Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Kirill Kondrashov"'
Publikováno v:
IEEE Open Journal of Signal Processing, Vol 5, Pp 195-203 (2024)
Bayesian model reduction provides an efficient approach for comparing the performance of all nested sub-models of a model, without re-evaluating any of these sub-models. Until now, Bayesian model reduction has been applied mainly in the computational
Externí odkaz:
https://doaj.org/article/3bf40b51c4d14a3abb46257d6fa8a780
Autor:
Graham W. Pulford, Kirill Kondrashov
Publikováno v:
IEEE Access, Vol 9, Pp 165366-165384 (2021)
Due to their success at synthesising highly realistic images, many claims have been made about optimality and convergence in generative adversarial networks (GANs). But what of vanishing gradients, saturation, and other numerical problems noted by AI
Externí odkaz:
https://doaj.org/article/0490e90f4ab74287a78b17f1585a953d
Publikováno v:
arXiv, 2022:2210.09134. Cornell University Library
Pure TUe
Pure TUe
Bayesian model reduction provides an efficient approach for comparing the performance of all nested sub-models of a model, without re-evaluating any of these sub-models. Until now, Bayesian model reduction has been applied mainly in the computational
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f850c9f4f498d1ff8629fb07b27b9141
https://arxiv.org/abs/2210.09134
https://arxiv.org/abs/2210.09134
Autor:
Valeri Jurakovsky, Kirill Kondrashov
Publikováno v:
Science and Education of the Bauman MSTU. 13