Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Abdullah, Mohammed Amin"'
Autor:
Abdullah, Mohammed Amin, Ren, Hang, Ammar, Haitham Bou, Milenkovic, Vladimir, Luo, Rui, Zhang, Mingtian, Wang, Jun
Reinforcement learning algorithms, though successful, tend to over-fit to training environments hampering their application to the real-world. This paper proposes $\text{W}\text{R}^{2}\text{L}$ -- a robust reinforcement learning algorithm with signif
Externí odkaz:
http://arxiv.org/abs/1907.13196
We describe an application of Wasserstein distance to Reinforcement Learning. The Wasserstein distance in question is between the distribution of mappings of trajectories of a policy into some metric space, and some other fixed distribution (which ma
Externí odkaz:
http://arxiv.org/abs/1802.03976
We study online robust matrix completion on graphs. At each iteration a vector with some entries missing is revealed and our goal is to reconstruct it by identifying the underlying low-dimensional subspace from which the vectors are drawn. We assume
Externí odkaz:
http://arxiv.org/abs/1605.04192
Suppose in a graph $G$ vertices can be either red or blue. Let $k$ be odd. At each time step, each vertex $v$ in $G$ polls $k$ random neighbours and takes the majority colour. If it doesn't have $k$ neighbours, it simply polls all of them, or all les
Externí odkaz:
http://arxiv.org/abs/1507.06818
We study typical distances in a geometric random graph on the hyperbolic plane. Introduced by Krioukov et al.~\cite{ar:Krioukov} as a model for complex networks, $N$ vertices are drawn randomly within a bounded subset of the hyperbolic plane and any
Externí odkaz:
http://arxiv.org/abs/1506.07811
The theme of this paper is the analysis of bootstrap percolation processes on random graphs generated by preferential attachment. This is a class of infection processes where vertices have two states: they are either infected or susceptible. At each
Externí odkaz:
http://arxiv.org/abs/1404.4070
Autor:
Abdullah, Mohammed Amin, Draief, Moez
Suppose in a graph $G$ vertices can be either red or blue. Let $k$ be odd. At each time step, each vertex $v$ in $G$ polls $k$ random neighbours and takes the majority colour. If it doesn't have $k$ neighbours, it simply polls all of them, or all les
Externí odkaz:
http://arxiv.org/abs/1209.5025
Autor:
Abdullah, Mohammed Amin, Draief, Moez
Publikováno v:
In Discrete Applied Mathematics 10 January 2015 180:1-10
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Abdullah Mohammed Amin Tashkandi, Mohammed Y Al-Hindi, Abdulrahman Bassam Albassam, Waiel Ahmed Alkhotani, Zeyad Mohammed Alshamrani, Mansour Abdullah AlQurashi
Publikováno v:
Journal of Clinical Neonatology. 10:37
Background: Preterm birth is the most significant factor for infant morbidity and mortality. Preterm infants are highly vulnerable to substantial comorbidities and need to be admitted to the neonatal intensive care unit (NICU). Prematurity and low bi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::39b81ebd0de52465e471afbf07e2df6b
https://doi.org/10.4103/jcn.jcn_204_20
https://doi.org/10.4103/jcn.jcn_204_20