Publications

An Empirical Study on Bugs Inside PyTorch: A Replication Study
Vahid Majdinasab
Sharon Chee Yin Ho
Mohayeminul Islam
Diego Elias Costa
Emad Shihab
Foutse Khomh
Sarah Nadi
Muhammad Raza
Software systems are increasingly relying on deep learning components, due to their remarkable capability of identifying complex data patter… (voir plus)ns and powering intelligent behaviour. A core enabler of this change in software development is the availability of easy-to-use deep learning libraries. Libraries like PyTorch and TensorFlow empower a large variety of intelligent systems, offering a multitude of algorithms and configuration options, applicable to numerous domains of systems. However, bugs in those popular deep learning libraries also may have dire consequences for the quality of systems they enable; thus, it is important to understand how bugs are identified and fixed in those libraries.Inspired by a study of Jia et al., which investigates the bug identification and fixing process at TensorFlow, we characterize bugs in the PyTorch library, a very popular deep learning framework. We investigate the causes and symptoms of bugs identified during PyTorch’s development, and assess their locality within the project, and extract patterns of bug fixes. Our results highlight that PyTorch bugs are more like traditional software projects bugs, than related to deep learning characteristics. Finally, we also compare our results with the study on TensorFlow, highlighting similarities and differences across the bug identification and fixing process.
2023-10-01
2023 IEEE International Conference on Software Maintenance and Evolution (ICSME) (publié)
doi.org
arxiv.org
F66. FROM GENE TO COGNITION: MAPPING THE EFFECTS OF GENOMIC DELETIONS AND DUPLICATIONS ON COGNITIVE ABILITY
Sayeh Kazem
Kuldeep Kumar
Guillaume Huguet
Myriam Lizotte
Thomas Renne
Jakub Kopal
Stefan Horoi
Martineau Jean-Louis
Zohra Saci
Laura Almasy
David C. Glahn
Guy Wolf
Guillaume Dumas
Sébastien Jacquemont
2023-10-01
European Neuropsychopharmacology (publié)
doi.org
A Generic Framework for Byzantine-Tolerant Consensus Achievement in Robot Swarms
Hanqing Zhao
Alexandre Pacheco
Volker Strobel
Andreagiovanni Reina
Xue (Steve) Liu
Gregory Dudek
Marco Dorigo
Recent studies show that some security features that blockchains grant to decentralized networks on the internet can be ported to swarm robo… (voir plus)tics. Although the integration of blockchain technology and swarm robotics shows great promise, thus far, research has been limited to proof-of-concept scenarios where the blockchain-based mechanisms are tailored to a particular swarm task and operating environment. In this study, we propose a generic framework based on a blockchain smart contract that enables robot swarms to achieve secure consensus in an arbitrary observation space. This means that our framework can be customized to fit different swarm robotics missions, while providing methods to identify and neutralize Byzantine robots, that is, robots which exhibit detrimental behaviours stemming from faults or malicious tampering.
2023-10-01
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publié)
doi.org
Going beyond the means: Exploring the role of bias from digital determinants of health in technologies
Marie-Laure Charpignon
Adrien Carrel
Yihang Jiang
Teddy Kwaga
Beatriz Cantada
Terry Hyslop
Christopher E. Cox
Krista Haines
Valencia Koomson
Guillaume Dumas
Michael Morley
Jessilyn Dunn
An-Kwok Ian Wong
2023-10-01
PLOS Digital Health (publié)
doi.org
Hybrid Scattering Transform - Long Short-Term Memory Networks for Intrapartum Fetal Heart Rate Classification
"Derek Kweku DEGBEDZUI
Michael W Kuzniewicz
Marie-Coralie Cornet
Yvonne Wu
Heather Forquer
Lawrence Gerstley
Emily F. Hamilton
Doina Precup
P. Warrick
Robert E. Kearney
This study assessed the early detection of the increased risk of hypoxic ischemic encephalopathy using raw fetal heart rate and its transfor… (voir plus)mation with scattering transform and a long short-term memory recurrent neural network. There was no significant difference between the two approaches. However, the use of scattering transform produced lower computational demands. Considering scalability to the large data in our database and computational efficiency, the experiments involving scattering transform coefficients will be selected to conduct subsequent experiments. Future works will address the limitations of this study, including the low model performance.
2023-10-01
2023 Computing in Cardiology (CinC) (publié)
doi.org
L'éthique au cœur de l'IA
Lyse Langlois
Marc-Antoine Dilhac
Jim Dratwa
Thierry Ménissier
Jean-gabriel Ganascia
Daniel Weinstock
L. Bégin
Allison Marchildon
Issu d’un travail collaboratif regroupant des spécialistes de l’éthique, de la philosophie, de l’informatique et de l’économie, l… (voir plus)e rapport « L’éthique au cœur de l’IA » vise à préciser et clarifier le rôle que doit occuper l’éthique à l’ère de l’intelligence artificielle (IA), et à mettre en lumière comment cette notion peut être appliquée et mise en œuvre de manière efficace et fructueuse. S’adressant à l’ensemble des individus engagés, de près ou de loin, dans le développement de l’IA, ce document met de l’avant une éthique centrée sur la réflexivité et le dialogue. Dans une volonté de traduire plus concrètement cette vision, il met en lumière l’approche méthodologique utilisée pour construire la Déclaration de Montréal et propose également quelques pistes de recommandation. En somme, le présent texte plaide pour l’inclusion d’une réelle réflexion éthique dans l’ensemble des étapes du processus de développement de l’IA. Il se veut ainsi une main tendue, un appel à la collaboration entre éthiciennes et éthiciens, développeuses et développeurs et membres de l’industrie afin de véritablement intégrer l’éthique au cœur de l’IA.
2023-10-01
(publié)
doi.org
One-4-All: Neural Potential Fields for Embodied Navigation
Sacha Morin
Miguel Saavedra-Ruiz
Liam Paull
A fundamental task in robotics is to navigate between two locations. In particular, real-world navigation can require long-horizon planning … (voir plus)using high-dimensional RGB images, which poses a substantial challenge for end-to-end learning-based approaches. Current semi-parametric methods instead achieve long-horizon navigation by combining learned modules with a topological memory of the environment, often represented as a graph over previously collected images. However, using these graphs in practice requires tuning a number of pruning heuristics. These heuristics are necessary to avoid spurious edges, limit runtime memory usage and maintain reasonably fast graph queries in large environments. In this work, we present One-4-All (O4A), a method leveraging self-supervised and manifold learning to obtain a graph-free, end-to-end navigation pipeline in which the goal is specified as an image. Navigation is achieved by greedily minimizing a potential function defined continuously over image embeddings. Our system is trained offline on non-expert exploration sequences of RGB data and controls, and does not require any depth or pose measurements. We show that 04A can reach long-range goals in 8 simulated Gibson indoor environments and that resulting embeddings are topologically similar to ground truth maps, even if no pose is observed. We further demonstrate successful real-world navigation using a Jackal UGV platform.aaProject page https://montrealrobotics.ca/o4a/.
2023-10-01
2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publié)
doi.org
arxiv.org
PRACTICAL APPLICATIONS OF MEDICAL GENETICS AND GENOMICS FOR PSYCHIATRISTS
Yannis Trakadis
2023-10-01
European Neuropsychopharmacology (publié)
doi.org
Robustness assessment of hyperspectral image CNNs using metamorphic testing
Rached Bouchoucha
Houssem Ben Braiek
Foutse Khomh
Sonia Bouzidi
Rania Zaatour
2023-10-01
Information and Software Technology (publié)
doi.org
Torque-Based Deep Reinforcement Learning for Task-and-Robot Agnostic Learning on Bipedal Robots Using Sim-to-Real Transfer
Donghyeon Kim
Glen Berseth
Mathew Schwartz
Jaeheung Park
In this letter, we review the question of which action space is best suited for controlling a real biped robot in combination with Sim2Real … (voir plus)training. Position control has been popular as it has been shown to be more sample efficient and intuitive to combine with other planning algorithms. However, for position control, gain tuning is required to achieve the best possible policy performance. We show that, instead, using a torque-based action space enables task-and-robot agnostic learning with less parameter tuning and mitigates the sim-to-reality gap by taking advantage of torque control's inherent compliance. Also, we accelerate the torque-based-policy training process by pre-training the policy to remain upright by compensating for gravity. The letter showcases the first successful sim-to-real transfer of a torque-based deep reinforcement learning policy on a real human-sized biped robot.
2023-10-01
IEEE Robotics and Automation Letters (publié)
doi.org
arxiv.org
Towards More General Loss and Setting in Unsupervised Domain Adaptation
Changjian Shui
Ruizhi Pu
Gezheng Xu
Jun Wen
Fan Zhou
Christian Gagné
Charles Ling
Boyu Wang
In this article, we present an analysis of unsupervised domain adaptation with a series of theoretical and algorithmic results. We derive a … (voir plus)novel Rényi-
2023-10-01
IEEE Transactions on Knowledge and Data Engineering (publié)
doi.org
W56. UNRAVELING THE IMPACT OF GENOMIC VARIATIONS ON COGNITIVE ABILITY ACROSS THE HUMAN CORTEX: INSIGHTS FROM GENE EXPRESSION AND COPY NUMBER VARIANTS
Kuldeep Kumar
Sayeh Kazem
Guillaume Huguet
Thomas Renne
Bank Engchuan
Omar Shanta
Bhooma Thiruvahindrapuram
J. MacDonald
Marieke Klein
Stephen W Scherer
Laura Almasy
Jonathan Sebat
David C. Glahn
Guillaume Dumas
Sébastien Jacquemont
2023-10-01
European Neuropsychopharmacology (publié)
doi.org