Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Matthias Freiberger"'
Publikováno v:
Applied Sciences, Vol 12, Iss 24, p 12615 (2022)
In this paper, we propose a methodology to accurately evaluate and compare the performance of efficient neural network building blocks for computer vision in a hardware-aware manner. Our comparison uses pareto fronts based on randomly sampled network
Externí odkaz:
https://doaj.org/article/a8b53222bbe24b46966c332456eab70f
Publikováno v:
Intelligent Data Engineering and Automated Learning – IDEAL 2022 ISBN: 9783031217524
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Intelligent Data Engineering and Automated Learning – IDEAL 2022
Intelligent Data Engineering and Automated Learning – IDEAL 2022
Lecture Notes in Computer Science
Lecture Notes in Computer Science-Intelligent Data Engineering and Automated Learning – IDEAL 2022
Intelligent Data Engineering and Automated Learning – IDEAL 2022
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c47455deec398c86aa645f1a004bd00c
https://doi.org/10.1007/978-3-031-21753-1_21
https://doi.org/10.1007/978-3-031-21753-1_21
Publikováno v:
COMPUTER VISION AND IMAGE UNDERSTANDING
This paper proposes anchor pruning for object detection in one-stage anchor-based detectors. While pruning techniques are widely used to reduce the computational cost of convolutional neural networks, they tend to focus on optimizing the backbone net
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15da5aee710a2645299af17862e3ab2c
Autor:
Matthias Freiberger, Andrew Katumba, Chonghuai Ma, Stijn Sackesyn, Floris Laporte, Peter Bienstman, Joni Dambre
Publikováno v:
Natural Computing Series ISBN: 9789811316869
The idea of using photonic systems as reservoirs to perform general-purpose computing was first introduced in 2008. Since then, a wide range of systems using either discrete or integrated optical components has been explored. In this chapter, we summ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::272bdbc56680148b411fe726a8d17ac3
https://doi.org/10.1007/978-981-13-1687-6_17
https://doi.org/10.1007/978-981-13-1687-6_17
Autor:
Joni Dambre, Peter Bienstman, Chonghuai Ma, Floris Laporte, Stijn Sackesyn, Andrew Katumba, Matthias Freiberger, Alessio Lugnan
Publikováno v:
IEEE Journal of Selected Topics in Quantum Electronics
IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS
IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS
We present our latest progress using new neuromorphic paradigms for optical information processing in silicon photonics. We show how passive reservoir computing chips can be used to perform a variety of tasks (bit level tasks, nonlinear dispersion co
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d9058374554ae217a1caaa8d41821a8
https://doi.org/10.1109/jstqe.2018.2821843
https://doi.org/10.1109/jstqe.2018.2821843
Publikováno v:
SCIENTIFIC REPORTS
Scientific Reports
Scientific Reports, Vol 10, Iss 1, Pp 1-11 (2020)
Scientific Reports
Scientific Reports, Vol 10, Iss 1, Pp 1-11 (2020)
Physical reservoir computing approaches have gained increased attention in recent years due to their potential for low-energy high-performance computing. Despite recent successes, there are bounds to what one can achieve simply by making physical res
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::00ee7abd726f560d7d8fe6f7db20ba57
https://biblio.ugent.be/publication/8692664
https://biblio.ugent.be/publication/8692664
Autor:
Matthias Freiberger, Andrew Katumba, Alessio Lugnan, Floris Laporte, Chonghuai Ma, Stijn Sackesyn, Joni Dambre, Emmanuel Gooskens, Peter Bienstman
Publikováno v:
APL Photonics
APL PHOTONICS
APL PHOTONICS
Photonic neuromorphic computing is attracting tremendous research interest now, catalyzed in no small part by the rise of deep learning in many applications. In this paper, we will review some of the exciting work that has been going in this area and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::42d348f1ac39f68c041c67911ea13754
Autor:
Andrew Katumba, Peter Bienstman, Matthias Freiberger, Stijn Sackesyn, Joni Dambre, Chonghuai Ma
Publikováno v:
IEEE JOURNAL OF SELECTED TOPICS IN QUANTUM ELECTRONICS
As the performance increase of traditional Von-Neumann computing attenuates, new approaches to computing need to be found. A promising approach for low-power computing at high bitrates is integrated photonic reservoir computing. In the past though, t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::546e5a5109a6173b040df0d4e39de4d0
https://hdl.handle.net/1854/LU-8638399
https://hdl.handle.net/1854/LU-8638399
Autor:
Matthias Freiberger, Alessio Lugnan, Andrew Katumba, Stijn Sackesyn, Chonghuai Ma, Joni Dambre, Peter Bienstman, Floris Laporte
Publikováno v:
Photonic Reservoir Computing
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::852d7bd8d9f037936e95d1b0531cbabf
https://doi.org/10.1515/9783110583496-003
https://doi.org/10.1515/9783110583496-003
Autor:
Chonghuai Ma, Joni Dambre, Matthias Freiberger, Peter Bienstman, Andrew Katumba, Alessio Lugnan, Floris Laporte, Stijn Sackesyn
Publikováno v:
Proceedings Volume 11081, Active Photonic Platforms XI
Active Photonic Platforms XI
Active Photonic Platforms XI
We present our latest results on silicon photonics neuromorphic information processing based a.o. on techniques like reservoir computing. First, we dicuss how passive reservoir computing can be used to perform non-linear signal equalisation in teleco
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6410f99800d40ac35ba7b593b750e770