Publications

Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning
Jensen Gao
Siddharth Reddy
Anca Dragan
Sergey Levine
Adaptive interfaces can help users perform sequential decision-making tasks like robotic teleoperation given noisy, high-dimensional command… (voir plus) signals (e.g., from a brain-computer interface). Recent advances in human-in-the-loop machine learning enable such systems to improve by interacting with users, but tend to be limited by the amount of data that they can collect from individual users in practice. In this paper, we propose a reinforcement learning algorithm to address this by training an interface to map raw command signals to actions using a combination of offline pre-training and online fine-tuning. To address the challenges posed by noisy command signals and sparse rewards, we develop a novel method for representing and inferring the user's long-term intent for a given trajectory. We primarily evaluate our method's ability to assist users who can only communicate through noisy, high-dimensional input channels through a user study in which 12 participants performed a simulated navigation task by using their eye gaze to modulate a 128-dimensional command signal from their webcam. The results show that our method enables successful goal navigation more often than a baseline directional interface, by learning to denoise user commands signals and provide shared autonomy assistance. We further evaluate on a simulated Sawyer pushing task with eye gaze control, and the Lunar Lander game with simulated user commands, and find that our method improves over baseline interfaces in these domains as well. Extensive ablation experiments with simulated user commands empirically motivate each component of our method.
Comparison of Radiologists and Deep Learning for US Grading of Hepatic Steatosis.
Pedro Vianna
Sara-Ivana Calce
Pamela Boustros
Cassandra Larocque-Rigney
Laurent Patry-Beaudoin
Yi Hui Luo
Emre Aslan
John Marinos
Talal M. Alamri
Kim-Nhien Vu
Jessica Murphy-Lavallée
Jean-Sébastien Billiard
Emmanuel Montagnon
Hongliang Li
Samuel Kadoury
Bich Nguyen
Shanel Gauthier
Benjamin Thérien
Michael Chassé
Guy Cloutier
An Tang
Background Screening for nonalcoholic fatty liver disease (NAFLD) is suboptimal due to the subjective interpretation of US images. Purpose T… (voir plus)o evaluate the agreement and diagnostic performance of radiologists and a deep learning model in grading hepatic steatosis in NAFLD at US, with biopsy as the reference standard. Materials and Methods This retrospective study included patients with NAFLD and control patients without hepatic steatosis who underwent abdominal US and contemporaneous liver biopsy from September 2010 to October 2019. Six readers visually graded steatosis on US images twice, 2 weeks apart. Reader agreement was assessed with use of κ statistics. Three deep learning techniques applied to B-mode US images were used to classify dichotomized steatosis grades. Classification performance of human radiologists and the deep learning model for dichotomized steatosis grades (S0, S1, S2, and S3) was assessed with area under the receiver operating characteristic curve (AUC) on a separate test set. Results The study included 199 patients (mean age, 53 years ± 13 [SD]; 101 men). On the test set (n = 52), radiologists had fair interreader agreement (0.34 [95% CI: 0.31, 0.37]) for classifying steatosis grades S0 versus S1 or higher, while AUCs were between 0.49 and 0.84 for radiologists and 0.85 (95% CI: 0.83, 0.87) for the deep learning model. For S0 or S1 versus S2 or S3, radiologists had fair interreader agreement (0.30 [95% CI: 0.27, 0.33]), while AUCs were between 0.57 and 0.76 for radiologists and 0.73 (95% CI: 0.71, 0.75) for the deep learning model. For S2 or lower versus S3, radiologists had fair interreader agreement (0.37 [95% CI: 0.33, 0.40]), while AUCs were between 0.52 and 0.81 for radiologists and 0.67 (95% CI: 0.64, 0.69) for the deep learning model. Conclusion Deep learning approaches applied to B-mode US images provided comparable performance with human readers for detection and grading of hepatic steatosis. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Tuthill in this issue.
Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges
Ahmed Haj Yahmed
Altaf Allah Abbassi
Amin Nikanjam
Heng Li
Deep reinforcement learning (DRL), leveraging Deep Learning (DL) in reinforcement learning, has shown significant potential in achieving hum… (voir plus)an-level autonomy in a wide range of domains, including robotics, computer vision, and computer games. This potential justifies the enthusiasm and growing interest in DRL in both academia and industry. However, the community currently focuses mostly on the development phase of DRL systems, with little attention devoted to DRL deployment. In this paper, we propose an empirical study on Stack Overflow (SO), the most popular Q&A forum for developers, to uncover and understand the challenges practitioners faced when deploying DRL systems. Specifically, we categorized relevant SO posts by deployment platforms: server/cloud, mobile/embedded system, browser, and game engine. After filtering and manual analysis, we examined 357 SO posts about DRL deployment, investigated the current state, and identified the challenges related to deploying DRL systems. Then, we investigate the prevalence and difficulty of these challenges. Results show that the general interest in DRL deployment is growing, confirming the study’s relevance and importance. Results also show that DRL deployment is more difficult than other DRL issues. Additionally, we built a taxonomy of 31 unique challenges in deploying DRL to different platforms. On all platforms, RL environment-related challenges are the most popular, and communication-related challenges are the most difficult among practitioners. We hope our study inspires future research and helps the community overcome the most common and difficult challenges practitioners face when deploying DRL systems.
An Empirical Study on Bugs Inside PyTorch: A Replication Study
Vahid Majdinasab
Sharon Chee Yin Ho
Mohayeminul Islam
Diego Elias Costa
Emad Shihab
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.
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
Sébastien Jacquemont
A Generic Framework for Byzantine-Tolerant Consensus Achievement in Robot Swarms
Hanqing Zhao
Alexandre Pacheco
Volker Strobel
Andreagiovanni Reina
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.
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
Michael Morley
Jessilyn Dunn
An-Kwok Ian Wong
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
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.
L'éthique au cœur de l'IA
Lyse Langlois
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.
One-4-All: Neural Potential Fields for Embodied Navigation
Sacha Morin
Miguel Saavedra-Ruiz
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/.
PRACTICAL APPLICATIONS OF MEDICAL GENETICS AND GENOMICS FOR PSYCHIATRISTS
Robustness assessment of hyperspectral image CNNs using metamorphic testing
Rached Bouchoucha
Houssem Ben Braiek
Sonia Bouzidi
Rania Zaatour