Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Ahmet Caner Yuzuguler"'
Publikováno v:
IEEE Micro. 39:55-63
Analog computing is a promising approach to improve the silicon efficiency for inference accelerators in extremely resource-constrained environments. Existing analog circuit proposals for neural networks, however, fall short of realizing the full pot
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4e759cee7408cca759a7298afa45c8f1
https://doi.org/10.1109/mm.2019.2931182
https://doi.org/10.1109/mm.2019.2931182
Publikováno v:
SmartGridComm
System modeling and simulation plays a crucial role in the engineering of large and complex systems from various fields, such as industrial automation or power systems. In this paper, we propose a method that can be used to easily deploy high fidelit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::53e8c03829ee86f690dbe4cbd590fed0
https://doi.org/10.1109/smartgridcomm.2018.8587599
https://doi.org/10.1109/smartgridcomm.2018.8587599
Autor:
Marcel Arditi, G. De Micheli, A. Ibrahim, Jean-Philippe Thiran, Federico Angiolini, William Andrew Simon, Ahmet Caner Yuzuguler
Publikováno v:
DASIP
In medical diagnosis, ultrasound (US) imaging is one of the most common, safe, and powerful techniques. Volumetric (3D) US is potentially very attractive, compared to 2D US, because it might enable telesonography - decoupling the local image acquisit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22cdb0f7b5584dcd9f250a84a0f96517
https://doi.org/10.1109/dasip.2016.7853826
https://doi.org/10.1109/dasip.2016.7853826
Autor:
Jean-Philippe Thiran, Marcel Arditi, William Andrew Simon, Federico Angiolini, G. De Micheli, Ahmet Caner Yuzuguler, A. Ibrahim
Publikováno v:
FPL
In medical diagnosis, ultrasound (US) imaging is one of the most common, safe, and powerful techniques. Volumetric (3D) US imaging, an emerging technique, is even more attractive than standard 2D imaging, as it allows for imaging without the local pr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cdb20fe7d593c0e0ae008b4b9b3d9a44
https://doi.org/10.1109/fpl.2016.7577387
https://doi.org/10.1109/fpl.2016.7577387
Autor:
G. De Micheli, William Andrew Simon, Marcel Arditi, Jean-Philippe Thiran, Federico Angiolini, A. Ibrahim, Ahmet Caner Yuzuguler
Publikováno v:
FPL
We present an efficient FPGA architecture suitable for a medical 3D ultrasound beamformer. We tackle the delay calculation bottleneck, which is the heart and the most critical part of the beam-former, by proposing a computationally efficient design t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::af389067dc8a5303caf7c78d7fa1485d
https://doi.org/10.1109/fpl.2016.7577391
https://doi.org/10.1109/fpl.2016.7577391
Publikováno v:
ICASSP
Sparse representations of images in well-designed dictionaries can be used for effective classification. Meanwhile, training data available in most realistic settings are likely to be exposed to geometric transformations, which poses a challenge for
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1ed577b5c0337373c1fe8a8a106132b
https://doi.org/10.1109/icassp.2014.6854264
https://doi.org/10.1109/icassp.2014.6854264
Autor:
Louis Coulon, Ahmet Caner Yuzuguler, Babak Falsafi, Arash Pourhabibi, Mario Drumond, Martin Jaggi
Publikováno v:
MICRO
DNN inference accelerators executing online services exhibit low average loads because of service demand variability, leading to poor resource utilization. Unfortunately, reclaiming idle inference cycles is difficult as other workloads can not execut
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::880c2c3830a23aa6d7504cde2a40f6b9
https://infoscience.epfl.ch/record/288715
https://infoscience.epfl.ch/record/288715
Autor:
A. Ibrahim, G. De Micheli, M. Arditi, Federico Angiolini, William Andrew Simon, Jean-Philippe Thiran, Ahmet Caner Yuzuguler
Publikováno v:
DATE
3D ultrasound, an emerging medical imaging technique that is presently only used in hospitals, has the potential to enable breakthrough telemedicine applications, provided that its cost and power dissipation can be minimized. In this paper, we presen
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a6a70bdce6679e602af760e0f0b2e55e
https://infoscience.epfl.ch/record/230867
https://infoscience.epfl.ch/record/230867