Zobrazeno 1 - 10
of 23 655
pro vyhledávání: '"Lesage, A."'
In this work, we propose Wasserstein distributionally robust shallow convex neural networks (WaDiRo-SCNNs) to provide reliable nonlinear predictions when subject to adverse and corrupted datasets. Our approach is based on a new convex training progra
Externí odkaz:
http://arxiv.org/abs/2407.16800
Autor:
Yahia, Olfa Ben, Garroussi, Zineb, Sansò, Brunilde, Frigon, Jean-François, Martel, Stéphane, Lesage-Landry, Antoine, Kurt, Gunes Karabulut
This paper addresses the limitations of current satellite payload architectures, which are predominantly hardware-driven and lack the flexibility to adapt to increasing data demands and uneven traffic. To overcome these challenges, we present a novel
Externí odkaz:
http://arxiv.org/abs/2407.06075
The last decade has seen the emergence of a new generation of multi-core in response to advances in machine learning, and in particular Deep Neural Network (DNN) training and inference tasks. These platforms, like the JETSON AGX XAVIER, embed several
Externí odkaz:
http://arxiv.org/abs/2406.14081
Autor:
Lesage, Benjamin, Boniol, Frédéric, Delmas, Kevin, Gauffriau, Adrien, Gonzalez, Alfonso Mascarenas, Pagetti, Claire
The emergence of Deep Neural Network (DNN) and machine learning-based applications paved the way for a new generation of hybrid hardware platforms. Hybrid platforms embed several cores and accelerators in a small package. However, in order to satisfy
Externí odkaz:
http://arxiv.org/abs/2406.12346
Autor:
Karran, A. J., Charland, P., Martineau, J-T., de Arana, A. Ortiz de Guinea Lopez, Lesage, AM., Senecal, S., Leger, P-M.
This study investigates the acceptability of different artificial intelligence (AI) applications in education from a multi-stakeholder perspective, including students, teachers, and parents. Acknowledging the transformative potential of AI in educati
Externí odkaz:
http://arxiv.org/abs/2402.15027
Model predictive control (MPC) has been shown to significantly improve the energy efficiency of buildings while maintaining thermal comfort. Data-driven approaches based on neural networks have been proposed to facilitate system modelling. However, s
Externí odkaz:
http://arxiv.org/abs/2401.15742
Thousands of satellites, asteroids, and rocket bodies break, collide, or degrade, resulting in large amounts of space debris in low Earth orbit. The presence of space debris poses a serious threat to satellite mega-constellations and to future space
Externí odkaz:
http://arxiv.org/abs/2311.11838
Convex relaxations of the optimal power flow (OPF) problem provide an efficient alternative to solving the intractable alternating current (AC) optimal power flow. The conic subset of OPF convex relaxations, in particular, greatly accelerate resoluti
Externí odkaz:
http://arxiv.org/abs/2311.07781
Autor:
Srinivasaragavan, Gokul P., Swain, Vishwajeet, O'Connor, Brendan M., Anand, Shreya, Ahumada, Tomás, Perley, Daniel A., Stein, Robert, Sollerman, Jesper, Fremling, Christoffer, Cenko, S. Bradley, Antier, Sarah, Guessoum, Nidhal, Hussenot-Desenonges, Thomas, Hello, Patrice, Lesage, Stephen, Hammerstein, Erica, Miller, M. Coleman, Andreoni, Igor, Bhalerao, Varun, Bloom, Joshua S., Dutta, Anirban, Gal-Yam, Avishay, Hinds, K-Ryan, Jaodand, Amruta D., Kasliwal, Mansi M., Kumar, Harsh, Kutyrev, Alexander, Ragosta, Fabio, Ravi, Vikram, Sharma, Kritti, Teja, Rishabh S., Yang, Sheng, Anupama, G. C., Bellm, Eric C., Coughlin, Michael W., Mahabal, Ashish A., Masci, Frank J., Pathak, Utkarsh, Purdum, Josiah, Roberts, Oliver J., Smith, Roger, Wold, Avery
We report observations of the optical counterpart of the long gamma-ray burst (LGRB) GRB 230812B, and its associated supernova (SN) SN 2023pel. The proximity ($z = 0.36$) and high energy ($E_{\gamma, \rm{iso}} \sim 10^{53}$ erg) make it an important
Externí odkaz:
http://arxiv.org/abs/2310.14397
Autor:
Tesson, Christelle, Bouchetara, Mohamed Sofiane, Ferrien, Mélanie, Lesage, Suzanne, Brice, Alexis
Publikováno v:
Movement Disorders, 2023, 38 (9), pp.1756-1757
Liu et al. recently reported that biallelic mutations in DAGLB are responsible for autosomal recessive early-onset Parkinson's disease. They identified six patients carrying DAGLB mutations, all of Chinese origin and presenting with typical Parkinson
Externí odkaz:
http://arxiv.org/abs/2310.12521