Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Anastasia Pentina"'
Autor:
Wouter Heyndrickx, Adam Arany, Jaak Simm, Anastasia Pentina, Noé Sturm, Lina Humbeck, Lewis Mervin, Adam Zalewski, Martijn Oldenhof, Peter Schmidtke, Lukas Friedrich, Regis Loeb, Arina Afanasyeva, Ansgar Schuffenhauer, Yves Moreau, Hugo Ceulemans
Publikováno v:
Artificial Intelligence in the Life Sciences, Vol 3, Iss , Pp 100070- (2023)
In a drug discovery setting, pharmaceutical companies own substantial but confidential datasets. The MELLODDY project developed a privacy-preserving federated machine learning solution and deployed it at an unprecedented scale. Each partner built mod
Externí odkaz:
https://doaj.org/article/c22676311fae4ecf96bc8d92b6788cad
Autor:
Wouter Heyndrickx, Lewis Mervin, Tobias Morawietz, Noé Sturm, Lukas Friedrich, Adam Zalewski, Anastasia Pentina, Lina Humbeck, Martijn Oldenhof, Ritsuya Niwayama, Peter Schmidtke, Nikolas Fechner, Jaak Simm, Adam Arany, Nicolas Drizard, Rama Jabal, Arina Afanasyeva, Regis Loeb, Shlok Verma, Simon Harnqvist, Matthew Holmes, Balasz Pejo, Maria Telenczuk, Nicholas Holway, Arne Dieckmann, Nicola Rieke, Friederike Zumsande, Djork-Arné Clevert, Michael Krug, Christopher Luscombe, Darren Green, Peter Ertl, Peter Antal, David Marcus, Nicolas Do Huu, Hideyoshi Fuji, Stephen Pickett, Gergely Acs, Eric Boniface, Bernd Beck, Yax Sun, Arnaud Gohier, Friedrich Rippmann, Ola Engkvist, Andreas H. Göller, Yves Moreau, Mathieu N. Galtier, Ansgar Schuffenhauer, Hugo Ceulemans
Federated multi-partner machine learning can be an appealing and efficient method to increase the effective training data volume and thereby the predictivity of models, particularly when the generation of training data is resource intensive. In the l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8072552725a14731d649af1b8aedc958
https://doi.org/10.26434/chemrxiv-2022-ntd3r
https://doi.org/10.26434/chemrxiv-2022-ntd3r
Autor:
Wouter Heyndrickx, Adam Arany, Jaak Simm, Anastasia Pentina, Noe Sturm, Lina Humbeck, Lewis Mervin, Adam Zalewski, Martijn Oldenhof, Peter Schmidtke, Lukas Friedrich, Regis Loeb, Arina Afanasyeva, Yves Moreau, Hugo Ceulemans
As training volume increases predictive model quality, leveraging existing external data sources holds the promise of time- and cost-efficiency. In a drug discovery setting, pharmaceutical companies all own substantial but confidential datasets. The
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3f77674e1a81c93db41d413ae8829209
https://doi.org/10.26434/chemrxiv-2022-j3xfk
https://doi.org/10.26434/chemrxiv-2022-j3xfk
Autor:
Brunner Dominik, Jonas Meyer, Christoph Hueglin, Michael Mueller, Fernando Perez-Cruz, Lukas Emmenegger, Peter Graf, Anastasia Pentina
More than 300 LP8 CO2 sensors were integrated into sensor units and evaluated for the purpose of long-term operation in the Carbosense CO2 sensor network in Switzerland. Prior to deployment, all sensors were calibrated in a pressure and climate chamb
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e946c0fcd2fc9ded2ac0cdada812eec
https://doi.org/10.5194/amt-2019-408
https://doi.org/10.5194/amt-2019-408
Autor:
Michael Mueller, Peter Graf, Jonas Meyer, Anastasia Pentina, Brunner Dominik, Fernando Perez-Cruz, Christoph Hueglin, Lukas Emmenegger
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::44e6037adad6fa0818dca5273e1d62c0
https://doi.org/10.5194/amt-2019-408-supplement
https://doi.org/10.5194/amt-2019-408-supplement
Autor:
Shai Ben-David, Anastasia Pentina
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783319244853
ALT
ALT
We consider a problem of learning kernels for use in SVM classification in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin classifier. Our results show that, under mild conditions on the family o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d7b1628cf5cfbb3ed6b6cf5089faa71d
https://doi.org/10.1007/978-3-319-24486-0_13
https://doi.org/10.1007/978-3-319-24486-0_13
Publikováno v:
IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
CVPR
CVPR
Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4fb3eb3ab730063989e3c738eb6e2a23
Transfer learning has received a lot of attention in the machine learning community over the last years, and several effective algorithms have been developed. However, relatively little is known about their theoretical properties, especially in the s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5b9e69628fd40da686d68a5a4a76eec1
http://arxiv.org/abs/1311.2838
http://arxiv.org/abs/1311.2838