journal, 2000 Sep . 321(7264), 826-826.
Externí odkaz:
https://www.jstor.org/stable/25225774
Autor:
Smith, Torbjørn, Egeland, Olav
This paper presents a new method for learning dissipative Hamiltonian dynamics from a limited and noisy dataset. The method uses the Helmholtz decomposition to learn a vector field as the sum of a symplectic and a dissipative vector field. The two ve
Externí odkaz:
http://arxiv.org/abs/2410.18656
Diffusion models have seen rapid adoption in robotic imitation learning, enabling autonomous execution of complex dexterous tasks. However, action synthesis is often slow, requiring many steps of iterative denoising, limiting the extent to which mode
Externí odkaz:
http://arxiv.org/abs/2406.04806
Autor:
Mamalakis, Michail, de Vareilles, Héloïse, Wu, Shun-Chin Jim, Agartz, Ingrid, Mørch-Johnsen, Lynn Egeland, Garrison, Jane, Simons, Jon, Lio, Pietro, Suckling, John, Murray, Graham
In the last decade, computer vision has witnessed the establishment of various training and learning approaches. Techniques like adversarial learning, contrastive learning, diffusion denoising learning, and ordinary reconstruction learning have becom
Externí odkaz:
http://arxiv.org/abs/2405.19204
Autor:
Mamalakis, Michail, Mamalakis, Antonios, Agartz, Ingrid, Mørch-Johnsen, Lynn Egeland, Murray, Graham, Suckling, John, Lio, Pietro
The accelerated progress of artificial intelligence (AI) has popularized deep learning models across domains, yet their inherent opacity poses challenges, notably in critical fields like healthcare, medicine and the geosciences. Explainable AI (XAI)
Externí odkaz:
http://arxiv.org/abs/2405.10008
Autor:
Smith, Torbjørn, Egeland, Olav
Publikováno v:
European Journal of Control, 2024
A method for learning Hamiltonian dynamics from a limited and noisy dataset is proposed. The method learns a Hamiltonian vector field on a reproducing kernel Hilbert space (RKHS) of inherently Hamiltonian vector fields, and in particular, odd Hamilto
Externí odkaz:
http://arxiv.org/abs/2404.07703
Autor:
Ancel, Stéphane1 stephaneancel@hotmail.com
Publikováno v:
Social Sciences & Missions. 2018, Vol. 31 Issue 3/4, p397-400. 4p.