Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Greenfeld, Daniel"'
Autor:
Yona, Gal, Greenfeld, Daniel
Saliency methods are a popular approach for model debugging and explainability. However, in the absence of ground-truth data for what the correct maps should be, evaluating and comparing different approaches remains a long-standing challenge. The san
Externí odkaz:
http://arxiv.org/abs/2110.14297
Out-of-domain (OOD) generalization is a significant challenge for machine learning models. Many techniques have been proposed to overcome this challenge, often focused on learning models with certain invariance properties. In this work, we draw a lin
Externí odkaz:
http://arxiv.org/abs/2102.10395
Autor:
Greenfeld, Daniel, Shalit, Uri
We investigate the use of a non-parametric independence measure, the Hilbert-Schmidt Independence Criterion (HSIC), as a loss-function for learning robust regression and classification models. This loss-function encourages learning models where the d
Externí odkaz:
http://arxiv.org/abs/1910.00270
Constructing fast numerical solvers for partial differential equations (PDEs) is crucial for many scientific disciplines. A leading technique for solving large-scale PDEs is using multigrid methods. At the core of a multigrid solver is the prolongati
Externí odkaz:
http://arxiv.org/abs/1902.10248
It is well known that for some tasks, labeled data sets may be hard to gather. Therefore, we wished to tackle here the problem of having insufficient training data. We examined learning methods from unlabeled data after an initial training on a limit
Externí odkaz:
http://arxiv.org/abs/1710.00209
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Chemical Communications (0009241X); 10/ 2/1968, Issue 19, p1162-1163, 2p