Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Hampus Linander"'
Publikováno v:
Machine Learning: Science and Technology, Vol 4, Iss 4, p 045032 (2023)
Bayesian inference can quantify uncertainty in the predictions of neural networks using posterior distributions for model parameters and network output. By looking at these posterior distributions, one can separate the origin of uncertainty into alea
Externí odkaz:
https://doaj.org/article/b297eca8815f44b3b0fce0c7832368a9
Autor:
Nicolò Ghielmetti, Vladimir Loncar, Maurizio Pierini, Marcel Roed, Sioni Summers, Thea Aarrestad, Christoffer Petersson, Hampus Linander, Jennifer Ngadiuba, Kelvin Lin, Philip Harris
Publikováno v:
Machine Learning: Science and Technology, 3 (4)
In this paper, we investigate how field programmable gate arrays can serve as hardware accelerators for real-time semantic segmentation tasks relevant for autonomous driving. Considering compressed versions of the ENet convolutional neural network ar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::88109b235b4c3c628cd2f34015476534
http://cds.cern.ch/record/2839971
http://cds.cern.ch/record/2839971
Autor:
Duc Hoang, Nhan Tran, Sioni Summers, Christoffer Petersson, Javier Duarte, Sergo Jindariani, Giuseppe Di Guglielmo, Edward Kreinar, Jennifer Ngadiuba, Kevin Pedro, Dylan Rankin, Maurizio Pierini, Nicolò Ghielmetti, Zhenbin Wu, Philip Harris, Mia Liu, Yutaro Iiyama, Hampus Linander, Vladimir Loncar, Thea Klaeboe Aarrestad
Publikováno v:
Machine Learning Science and Technology
We introduce an automated tool for deploying ultra low-latency, low-power deep neural networks with convolutional layers on FPGAs. By extending the hls4ml library, we demonstrate an inference latency of $5\,\mu$s using convolutional architectures, ta
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::05fc325c7500b44ac1f69bc4e6110cc5
http://arxiv.org/abs/2101.05108
http://arxiv.org/abs/2101.05108
Autor:
Hampus Linander, Bengt E. W. Nilsson
Publikováno v:
Journal of High Energy Physics
In the context of three-dimensional conformal higher spin theory we derive, in the frame field formulation, the full non-linear spin 3 Cotton equation coupled to spin 2. This is done by solving the corresponding Chern-Simons gauge theory system of eq
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ea18d398e543c73e141171bb43d1e337
http://repo.scoap3.org/api
http://repo.scoap3.org/api
Publikováno v:
Journal of High Energy Physics
A $Q$-exact off-shell action is constructed for twisted abelian (2,0) theory on a Lorentzian six-manifold of the form $M_{1,5} = C\times M_4$, where $C$ is a flat two-manifold and $M_4$ is a general Euclidean four-manifold. The properties of this for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c973b6b0df374f9da8673c5afdbef28e
http://arxiv.org/abs/1406.4499
http://arxiv.org/abs/1406.4499
Autor:
Hampus Linander, Louise Anderson
Publikováno v:
Journal of High Energy Physics
We consider a twisted version of the abelian $(2,0)$ theory placed upon a Lorenzian six-manifold with a product structure, $M_6=C \times M_4 $. This is done by an investigation of the free tensor multiplet on the level of equations of motion, where t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::02ef8039a8e23ea23c82890b9a91e8dc
http://repo.scoap3.org/api
http://repo.scoap3.org/api
Autor:
Hampus Linander, Fredrik Ohlsson
Publikováno v:
Journal of High Energy Physics. 2012
We consider (2,0) theory on a manifold M_6 that is a fibration of a spatial S^1 over some five-dimensional base manifold M_5. Initially, we study the free (2,0) tensor multiplet which can be described in terms of classical equations of motion in six
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4fed78d6ee0f6e596797a3c885b50bbc
https://doi.org/10.1007/jhep01(2012)159
https://doi.org/10.1007/jhep01(2012)159