Zobrazeno 1 - 10
of 213
pro vyhledávání: '"Laviolette, François"'
Address parsing consists of identifying the segments that make up an address, such as a street name or a postal code. Because of its importance for tasks like record linkage, address parsing has been approached with many techniques, the latest relyin
Externí odkaz:
http://arxiv.org/abs/2112.04008
Autor:
Fortier-Dubois, Louis, Letarte, Gaël, Leblanc, Benjamin, Laviolette, François, Germain, Pascal
Considering a probability distribution over parameters is known as an efficient strategy to learn a neural network with non-differentiable activation functions. We study the expectation of a probabilistic neural network as a predictor by itself, focu
Externí odkaz:
http://arxiv.org/abs/2110.15137
Autor:
Tambon, Florian, Laberge, Gabriel, An, Le, Nikanjam, Amin, Mindom, Paulina Stevia Nouwou, Pequignot, Yann, Khomh, Foutse, Antoniol, Giulio, Merlo, Ettore, Laviolette, François
Publikováno v:
Autom Softw Eng 29, 38 (2022)
Context: Machine Learning (ML) has been at the heart of many innovations over the past years. However, including it in so-called 'safety-critical' systems such as automotive or aeronautic has proven to be very challenging, since the shift in paradigm
Externí odkaz:
http://arxiv.org/abs/2107.12045
Autor:
Pequignot, Yann, Alain, Mathieu, Dallaire, Patrick, Yeganehparast, Alireza, Germain, Pascal, Desharnais, Josée, Laviolette, François
It is crucial to detect when an instance lies downright too far from the training samples for the machine learning model to be trusted, a challenge known as out-of-distribution (OOD) detection. For neural networks, one approach to this task consists
Externí odkaz:
http://arxiv.org/abs/2010.12995
Publikováno v:
2020 6th IEEE Congress on Information Science and Technology (CiSt)
Address parsing consists of identifying the segments that make up an address such as a street name or a postal code. Because of its importance for tasks like record linkage, address parsing has been approached with many techniques. Neural network met
Externí odkaz:
http://arxiv.org/abs/2006.16152
Cops and Robbers games have been studied for the last few decades in computer science and mathematics. As in general pursuit evasion games, pursuers (cops) seek to capture evaders (robbers); however, players move in turn and are constrained to move o
Externí odkaz:
http://arxiv.org/abs/2004.11503
Autor:
Dallaire, Patrick, Ambrogioni, Luca, Trottier, Ludovic, Güçlü, Umut, Hinne, Max, Giguère, Philippe, Chaib-Draa, Brahim, van Gerven, Marcel, Laviolette, Francois
This paper introduces the Indian Chefs Process (ICP), a Bayesian nonparametric prior on the joint space of infinite directed acyclic graphs (DAGs) and orders that generalizes Indian Buffet Processes. As our construction shows, the proposed distributi
Externí odkaz:
http://arxiv.org/abs/2001.10657
Autor:
Côté-Allard, Ulysse, Gagnon-Turcotte, Gabriel, Phinyomark, Angkoon, Glette, Kyrre, Scheme, Erik, Laviolette, François, Gosselin, Benoit
Publikováno v:
in IEEE Access, vol. 8, pp. 177941-177955, 2020
Surface electromyography (sEMG) provides an intuitive and non-invasive interface from which to control machines. However, preserving the myoelectric control system's performance over multiple days is challenging, due to the transient nature of the si
Externí odkaz:
http://arxiv.org/abs/1912.11037
Autor:
Côté-Allard, Ulysse, Gagnon-Turcotte, Gabriel, Phinyomark, Angkoon, Glette, Kyrre, Scheme, Erik, Laviolette, François, Gosselin, Benoit
Within the field of electromyography-based (EMG) gesture recognition, disparities exist between the offline accuracy reported in the literature and the real-time usability of a classifier. This gap mainly stems from two factors: 1) The absence of a c
Externí odkaz:
http://arxiv.org/abs/1912.09380
Autor:
Côté-Allard, Ulysse, Campbell, Evan, Phinyomark, Angkoon, Laviolette, François, Gosselin, Benoit, Scheme, Erik
Publikováno v:
Frontiers in Bioengineering and Biotechnology, 8, 158 (2020)
The research in myoelectric control systems primarily focuses on extracting discriminative representations from the electromyographic (EMG) signal by designing handcrafted features. Recently, deep learning techniques have been applied to the challeng
Externí odkaz:
http://arxiv.org/abs/1912.00283