Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Kiani, Bobak Toussi"'
Autor:
Kiani, Bobak Toussi.
Thesis: S.M., Massachusetts Institute of Technology, Department of Mechanical Engineering, May, 2020
Cataloged from the official PDF of thesis.
Includes bibliographical references (pages 77-83).
Linear algebra is a simple yet elegant m
Cataloged from the official PDF of thesis.
Includes bibliographical references (pages 77-83).
Linear algebra is a simple yet elegant m
Externí odkaz:
https://hdl.handle.net/1721.1/127158
Publikováno v:
Quantum Science and Technology 7(4), 045002 (2022)
Quantifying how far the output of a learning algorithm is from its target is an essential task in machine learning. However, in quantum settings, the loss landscapes of commonly used distance metrics often produce undesirable outcomes such as poor lo
Externí odkaz:
http://arxiv.org/abs/2101.03037
A central task in medical imaging is the reconstruction of an image or function from data collected by medical devices (e.g., CT, MRI, and PET scanners). We provide quantum algorithms for image reconstruction with exponential speedup over classical c
Externí odkaz:
http://arxiv.org/abs/2004.02036
We study the hardness of learning unitary transformations in $U(d)$ via gradient descent on time parameters of alternating operator sequences. We provide numerical evidence that, despite the non-convex nature of the loss landscape, gradient descent a
Externí odkaz:
http://arxiv.org/abs/2001.11897
Publikováno v:
Advances in Neural Information Processing Systems 32, 1962-1974 (2019)
We prove that the binary classifiers of bit strings generated by random wide deep neural networks with ReLU activation function are biased towards simple functions. The simplicity is captured by the following two properties. For any given input bit s
Externí odkaz:
http://arxiv.org/abs/1812.10156
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Bobak Toussi Kiani, Giacomo De Palma, Dirk Englund, William Kaminsky, Milad Marvian, Seth Lloyd
Publikováno v:
Physical Review A. 105
Quantum algorithms for differential equation solving, data processing, and machine learning potentially offer an exponential speedup over all known classical algorithms. However, there also exist obstacles to obtaining this potential speedup in usefu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f52d03b6b5925b1782b0bfaadf126de4
https://doi.org/10.1103/physreva.105.022415
https://doi.org/10.1103/physreva.105.022415
Quantifying how far the output of a learning algorithm is from its target is an essential task in machine learning. However, in quantum settings, the loss landscapes of commonly used distance metrics often produce undesirable outcomes such as poor lo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9016d81ac06d4aa74d69296c46d1e5ee
http://arxiv.org/abs/2101.03037
http://arxiv.org/abs/2101.03037