Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Loppi, Niki"'
Autor:
Witherden, Freddie D., Vincent, Peter E., Trojak, Will, Abe, Yoshiaki, Akbarzadeh, Amir, Akkurt, Semih, Alhawwary, Mohammad, Caros, Lidia, Dzanic, Tarik, Giangaspero, Giorgio, Iyer, Arvind S., Jameson, Antony, Koch, Marius, Loppi, Niki, Mishra, Sambit, Modi, Rishit, Sáez-Mischlich, Gonzalo, Park, Jin Seok, Vermeire, Brian C., Wang, Lai
PyFR is an open-source cross-platform computational fluid dynamics framework based on the high-order Flux Reconstruction approach, specifically designed for undertaking high-accuracy scale-resolving simulations in the vicinity of complex engineering
Externí odkaz:
http://arxiv.org/abs/2408.16509
Differentially private stochastic gradient descent (DP-SGD) is the standard algorithm for training machine learning models under differential privacy (DP). The most common DP-SGD privacy accountants rely on Poisson subsampling for ensuring the theore
Externí odkaz:
http://arxiv.org/abs/2406.17298
We introduce visual hints expansion for guiding stereo matching to improve generalization. Our work is motivated by the robustness of Visual Inertial Odometry (VIO) in computer vision and robotics, where a sparse and unevenly distributed set of featu
Externí odkaz:
http://arxiv.org/abs/2211.00392
We introduce a scalable approach to Gaussian process inference that combines spatio-temporal filtering with natural gradient variational inference, resulting in a non-conjugate GP method for multivariate data that scales linearly with respect to time
Externí odkaz:
http://arxiv.org/abs/2111.01732
Publikováno v:
Proceedings on Privacy Enhancing Technologies, 2022(2), 407-425
We present d3p, a software package designed to help fielding runtime efficient widely-applicable Bayesian inference under differential privacy guarantees. d3p achieves general applicability to a wide range of probabilistic modelling problems by imple
Externí odkaz:
http://arxiv.org/abs/2103.11648
Publikováno v:
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
We introduce visual hints expansion for guiding stereo matching to improve generalization. Our work is motivated by the robustness of Visual Inertial Odometry (VIO) in computer vision and robotics, where a sparse and unevenly distributed set of featu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::36f12da95eb5e6a85e5206daac316c41
https://doi.org/10.1109/wacv56688.2023.00579
https://doi.org/10.1109/wacv56688.2023.00579
The similarity of documents represented using static word embeddings is best measured using second-order metrics accounting for the covariance of the embeddings. Transformers provide superior representations for words compared to static embeddings, b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1593::3b3d0a542487258e1a6f258edc09f131
http://hdl.handle.net/10138/357188
http://hdl.handle.net/10138/357188
Publikováno v:
Pölönen, H, Loppi, N & Hundt, C 2021, ' Experiences on generating synthetic medical data with GAN models ', FCAI AI Day 2021, Finland, 4/11/21-4/11/21 .
Medical data is privacy-sensitive and protected by national legislation and GDPR making data sharing between hospitals and research organizations difficult. In addition, the amount of data for a specific medical condition and imaging modality can be
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=355e65625b88::7427fcb71419478f7ba1f280eb05a9d3
https://cris.vtt.fi/en/publications/2c20b7ca-d9f9-4410-8d97-d0f8ea8d0862
https://cris.vtt.fi/en/publications/2c20b7ca-d9f9-4410-8d97-d0f8ea8d0862
Autor:
Loppi, Niki, Kynkäänniemi, Tuomas
Publisher Copyright: © 2021, Springer Nature Switzerland AG. Copyright: Copyright 2021 Elsevier B.V., All rights reserved. StyleGAN2 is a Tensorflow-based Generative Adversarial Network (GAN) framework that represents the state-of-the-art in generat
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______661::7485664b211c83157fd7058fb36b5187
https://aaltodoc.aalto.fi/handle/123456789/110931
https://aaltodoc.aalto.fi/handle/123456789/110931