Zobrazeno 1 - 10
of 221
pro vyhledávání: '"Paolo Bientinesi"'
Publikováno v:
Signals, Vol 4, Iss 4, Pp 768-787 (2023)
Within the broad problem known as automatic music transcription, we considered the specific task of automatic drum transcription (ADT). This is a complex task that has recently shown significant advances thanks to deep learning (DL) techniques. Most
Externí odkaz:
https://doaj.org/article/296379d2f4654301a6b759c59c167941
Publikováno v:
Frontiers in Applied Mathematics and Statistics, Vol 8 (2022)
Externí odkaz:
https://doaj.org/article/db8d7c243c4e401ab3528e5db4a0cf25
Publikováno v:
Frontiers in Applied Mathematics and Statistics, Vol 8 (2022)
The Canonical Polyadic (CP) tensor decomposition is frequently used as a model in applications in a variety of different fields. Using jackknife resampling to estimate parameter uncertainties is often desirable but results in an increase of the alrea
Externí odkaz:
https://doaj.org/article/6f323d3be3bb4b0cbfa59e8fa65e5a2c
Autor:
Jure Vreca, Karl J. X. Sturm, Ernest Gungl, Farhad Merchant, Paolo Bientinesi, Rainer Leupers, Zmago Brezocnik
Publikováno v:
IEEE Access, Vol 8, Pp 165913-165926 (2020)
Deep learning algorithms have seen success in a wide variety of applications, such as machine translation, image and speech recognition, and self-driving cars. However, these algorithms have only recently gained a foothold in the embedded systems dom
Externí odkaz:
https://doaj.org/article/1ec88e37e19545149b19e47d18d31826
Publikováno v:
Emergency Care Journal, Vol 17, Iss 2 (2021)
If acute carbon monoxide poisoning is a well-known emergency situation, this is not the case for chronic poisoning. The missed diagnosis of acute CO poisoning is a well-known problem but the identification of a chronic poisoning is very challenging.
Externí odkaz:
https://doaj.org/article/d20e2c111470440f9c4bb3bafbcbefc5
Publikováno v:
Psarras, C, Karlsson, L, Bro, R & Bientinesi, P 2022, ' Algorithm 1026 : Concurrent Alternating Least Squares for Multiple Simultaneous Canonical Polyadic Decompositions ', ACM Transactions on Mathematical Software, vol. 48, no. 3, 34 . https://doi.org/10.1145/3519383
Tensor decompositions, such as CANDECOMP/PARAFAC (CP), are widely used in a variety of applications, such as chemometrics, signal processing, and machine learning. A broadly used method for computing such decompositions relies on the Alternating Leas
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a22305df4cb53a6e9c0c51ab81191f60
https://doi.org/10.1145/3519383
https://doi.org/10.1145/3519383
Publikováno v:
SIAM journal on scientific computing 43(4), A2660–A2684 (2021). doi:10.1137/20M1313933
Siam Journal on Scientific Computing, 43(4), A2660-A2684. Society for Industrial and Applied Mathematics Publications
Siam Journal on Scientific Computing, 43(4), A2660-A2684. Society for Industrial and Applied Mathematics Publications
In recent years, contour-based eigensolvers have emerged as a standard approach for the solution of large and sparse eigenvalue problems. Building upon recent performance improvements through non-linear least square optimization of so-called rational
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::280c45caea2a02d388ab5367b32a7b82
https://doi.org/10.1137/20m1313933
https://doi.org/10.1137/20m1313933
Publikováno v:
2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW).
Linear algebra operations, which are ubiquitous in machine learning, form major performance bottlenecks. The High-Performance Computing community invests significant effort in the development of architecture-specific optimized kernels, such as those
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::aab833bbc6f570a4f7024a7d296aedb0
https://doi.org/10.1109/ipdpsw55747.2022.00150
https://doi.org/10.1109/ipdpsw55747.2022.00150
Publikováno v:
Frontiers Research Topics ISBN: 9782832504253
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::be9e1838afc41109f1c2de17807433cf
https://doi.org/10.3389/978-2-8325-0425-3
https://doi.org/10.3389/978-2-8325-0425-3
Autor:
Aravind Sankaran, Paolo Bientinesi
Publikováno v:
IPDPS Workshops
In a typical Internet-of-Things setting that involves scientific applications, a target computation can be evaluated in many different ways depending on the split of computations among various devices. On the one hand, different implementations (or a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f985b45241c241b9397796807175e0f1
https://doi.org/10.1109/ipdpsw52791.2021.00132
https://doi.org/10.1109/ipdpsw52791.2021.00132