4k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Centre National de la Recherche ScientifiqueFR123 papers
- Centre for Research in Astrophysics of QuébecCA107 papers
- Université de MontréalCA52 papers
- University of TorontoCA52 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR51 papers
- Université Paris-SudFR43 papers
- McGill UniversityCA42 papers
- University College LondonGB40 papers
- Canadian Institute for Theoretical AstrophysicsCA35 papers
- Institut National de Physique Nucléaire et de Physique des ParticulesFR35 papers
- Grand Accélérateur National d'Ions LourdsFR33 papers
- Space Telescope Science InstituteUS33 papers
60 papers · 1 filter
Attending Form and Context to Generate Specialized Out-of-VocabularyWords Representations
Nicolas Garneau, Jean-Samuel Leboeuf, Yuval Pinter +1
We propose a new contextual-compositional neural network layer that handles out-of-vocabulary (OOV) words in natural language processing (NLP) tagging tasks. This layer consists of…
Unsupervised Domain Adversarial Self-Calibration for Electromyographic-based Gesture Recognition
Ulysse Côté-Allard, Gabriel Gagnon-Turcotte, Angkoon Phinyomark +4
Surface electromyography (sEMG) provides an intuitive and non-invasive interface from which to control machines. However, preserving the myoelectric control system's performance ov…
A Transferable Adaptive Domain Adversarial Neural Network for Virtual Reality Augmented EMG-Based Gesture Recognition
Ulysse Côté-Allard, Gabriel Gagnon-Turcotte, Angkoon Phinyomark +4
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 cla…
A Robust Self-Learning Method for Fully Unsupervised Cross-Lingual Mappings of Word Embeddings: Making the Method Robustly Reproducible as Well
Nicolas Garneau, Mathieu Godbout, David Beauchemin +2
In this paper, we reproduce the experiments of Artetxe et al. (2018b) regarding the robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings. We…
Explicit uniformizers for certain totally ramified extensions of the field of -adic numbers
Hugues Bellemare, Antonio Lei
Let be an odd prime number. We construct explicit uniformizers for the totally ramified extension of the field of -adic numbers $\mathbb{…
Confounding Adjustment Methods for Multi-level Treatment Comparisons Under Lack of Positivity and Unknown Model Specification
Diop S. Arona, Duchesne Thierry, Cumming Steven +2
Imbalances in covariates between treatment groups are frequent in observational studies and can lead to biased comparisons. Various adjustment methods can be employed to correct th…
Interpreting Deep Learning Features for Myoelectric Control: A Comparison with Handcrafted Features
Ulysse Côté-Allard, Evan Campbell, Angkoon Phinyomark +3
The research in myoelectric control systems primarily focuses on extracting discriminative representations from the electromyographic (EMG) signal by designing handcrafted features…
A Novel Unsupervised Post-Processing Calibration Method for DNNS with Robustness to Domain Shift
Azadeh Sadat Mozafari, Hugo Siqueira Gomes, Christian Gagne
The uncertainty estimation is critical in real-world decision making applications, especially when distributional shift between the training and test data are prevalent. Many calib…
Equilibrium constants of Hydrogen and Helium isotopes at low nuclear densities
R. Bougault, E. Bonnet, B. Borderie +14
Equilibrium constants for Hydrogen and Helium isotopes as a function of density and temperature are measured in the framework of the study made by Qin et al. [Qin L et al 2012 Phys…
Higher-Point Conformal Blocks in the Comb Channel
Jean-François Fortin, Wenjie Ma, Witold Skiba
We compute -point conformal blocks with scalar external and exchange operators in the so-called comb configuration for any in any dimension . Our computation involves rep…
Mordell-Weil ranks and Tate-Shafarevich groups of elliptic curves with mixed-reduction type over cyclotomic extensions
Antonio Lei, Meng Fai Lim
Let be an elliptic curve defined over a number field where splits completely. Suppose that has good reduction at all primes above . Generalizing previous works o…
Deep Active Learning: Unified and Principled Method for Query and Training
Changjian Shui, Fan Zhou, Christian Gagné +1
In this paper, we are proposing a unified and principled method for both the querying and training processes in deep batch active learning. We are providing theoretical insights fr…
Towards Neural Language Evaluators
Hassan Kané, Yusuf Kocyigit, Pelkins Ajanoh +2
We review three limitations of BLEU and ROUGE -- the most popular metrics used to assess reference summaries against hypothesis summaries, come up with criteria for what a good met…
Dosimetric performance of a multi-point plastic scintillator dosimeter as a tool for real-time source tracking in high dose rate brachytherapy
Haydee M. Linares Rosales, Louis Archambault, Sam Beddar +1
Purpose: To present the performance of a multi-point plastic scintillation detector (mPSD) as a tool in vivo dosimetry in brachytherapy. Methods: A previously optimized three-point…
Erbium-doped aluminophosphosilicate all-fiber laser operating at 1584 nm
Marie-Pier Lord, Lauris Talbot, Olivier Boily +8
We report on an ytterbium-free erbium-doped aluminophosphosilicate all-fiber laser, producing an output power of 25 W at a wavelength of 1584 nm with a slope efficiency of 30% with…
Toward Metrics for Differentiating Out-of-Distribution Sets
Mahdieh Abbasi, Changjian Shui, Arezoo Rajabi +2
Vanilla CNNs, as uncalibrated classifiers, suffer from classifying out-of-distribution (OOD) samples nearly as confidently as in-distribution samples. To tackle this challenge, som…
Inference for growing trees
George T. Cantwell, Guillaume St-Onge, Jean-Gabriel Young
One can often make inferences about a growing network from its current state alone. For example, it is generally possible to determine how a network changed over time or pick among…
Clocking the formation of today's largest galaxies: Wide field integral spectroscopy of Brightest Cluster Galaxies and their surroundings
Louise O. V. Edwards, Matthew Salinas, Steffanie Stanley +8
The formation and evolution of local brightest cluster galaxies (BCGs) is investigated by determining the stellar populations and dynamics from the galaxy core, though the outskirt…
Single-frequency mid-infrared chip laser with a sub-hertz Lorentzian linewidth
Philippe Guay, Jérôme Genest, Vincent Michaud-Belleau +2
A guided-wave chip laser operating in a single longitudinal mode at 2860 nm is presented. The cavity was set in the Littman-Metcalf configuration to achieve single-frequency operat…
Amplified noise nonstationarity in a mode-locked laser based on nonlinear polarization rotation
Carlos Andres Perilla Rozo, Philippe Guay, Jean-Daniel Deschênes +1
Beat note measurements between a mode-locked and a continuous-wave laser as well as between two mode-locked sources were used to demonstrate that the sub-threshold, cavity filtered…
A Primal Decomposition Algorithm for the Two-dimensional Bin Packing Problem
Jean-François Côté, Mohamed Haouari, Manuel Iori
The Two-dimensional Bin Packing Problem calls for packing a set of rectangular items into a minimal set of larger rectangular bins. Items must be packed with their edges parallel t…
Searching for intergalactic star forming regions in Stephan's Quintet with SITELLE. I. Ionised gas structures and kinematics
S. Duarte Puertas, J. Iglesias-Páramo, J. M. Vilchez +3
Stephan's Quintet (SQ), the prototypical compact group of galaxies in the local Universe, has been observed with the imaging Fourier transform spectrometer SITELLE, attached to the…
Coarse-to-Fine Registration of Airborne LiDAR Data and Optical Imagery on Urban Scenes
Thanh Huy Nguyen, Sylvie Daniel, Didier Gueriot +2
Applications based on synergistic integration of optical imagery and LiDAR data are receiving a growing interest from the remote sensing community. However, a misaligned integratio…
Towards a reliable approach on scaling in data acquisition
Nicolae Paraschiv, Emil Pricop, Jaouhar Fattahi +1
Data acquisition is an important process in the functioning of any control system. Usually, the acquired signal is analogic, representing a continuous physical measure, and it shou…