Zobrazeno 1 - 10
of 180
pro vyhledávání: '"Stoian, Andrei"'
We present an approach to outsourcing of training neural networks while preserving data confidentiality from malicious parties. We use fully homomorphic encryption to build a unified training approach that works on encrypted data and learns quantized
Externí odkaz:
http://arxiv.org/abs/2401.16136
Autor:
Frery, Jordan, Stoian, Andrei, Bredehoft, Roman, Montero, Luis, Kherfallah, Celia, Chevallier-Mames, Benoit, Meyre, Arthur
Privacy enhancing technologies (PETs) have been proposed as a way to protect the privacy of data while still allowing for data analysis. In this work, we focus on Fully Homomorphic Encryption (FHE), a powerful tool that allows for arbitrary computati
Externí odkaz:
http://arxiv.org/abs/2303.01254
Autor:
Stoian, Andrei, Frery, Jordan, Bredehoft, Roman, Montero, Luis, Kherfallah, Celia, Chevallier-Mames, Benoit
Fully homomorphic encryption (FHE) is an encryption method that allows to perform computation on encrypted data, without decryption. FHE preserves the privacy of the users of online services that handle sensitive data, such as health data, biometrics
Externí odkaz:
http://arxiv.org/abs/2302.10906
We introduce in this paper a novel active learning algorithm for satellite image change detection. The proposed solution is interactive and based on a question and answer model, which asks an oracle (annotator) the most informative questions about th
Externí odkaz:
http://arxiv.org/abs/2110.04250
Autor:
Prodana, Mariana1 (AUTHOR) mariana.prodana@upb.ro, Stoian, Andrei Bogdan1 (AUTHOR) andreibstoian@yahoo.com, Ionita, Daniela1 (AUTHOR) daniela.ionita@upb.ro, Brajnicov, Simona2 (AUTHOR) brajnicov.simona@inflpr.ro, Boerasu, Iulian3 (AUTHOR) iulian.boerasu@cssnt-upb.ro, Enachescu, Marius3 (AUTHOR) marius.enachescu@cssnt-upb.ro, Burnei, Cristian4 (AUTHOR) cristian.burnei@umfcd.ro
Publikováno v:
Materials (1996-1944). Jun2024, Vol. 17 Issue 12, p2989. 14p.
In most machine learning algorithms, training data is assumed to be independent and identically distributed (iid). When it is not the case, the algorithm's performances are challenged, leading to the famous phenomenon of catastrophic forgetting. Algo
Externí odkaz:
http://arxiv.org/abs/1912.03049
Autor:
Lesort, Timothée, Lomonaco, Vincenzo, Stoian, Andrei, Maltoni, Davide, Filliat, David, Díaz-Rodríguez, Natalia
Continual learning (CL) is a particular machine learning paradigm where the data distribution and learning objective changes through time, or where all the training data and objective criteria are never available at once. The evolution of the learnin
Externí odkaz:
http://arxiv.org/abs/1907.00182
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Lesort, Timothée, Caselles-Dupré, Hugo, Garcia-Ortiz, Michael, Stoian, Andrei, Filliat, David
Which generative model is the most suitable for Continual Learning? This paper aims at evaluating and comparing generative models on disjoint sequential image generation tasks. We investigate how several models learn and forget, considering various s
Externí odkaz:
http://arxiv.org/abs/1812.09111
We present a new replay-based method of continual classification learning that we term "conditional replay" which generates samples and labels together by sampling from a distribution conditioned on the class. We compare conditional replay to another
Externí odkaz:
http://arxiv.org/abs/1810.12069