Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Ashkan Panahi"'
Publikováno v:
Mathematics, Vol 9, Iss 2, p 168 (2021)
The purpose of this paper is to infer a dynamic graph as a global (collective) model of time-varying measurements at a set of network nodes. This model captures both pairwise as well as higher order interactions (i.e., more than two nodes) among the
Externí odkaz:
https://doaj.org/article/6cbc7394cc9c451c895cfacba4e5869e
Publikováno v:
Optical Fiber Communication Conference (OFC) 2023.
MLaaS is introduced in the context of optical networks, and an architecture to take advantage of its potential is proposed. A use case of QoT classification using MLaaS techniques is benchmarked against state-of-the-art methods.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2b2470743ab7475d5d039c23d5a5b5f6
https://doi.org/10.1364/ofc.2023.w4g.3
https://doi.org/10.1364/ofc.2023.w4g.3
Publikováno v:
IEEE Sensors Journal. 20:12307-12316
Robust Subspace Recovery (RoSuRe) algorithm was recently introduced as a principled and numerically efficient algorithm that unfolds underlying Unions of Subspaces (UoS) structure, present in the data. The union of Subspaces (UoS) is capable of ident
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::876da49d2b257287d3e72fdbac434c30
https://doi.org/10.1109/jsen.2020.2999461
https://doi.org/10.1109/jsen.2020.2999461
Publikováno v:
Theoretical Computer Science. 812:203-213
There have been a number of recent advances in accelerated gradient and proximal schemes for optimization of convex finite sum problems. Defazio introduced a simple accelerated scheme for incremental stochastic proximal algorithms inspired by gradien
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d292e5e40871bdffd3ec5c7f84a07e37
https://doi.org/10.1016/j.tcs.2019.10.030
https://doi.org/10.1016/j.tcs.2019.10.030
Publikováno v:
Signal Processing. 152:148-159
The success of sparse models in computer vision and machine learning is due to the fact that, high dimensional data is distributed in a union of low dimensional subspaces in many real-world applications. The underlying structure may, however, be adve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fa5275f1f430341f303c7b2988b3ef2f
https://doi.org/10.1016/j.sigpro.2018.05.024
https://doi.org/10.1016/j.sigpro.2018.05.024
Autor:
Mats Viberg, Ashkan Panahi
Publikováno v:
IEEE Transactions on Signal Processing. 65:6478-6488
Since the advent of the $\ell _1$ regularized least squares method (LASSO), a new line of research has emerged, which has been geared toward the application of the LASSO to parameter estimation problems. Recent years witnessed a considerable progress
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::46e3b7aa2f1cebefe6c272d3689b609c
https://doi.org/10.1109/tsp.2017.2755602
https://doi.org/10.1109/tsp.2017.2755602
We investigate the widely encountered problem of detecting communities in multiplex networks, such as social networks, with an unknown arbitrary heterogeneous structure. To improve detectability, we propose a generative model that leverages the multi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a0786d25edfbef8af991d9d1b0d9c6e4
http://arxiv.org/abs/1909.10477
http://arxiv.org/abs/1909.10477
Publikováno v:
ICCV Workshops
We propose a new approach to Generative Adversarial Networks (GANs) to achieve an improved performance with additional robustness to its so-called and well recognized mode collapse. We first proceed by mapping the desired data onto a frame-based spac
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8d5d7b0789f9841d2564ff51b44c05f1
http://arxiv.org/abs/1908.08930
http://arxiv.org/abs/1908.08930
Publikováno v:
ICASSP
We propose a deep learning architecture capable of performing up to 8× single image super-resolution. Our architecture incorporates an adversarial component from the super-resolution generative adversarial networks (SRGANs) and a multi-scale learnin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8681e99c42b0f9163ef22bc18367abbf
https://doi.org/10.1109/icassp.2019.8682354
https://doi.org/10.1109/icassp.2019.8682354
Publikováno v:
ICASSP
Discriminative Dictionary Learning (DL) methods have been widely advocated for image classification problems. To further sharpen their discriminative capabilities, most state-of-the-art DL methods have additional constraints included in the learning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::dc896442be4743047acc62f93d905cfc