Zobrazeno 1 - 10
of 302
pro vyhledávání: '"Langseth, Helge"'
Autor:
Kjærnli, Håkon Hanisch, Mas-Ribas, Lluis, Ashrafi, Aida, Sizov, Gleb, Langseth, Helge, Gundersen, Odd Erik
A common issue for machine learning models applied to time-series forecasting is the temporal evolution of the data distributions (i.e., concept drift). Because most of the training data does not reflect such changes, the models present poor performa
Externí odkaz:
http://arxiv.org/abs/2403.03508
Autor:
Strümke, Inga, Langseth, Helge
Diffusion models are loosely modelled based on non-equilibrium thermodynamics, where \textit{diffusion} refers to particles flowing from high-concentration regions towards low-concentration regions. In statistics, the meaning is quite similar, namely
Externí odkaz:
http://arxiv.org/abs/2312.10393
An emerging definition of fairness in machine learning requires that models are oblivious to demographic user information, e.g., a user's gender or age should not influence the model. Personalized recommender systems are particularly prone to violati
Externí odkaz:
http://arxiv.org/abs/2308.15230
Autor:
Vassøy, Bjørnar, Langseth, Helge
In the current landscape of ever-increasing levels of digitalization, we are facing major challenges pertaining to scalability. Recommender systems have become irreplaceable both for helping users navigate the increasing amounts of data and, converse
Externí odkaz:
http://arxiv.org/abs/2305.09330
Within the field of prognostics and health management (PHM), health indicators (HI) can be used to aid the production and, e.g. schedule maintenance and avoid failures. However, HI is often engineered to a specific process and typically requires larg
Externí odkaz:
http://arxiv.org/abs/2208.05208
Autor:
Stubberud, Anker1,2 (AUTHOR), Langseth, Helge1,3 (AUTHOR), Nachev, Parashkev4 (AUTHOR), Matharu, Manjit S.1,5 (AUTHOR), Tronvik, Erling1,2,6 (AUTHOR) erling.tronvik@ntnu.no
Publikováno v:
Cephalalgia. Aug2024, Vol. 44 Issue 8, p1-13. 13p.
Publikováno v:
In Applied Ocean Research December 2024 153
Publikováno v:
In Marine Structures March 2024 94
Autor:
Bekkemoen, Yanzhe, Langseth, Helge
Neural networks (NNs) have shown high predictive performance, however, with shortcomings. Firstly, the reasons behind the classifications are not fully understood. Several explanation methods have been developed, but they do not provide mechanisms fo
Externí odkaz:
http://arxiv.org/abs/2105.02653
Autor:
Danelakis, Antonios1,2 (AUTHOR) antonios.danelakis@ntnu.no, Langseth, Helge1,2 (AUTHOR), Nachev, Parashkev3 (AUTHOR), Nelson, Amy3 (AUTHOR), Bjørk, Marte-Helene1,4,5 (AUTHOR), Matharu, Manjit S.1,6 (AUTHOR), Tronvik, Erling1,7 (AUTHOR), May, Arne1,8 (AUTHOR), Stubberud, Anker1,7 (AUTHOR)
Publikováno v:
Cephalalgia. May2024, Vol. 44 Issue 5, p1-11. 11p.