Publications

Concurrent prescriptions for opioids and benzodiazepines and risk of opioid overdose: protocol for a retrospective cohort study using linked administrative data
Erin Y Liu
Robyn Tamblyn
Kristian B Filion
David L Buckeridge
2021-02-17
BMJ Open (publié)
doi.org
Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing Its Gradient Estimator Bias
Axel Laborieux
Maxence Ernoult
Benjamin Scellier
Yoshua Bengio
Julie Grollier
Damien Querlioz
2021-02-17
Frontiers in Neuroscience (publié)
doi.org
arxiv.org
Bridging the Gap Between Adversarial Robustness and Optimization Bias
Fartash Faghri
Cristina Vasconcelos
David J Fleet
Fabian Pedregosa
Nicolas Roux
2021-02-16
ArXiv (prépublication)
arxiv.org
arxiv.org
A Strategic Markovian Traffic Equilibrium Model for Capacitated Networks
Maëlle Zimmermann
Emma Frejinger
Patrice Marcotte
In the realm of traffic assignment over a network involving rigid arc capacities, the aim of the present work is to generalize the model of … (voir plus)Marcotte, Nguyen, and Schoeb [Marcotte P, Nguyen S, Schoeb A (2004) A strategic flow model of traffic assignment in static capacitated networks. Oper. Res. 52(2):191–212.] by casting it within a stochastic user equilibrium framework. The strength of the proposed model is to incorporate two sources of stochasticity stemming, respectively, from the users’ imperfect knowledge regarding arc costs (represented by a discrete choice model) and the probability of not accessing saturated arcs. Moreover, the arc-based formulation extends the Markovian traffic equilibrium model of Baillon and Cominetti [Baillon JB, Cominetti R ( 2008 ) Markovian traffic equilibrium. Math. Programming 111(1-2):33–56.] through the explicit consideration of capacities. This paper is restricted to the case of acyclic networks, for which we present solution algorithms and numerical experiments.
2021-02-16
Transportation Science (publié)
doi.org
Are Multi-language Design Smells Fault-prone? An Empirical Study
Mouna Abidi
Md Saidur Rahman
Moses Openja
Foutse Khomh
Nowadays, modern applications are developed using components written in different programming languages. These systems introduce several adv… (voir plus)antages. However, as the number of languages increases, so does the challenges related to the development and maintenance of these systems. In such situations, developers may introduce design smells (i.e., anti-patterns and code smells) which are symptoms of poor design and implementation choices. Design smells are defined as poor design and coding choices that can negatively impact the quality of a software program despite satisfying functional requirements. Studies on mono-language systems suggest that the presence of design smells affects code comprehension, thus making systems harder to maintain. However, these studies target only mono-language systems and do not consider the interaction between different programming languages. In this paper, we present an approach to detect multi-language design smells in the context of JNI systems. We then investigate the prevalence of those design smells. Specifically, we detect 15 design smells in 98 releases of nine open-source JNI projects. Our results show that the design smells are prevalent in the selected projects and persist throughout the releases of the systems. We observe that in the analyzed systems, 33.95% of the files involving communications between Java and C/C++ contains occurrences of multi-language design smells. Some kinds of smells are more prevalent than others, e.g., Unused Parameters, Too Much Scattering, Unused Method Declaration. Our results suggest that files with multi-language design smells can often be more associated with bugs than files without these smells, and that specific smells are more correlated to fault-proneness than others.
2021-02-10
ACM Transactions on Software Engineering and Methodology (publié)
doi.org
arxiv.org
Analyzing the Contribution of Ethical Charters to Building the Future of Artificial Intelligence Governance
Lyse Langlois
Catherine Régis
2021-02-06
Reflections on Artificial Intelligence for Humanity (publié)
doi.org
Structured Sparsity Inducing Adaptive Optimizers for Deep Learning
Tristan Deleu
Yoshua Bengio
The parameters of a neural network are naturally organized in groups, some of which might not contribute to its overall performance. To prun… (voir plus)e out unimportant groups of parameters, we can include some non-differentiable penalty to the objective function, and minimize it using proximal gradient methods. In this paper, we derive the weighted proximal operator, which is a necessary component of these proximal methods, of two structured sparsity inducing penalties. Moreover, they can be approximated efficiently with a numerical solver, and despite this approximation, we prove that existing convergence guarantees are preserved when these operators are integrated as part of a generic adaptive proximal method. Finally, we show that this adaptive method, together with the weighted proximal operators derived here, is indeed capable of finding solutions with structure in their sparsity patterns, on representative examples from computer vision and natural language processing.
2021-02-06
ArXiv (prépublication)
arxiv.org
arxiv.org
A Deep Learning Framework for Spatiotemporal Ultrasound Localization Microscopy
Léo Milecki
Jonathan Porée
Hatim Belgharbi
Chloé Bourquin
Rafat Damseh
Patrick Delafontaine-Martel
Frédéric Lesage
Maxime Gasse
Jean Provost
Ultrasound Localization Microscopy (ULM) can resolve the microvascular bed down to a few micrometers. To achieve such performance, microbubb… (voir plus)le contrast agents must perfuse the entire microvascular network. Microbubbles are then located individually and tracked over time to sample individual vessels, typically over hundreds of thousands of images. To overcome the fundamental limit of diffraction and achieve a dense reconstruction of the network, low microbubble concentrations must be used, which leads to acquisitions lasting several minutes. Conventional processing pipelines are currently unable to deal with interference from multiple nearby microbubbles, further reducing achievable concentrations. This work overcomes this problem by proposing a Deep Learning approach to recover dense vascular networks from ultrasound acquisitions with high microbubble concentrations. A realistic mouse brain microvascular network, segmented from 2-photon microscopy, was used to train a three-dimensional convolutional neural network (CNN) based on a V-net architecture. Ultrasound data sets from multiple microbubbles flowing through the microvascular network were simulated and used as ground truth to train the 3D CNN to track microbubbles. The 3D-CNN approach was validated in silico using a subset of the data and in vivo in a rat brain. In silico, the CNN reconstructed vascular networks with higher precision (81%) than a conventional ULM framework (70%). In vivo, the CNN could resolve micro vessels as small as 10 μ m with an improvement in resolution when compared against a conventional approach.
2021-02-02
IEEE Transactions on Medical Imaging (publié)
doi.org
arxiv.org
Enabling Secure Trustworthiness Assessment and Privacy Protection in Integrating Data for Trading Person-Specific Information
Rashid Hussain Khokhar
Farkhund Iqbal
Benjamin C. M. Fung
Jamal Bentahar
With increasing adoption of cloud services in the e-market, collaboration between stakeholders is easier than ever. Consumer stakeholders de… (voir plus)mand data from various sources to analyze trends and improve customer services. Data-as-a-service enables data integration to serve the demands of data consumers. However, the data must be of good quality and trustful for accurate analysis and effective decision making. In addition, a data custodian or provider must conform to privacy policies to avoid potential penalties for privacy breaches. To address these challenges, we propose a twofold solution: 1) we present the first information entropy-based trust computation algorithm, IEB_Trust, that allows a semitrusted arbitrator to detect the covert behavior of a dishonest data provider and chooses the qualified providers for a data mashup and 2) we incorporate the Vickrey–Clarke–Groves (VCG) auction mechanism for the valuation of data providers’ attributes into the data mashup process. Experiments on real-life data demonstrate the robustness of our approach in restricting dishonest providers from participation in the data mashup and improving the efficiency in comparison to provenance-based approaches. Furthermore, we derive the monetary shares for the chosen providers from their information utility and trust scores over the differentially private release of the integrated dataset under their joint privacy requirements.
2021-01-31
IEEE transactions on engineering management (publié)
doi.org
The neural correlates of ongoing conscious thought
Jonathan Smallwood
Adam Turnbull
Hao-Ting Wang
Nerissa S.P. Ho
Giulia L. Poerio
Theodoros Karapanagiotidis
Delali Konu
Brontë Mckeown
Meichao Zhang
Charlotte Murphy
Deniz Vatansever
Danilo Bzdok
Mahiko Konishi
Robert Leech
Paul Seli
Jonathan W. Schooler
Boris C Bernhardt
Daniel S. Margulies
Elizabeth Jefferies
2021-01-31
iScience (publié)
doi.org
Training neural networks to recognize speech increased their correspondence to the human auditory pathway but did not yield a shared hierarchy of acoustic features
Jessica A.F. Thompson
Yoshua Bengio
Elia Formisano
Marc Schönwiesner
Trained CNNs more similar to auditory fMRI activity than untrainedNo evidence of a shared representational hierarchy for acoustic featuresAl… (voir plus)l ROIs were most similar to the first fully-connected layerCNN performance on speech recognition task positively associated with fmri similarity
2021-01-26
bioRxiv (prépublication)
doi.org
A systematic analysis of ICSD-3 diagnostic criteria and proposal for further structured iteration.
Christophe Gauld
Régis Lopez
Pierre A. GEOFFROY
Charles Morin
Kelly Guichard
Elodie Giroux
Yves Dauvilliers
Guillaume Dumas
Pierre Philip
Jean‐Arthur Micoulaud‐Franchi
2021-01-25
Sleep Medicine Reviews (publié)
doi.org