Zobrazeno 1 - 10
of 311
pro vyhledávání: '"Heikkilä, Mikko"'
Emissions of non-road machines are reduced by precise control of combustion process inside the engine and by after-treatment systems. One additional measure is the hybridization of the powertrain, which can be used to stabilize the engine load. This
Externí odkaz:
https://tud.qucosa.de/id/qucosa%3A71222
https://tud.qucosa.de/api/qucosa%3A71222/attachment/ATT-0/
https://tud.qucosa.de/api/qucosa%3A71222/attachment/ATT-0/
Publikováno v:
Transactions on Machine Learning Research, ISSN 2835-8856, 2023
Learning a privacy-preserving model from sensitive data which are distributed across multiple devices is an increasingly important problem. The problem is often formulated in the federated learning context, with the aim of learning a single global mo
Externí odkaz:
http://arxiv.org/abs/2209.11595
Publikováno v:
In Atmospheric Environment: X August 2024 23
Shuffle model of differential privacy is a novel distributed privacy model based on a combination of local privacy mechanisms and a secure shuffler. It has been shown that the additional randomisation provided by the shuffler improves privacy bounds
Externí odkaz:
http://arxiv.org/abs/2106.00477
Publikováno v:
In Transport Policy March 2024 148:168-180
Autor:
Napari, Mari, Huq, Tahmida N., Meeth, David J., Heikkilä, Mikko J., Niang, Kham M., Wang, Han, Iivonen, Tomi, Wang, Haiyan, Leskelä, Markku, Ritala, Mikko, Flewitt, Andrew J., Hoye, Robert L. Z., MacManus-Driscol, Judith L.
High-performance p-type oxide thin film transistors (TFTs) have great potential for many semiconductor applications. However, these devices typically suffer from low hole mobility and high off-state currents. We fabricated p-type TFTs with a phase-pu
Externí odkaz:
http://arxiv.org/abs/2010.10928
Strict privacy is of paramount importance in distributed machine learning. Federated learning, with the main idea of communicating only what is needed for learning, has been recently introduced as a general approach for distributed learning to enhanc
Externí odkaz:
http://arxiv.org/abs/2007.05553
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Recent developments in differentially private (DP) machine learning and DP Bayesian learning have enabled learning under strong privacy guarantees for the training data subjects. In this paper, we further extend the applicability of DP Bayesian learn
Externí odkaz:
http://arxiv.org/abs/1901.10275