Zobrazeno 1 - 10
of 267
pro vyhledávání: '"Mahdiyar P"'
In this paper, we propose a novel approach, Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training (FedSB), to address the challenges of data heterogeneity within a federated learning framework. FedSB utilizes label
Externí odkaz:
http://arxiv.org/abs/2412.11408
Publikováno v:
Proceedings of the SPIE, Volume 13097, id. 1309783 10 pp. (2024)
Adaptive optics (AO) systems are crucial for high-resolution astronomical observations by compensating for atmospheric turbulence. While laser guide stars (LGS) address high-order wavefront aberrations, natural guide stars (NGS) remain vital for low-
Externí odkaz:
http://arxiv.org/abs/2410.12084
Autor:
Noorbala, Mahdiyar
Publikováno v:
JCAP10(2024)053
It is well known that a coarse-grained scalar field living on a de~Sitter (dS) background exhibits classical stochastic behavior, driven by a noise whose amplitude is set by the Hubble constant $H$. The coarse-graining is achieved by discarding wave
Externí odkaz:
http://arxiv.org/abs/2408.11640
We address the problem of federated domain generalization in an unsupervised setting for the first time. We first theoretically establish a connection between domain shift and alignment of gradients in unsupervised federated learning and show that al
Externí odkaz:
http://arxiv.org/abs/2405.16304
Autor:
Mousavi-Sadr, Mahdiyar
The number of extrasolar planets discovered is increasing, so that more than five thousand exoplanets have been confirmed to date. Now we have an opportunity to test the validity of the laws governing planetary systems and take steps to discover the
Externí odkaz:
http://arxiv.org/abs/2402.17898
A continual learning solution is proposed to address the out-of-distribution generalization problem for pedestrian detection. While recent pedestrian detection models have achieved impressive performance on various datasets, they remain sensitive to
Externí odkaz:
http://arxiv.org/abs/2306.15117
The Long-Tailed Recognition (LTR) problem emerges in the context of learning from highly imbalanced datasets, in which the number of samples among different classes is heavily skewed. LTR methods aim to accurately learn a dataset comprising both a la
Externí odkaz:
http://arxiv.org/abs/2306.13275
The tail of the distribution of primordial fluctuations (corresponding to the likelihood of realization of large fluctuations) is of interest, from both theoretical and observational perspectives. In particular, it is relevant for the accurate evalua
Externí odkaz:
http://arxiv.org/abs/2305.19257
The growing number of exoplanet discoveries and advances in machine learning techniques have opened new avenues for exploring and understanding the characteristics of worlds beyond our Solar System. In this study, we employ efficient machine learning
Externí odkaz:
http://arxiv.org/abs/2301.07143
Autor:
Mehrdad Kashefi, Sasha Reschechtko, Giacomo Ariani, Mahdiyar Shahbazi, Alice Tan, Jörn Diedrichsen, J Andrew Pruszynski
Publikováno v:
eLife, Vol 13 (2024)
Real-world actions often comprise a series of movements that cannot be entirely planned before initiation. When these actions are executed rapidly, the planning of multiple future movements needs to occur simultaneously with the ongoing action. How t
Externí odkaz:
https://doaj.org/article/1babca7d82044045ba453058004aca9c
