Zobrazeno 1 - 10
of 12 358
pro vyhledávání: '"A. PARIENTE"'
Optical training of large-scale Transformers and deep neural networks with direct feedback alignment
Autor:
Wang, Ziao, Müller, Kilian, Filipovich, Matthew, Launay, Julien, Ohana, Ruben, Pariente, Gustave, Mokaadi, Safa, Brossollet, Charles, Moreau, Fabien, Cappelli, Alessandro, Poli, Iacopo, Carron, Igor, Daudet, Laurent, Krzakala, Florent, Gigan, Sylvain
Modern machine learning relies nearly exclusively on dedicated electronic hardware accelerators. Photonic approaches, with low consumption and high operation speed, are increasingly considered for inference but, to date, remain mostly limited to rela
Externí odkaz:
http://arxiv.org/abs/2409.12965
Autor:
Fuchs, Franz G., Stasik, Alexander J., Miao, Stanley, Kulseng, Ola Tangen, Bassa, Ruben Pariente
Utilizing a quantum system for reservoir computing has recently received a lot of attention. Key challenges are related to how on can optimally en- and decode classical information, as well as what constitutes a good reservoir. Our main contribution
Externí odkaz:
http://arxiv.org/abs/2407.00445
Autor:
Pariente, Yaacov, Indelman, Vadim
Risk averse decision making under uncertainty in partially observable domains is a fundamental problem in AI and essential for reliable autonomous agents. In our case, the problem is modeled using partially observable Markov decision processes (POMDP
Externí odkaz:
http://arxiv.org/abs/2406.03000
Autor:
Leglaive, Simon, Fraticelli, Matthieu, ElGhazaly, Hend, Borne, Léonie, Sadeghi, Mostafa, Wisdom, Scott, Pariente, Manuel, Hershey, John R., Pressnitzer, Daniel, Barker, Jon P.
Supervised models for speech enhancement are trained using artificially generated mixtures of clean speech and noise signals. However, the synthetic training conditions may not accurately reflect real-world conditions encountered during testing. This
Externí odkaz:
http://arxiv.org/abs/2402.01413
Autor:
Leglaive, Simon, Borne, Léonie, Tzinis, Efthymios, Sadeghi, Mostafa, Fraticelli, Matthieu, Wisdom, Scott, Pariente, Manuel, Pressnitzer, Daniel, Hershey, John R.
Publikováno v:
The 7th International Workshop on Speech Processing in Everyday Environments (CHiME), Dublin, Ireland, 2023
Supervised speech enhancement models are trained using artificially generated mixtures of clean speech and noise signals, which may not match real-world recording conditions at test time. This mismatch can lead to poor performance if the test domain
Externí odkaz:
http://arxiv.org/abs/2307.03533
Autor:
Fuchs, Franz G., Bassa, Ruben Pariente
We present a novel formalism to both understand and construct mixers that preserve a given subspace. The method connects and utilizes the stabilizer formalism that is used in error correcting codes. This can be useful in the setting when the quantum
Externí odkaz:
http://arxiv.org/abs/2306.17083
Autor:
Vidal, Julie P., Danet, Lola, Péran, Patrice, Pariente, Jérémie, Cuadra, Meritxell Bach, Zahr, Natalie M., Barbeau, Emmanuel J., Saranathan, Manojkumar
Accurate segmentation of thalamic nuclei, crucial for understanding their role in healthy cognition and in pathologies, is challenging to achieve on standard T1-weighted (T1w) magnetic resonance imaging (MRI) due to poor image contrast. White-matter-
Externí odkaz:
http://arxiv.org/abs/2304.07167
Autor:
Maria Linares, Miguel Martín-Sómer, Alicia García, Inés Moreno, Arturo Vizcaíno, Isabel Pariente, Cintia Casado, Patricia Pizarro, Antonio Martín-Rengel, Cristina Pablos, Gema Gómez-Pozuelo, Gisela Orcajo
Publikováno v:
Advances in Building Education, Vol 8, Iss 2, Pp 9-19 (2024)
La incorporación de actividades de trabajo en equipo en los programas de formación universitaria es esencial, ya que es una de las habilidades más valoradas para los profesionales en el campo de la ingeniería. La selección de los grupos de traba
Externí odkaz:
https://doaj.org/article/9a01421c686f497cb9f54b3d4ebe2c30
Publikováno v:
Scientific Reports, Vol 14, Iss 1, Pp 1-12 (2024)
Abstract Bioeconomy goals for using biomass feedstock for biofuels and bio-based production has arisen the demand for fungal strains and enzymes for biomass processing. Despite well-known Trichoderma and Aspergillus commercial strains, continuous bio
Externí odkaz:
https://doaj.org/article/87b7565be49443d9ad8c36e537ad7ebb
Autor:
Cornell, Samuele, Wang, Zhong-Qiu, Masuyama, Yoshiki, Watanabe, Shinji, Pariente, Manuel, Ono, Nobutaka
This paper describes our submission to the Second Clarity Enhancement Challenge (CEC2), which consists of target speech enhancement for hearing-aid (HA) devices in noisy-reverberant environments with multiple interferers such as music and competing s
Externí odkaz:
http://arxiv.org/abs/2302.07928