Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Stefan Pechmann"'
Autor:
Kristina Nikiruy, Eduardo Perez, Andrea Baroni, Keerthi Dorai Swamy Reddy, Stefan Pechmann, Christian Wenger, Martin Ziegler
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-11 (2024)
Abstract Blooming and pruning is one of the most important developmental mechanisms of the biological brain in the first years of life, enabling it to adapt its network structure to the demands of the environment. The mechanism is thought to be funda
Externí odkaz:
https://doaj.org/article/d240a07a7079409997238de754e162bc
Autor:
Daniel Reiser, Peter Reichel, Stefan Pechmann, Maen Mallah, Maximilian Oppelt, Amelie Hagelauer, Marco Breiling, Dietmar Fey, Marc Reichenbach
Publikováno v:
Journal of Low Power Electronics and Applications, Vol 12, Iss 1, p 2 (2021)
In embedded applications that use neural networks (NNs) for classification tasks, it is important to not only minimize the power consumption of the NN calculation, but of the whole system. Optimization approaches for individual parts exist, such as q
Externí odkaz:
https://doaj.org/article/68ac0723146c4766a5980d12aa86f3f3
Autor:
Stefan Pechmann, Timo Mai, Julian Potschka, Daniel Reiser, Peter Reichel, Marco Breiling, Marc Reichenbach, Amelie Hagelauer
Publikováno v:
Micromachines, Vol 12, Iss 11, p 1277 (2021)
Pattern recognition as a computing task is very well suited for machine learning algorithms utilizing artificial neural networks (ANNs). Computing systems using ANNs usually require some sort of data storage to store the weights and bias values for t
Externí odkaz:
https://doaj.org/article/562cb5742c42492f993e25ce25091a4c
Autor:
Stefan Pechmann, Amelie Hagelauer
Publikováno v:
2022 IEEE 35th International System-on-Chip Conference (SOCC).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1e60c4d2893e96020a577846e5ffaebb
https://doi.org/10.1109/socc56010.2022.9908137
https://doi.org/10.1109/socc56010.2022.9908137
Autor:
Stefan Pechmann, Amelie Hagelauer
Publikováno v:
2022 IEEE 65th International Midwest Symposium on Circuits and Systems (MWSCAS).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cfdb1e39a451286fcc69f370fa98ed35
https://doi.org/10.1109/mwscas54063.2022.9859436
https://doi.org/10.1109/mwscas54063.2022.9859436
Autor:
Markus Fritscher, Johannes Knödtel, Maen Mallah, Stefan Pechmann, Emilio Perez-Bosch Quesada, Tommaso Rizzi, Christian Wenger, Marc Reichenbach
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031045790
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::534856f29d7c8634909880e01899c620
https://doi.org/10.1007/978-3-031-04580-6_27
https://doi.org/10.1007/978-3-031-04580-6_27
Autor:
Markus Fritscher, Dietmar Fey, Marc Reichenbach, Stefan Pechmann, Daniel Reiser, Johannes Knodtel, Maen Mallah
Publikováno v:
LASCAS
In this paper we present a method to evaluate the behavior of neuronal network (NN) architectures, concerning the error rate of RRAM devices used as weight storage, relative to fabrication variances. While the behavior of non-ideal RRAM devices can c
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d6483b9d140bb7612ef676f1fe348b2e
https://doi.org/10.1109/lascas51355.2021.9459159
https://doi.org/10.1109/lascas51355.2021.9459159
Autor:
Stefan Pechmann, John Reuben
To overcome the “von Neumann bottleneck,” methods to compute in memory are being researched in many emerging memory technologies, including resistive RAMs (ReRAMs). Majority logic is efficient for synthesizing arithmetic circuits when compared to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2aadd958b15256c628b4795ac8db93f5
https://opus4.kobv.de/opus4-fau/files/16146/AuthorsVersion_TVLSI2021.pdf
https://opus4.kobv.de/opus4-fau/files/16146/AuthorsVersion_TVLSI2021.pdf
Autor:
Stefan Pechmann, Herman Jalli Ng, Matthias Voelkel, Robert Weigel, Dietmar Kissinger, Amelie Hagelauer
Publikováno v:
2020 IEEE/MTT-S International Microwave Symposium (IMS).
In this paper, a scalable, fully digital adjustable, bistatic 60 GHz MIMO six-port transceiver is presented. The circuit features four independent transmitters and four six-port receivers on a single chip. The reference clock frequency of 15 GHz is b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::62bade1b8d26f65f3c35f59f59dd26b7
https://doi.org/10.1109/ims30576.2020.9224001
https://doi.org/10.1109/ims30576.2020.9224001
Autor:
Stefan Pechmann, John Reuben
Publikováno v:
ASAP
Efforts to combat the ‘von Neumann bottleneck’ have been strengthened by Resistive RAMs (RRAMs), which enable computation in the memory array. Majority logic can accelerate computation when compared to NAND/NOR/IMPLY logic due to it’s expressiv
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0ecb60616b793d26f28336a16ab477bb
https://opus4.kobv.de/opus4-fau/files/14051/PID6490015_AuthorsVersion.pdf
https://opus4.kobv.de/opus4-fau/files/14051/PID6490015_AuthorsVersion.pdf