Zobrazeno 1 - 10
of 57
pro vyhledávání: '"Tomas Nordström"'
Publikováno v:
Information, Vol 13, Iss 4, p 176 (2022)
Recurrent neural networks (RNNs) are neural networks (NN) designed for time-series applications. There is a growing interest in running RNNs to support these applications on edge devices. However, RNNs have large memory and computational demands that
Externí odkaz:
https://doaj.org/article/2eff7712d1e44a04ac0c7fd2b8165289
Autor:
Ramiro Sámano-Robles, Tomas Nordström, Kristina Kunert, Salvador Santonja-Climent, Mikko Himanka, Markus Liuska, Michael Karner, Eduardo Tovar
Publikováno v:
Technologies, Vol 9, Iss 4, p 99 (2021)
This paper presents the High-Level Architecture (HLA) of the European research project DEWI (Dependable Embedded Wireless Infrastructure). The objective of this HLA is to serve as a reference framework for the development of industrial Wireless Senso
Externí odkaz:
https://doaj.org/article/709507717782478b9b1ed550dee8f7cd
Publikováno v:
Computers, Vol 7, Iss 2, p 27 (2018)
The last ten years have seen performance and power requirements pushing computer architectures using only a single core towards so-called manycore systems with hundreds of cores on a single chip. To further increase performance and energy efficiency,
Externí odkaz:
https://doaj.org/article/d1e126f988644d73b9aa9c03a76dc4ed
Publikováno v:
IEEE Access, Vol 8, Pp 57967-57996 (2020)
Recurrent Neural Networks (RNNs) are a class of machine learning algorithms used for applications with time-series and sequential data. Recently, there has been a strong interest in executing RNNs on embedded devices. However, difficulties have arise
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aaa1a1c09a89707f47cf1646767efb7e
https://ieeexplore.ieee.org/document/9044359/
https://ieeexplore.ieee.org/document/9044359/
Publikováno v:
SSRN Electronic Journal.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7244f2d945ae5cd1939eda96b2d14778
https://doi.org/10.2139/ssrn.4141234
https://doi.org/10.2139/ssrn.4141234
Publikováno v:
Information; Volume 13; Issue 4; Pages: 176
Recurrent neural networks (RNNs) are neural networks (NN) designed for time-series applications. There is a growing interest in running RNNs to support these applications on edge devices. However, RNNs have large memory and computational demands that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::efaf4ea0d360742ab6059a4a9ad36af6
https://doi.org/10.3390/info13040176
https://doi.org/10.3390/info13040176
Publikováno v:
Optical Switching and Networking. 24:47-56
High-performance embedded systems running real-time applications demand communication solutions providing high data rates and low error probabilities, properties inherent to optical solutions. However, providing timing guarantees for deadline bound a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::983aa5620c96b10a675075d34aa24345
https://doi.org/10.1016/j.osn.2016.11.004
https://doi.org/10.1016/j.osn.2016.11.004
Using Harmonized Parabolic Synthesis to Implement a Single-Precision Floating-Point Square Root Unit
Publikováno v:
ISVLSI
This paper proposes a novel method for performing square root operation on floating-point numbers represented in IEEE-754 single-precision (binary32) format. The method is implemented using Harmonized Parabolic Synthesis. It is implemented with and w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3333ef81cffdaf30ca4971aefe3012a6
http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-39322
http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-39322
Publikováno v:
Computers; Volume 7; Issue 2; Pages: 27
Computers, Vol 7, Iss 2, p 27 (2018)
Computers, Vol 7, Iss 2, p 27 (2018)
The last ten years have seen performance and power requirements pushing computer architectures using only a single core towards so-called manycore systems with hundreds of cores on a single chip. To further increase performance and energy efficiency,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::05842a3378124c6282dc947cb1f07320
Autor:
Sebastian Raase, Tomas Nordström
Publikováno v:
ICCS
The increased availability of modern embedded many-core architectures supporting floating-point operations in hardware makes them interesting targets in traditional high performance computing areas as well. In this paper, the Lattice Boltzmann Method
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d201ac44d68d3a346fa9b90c7cdacdb7
https://doi.org/10.1016/j.procs.2015.05.348
https://doi.org/10.1016/j.procs.2015.05.348