Publications

Beyond Simple Meta-Learning: Multi-Purpose Models for Multi-Domain, Active and Continual Few-Shot Learning
Peyman Bateni
Jarred Barber
Raghav Goyal
Vaden Masrani
Jan-Willem van de Meent
Leonid Sigal
Frank N. Wood
2022-01-12
ArXiv (prépublication)
doi.org
arxiv.org
Biomedical Research & Informatics Living Laboratory for Innovative Advances of New Technologies in Community Mobility Rehabilitation: Protocol for a longitudinal evaluation of mobility outcomes (Preprint)
Sara Ahmed
Philippe Archambault
Claudine Auger
Audrey Durand
Joyce Fung
Eva Kehayia
Anouk Lamontagne
Annette Majnemer
Sylvie Nadeau
Joelle Pineau
Alain Ptito
Bonnie Swaine
2022-01-12
(publié)
doi.org
Haptics-based Curiosity for Sparse-Reward Tasks
Sai Rajeswar
Cyril Ibrahim
Nitin Surya
Florian Golemo
David Vázquez
Aaron Courville
Pedro O. Pinheiro
2022-01-10
Proceedings of the 5th Conference on Robot Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
Magnetoencephalography resting-state correlates of executive and language components of verbal fluency
Victor Oswald
Younes Zerouali
Aubrée Boulet-Craig
Maja Krajinovic
Caroline Laverdière
Daniel Sinnett
Pierre Jolicoeur
Sarah Lippé
Karim Jerbi CoCo Lab
Philippe Robaey
2022-01-09
Scientific Reports (publié)
doi.org
Automated, interactive, and traceable domain modelling empowered by artificial intelligence
Rijul Saini
Gunter Mussbacher
Jin L.C. Guo
Jörg Kienzle
2022-01-07
Software and Systems Modeling (publié)
doi.org
Global variation in event-based surveillance for disease outbreak detection: A time series analysis (Preprint)
Iris Ganser
Rodolphe Thiébaut
David L Buckeridge
BACKGROUND Robust and flexible infectious disease surveillance is crucial for public health. Event-based surveillance (EBS) was developed t… (voir plus)o allow timely detection of infectious disease outbreaks using mostly web-based data. Despite its widespread use, EBS has not been evaluated systematically on a global scale in terms of outbreak detection performance. OBJECTIVE To assess the variation in timing and frequency of EBS reports compared to true outbreaks and to identify the determinants of variability, using the example of seasonal influenza epidemics in 24 countries. METHODS We obtained influenza-related reports from two EBS systems, HealthMap and the WHO Epidemic Intelligence from Open Sources (EIOS), and weekly virologic influenza counts from FluNet as a gold standard. Epidemic influenza periods were detected based on report frequency using Bayesian change point analysis. Timely sensitivity, i.e., outbreak detection within the first two weeks before or after an outbreak onset, was calculated along with sensitivity, specificity, positive predictive value, and timeliness of detection. Linear regressions were performed to assess the influence of country-specific factors on EBS performance. RESULTS Overall, monitoring the frequency of EBS reports detected 73.5% of outbreaks, but only 9.2% within two weeks of onset; in the best case, monitoring the frequency of health-related reports identified 29% of outbreaks within two weeks of onset. We observed a large degree of variability in all evaluation metrics across countries. The number of EBS reports available within a country, the human development index, and the country’s geographical location partially explained this variability. CONCLUSIONS Monitoring the frequency of EBS reports allowed just under 10% of seasonal influenza outbreaks to be detected in a timely manner in a worldwide analysis, with a large variability in detection capabilities. This article documents the global variation of EBS performance and demonstrates that monitoring report frequency alone in EBS may be insufficient for timely detection of outbreaks. Moreover, factors such as human development index and geographical location of a country may influence the performance of EBS and should be considered in future evaluations.
2022-01-04
(publié)
doi.org
Statistical Evidence for Learnable Lexical Subclasses in Japanese
Takashi Morita
Timothy J. O’Donnell
It has been proposed that the Japanese lexicon can be divided into etymologically defined sublexica on phonotactic and other grounds. Howeve… (voir plus)r, the psychological reality of this sublexical analysis has been challenged by some authors, who have appealed to putative problems with the learnability of the system. In this study, we apply a commonly used clustering method to Japanese words and show that there is robust statistical evidence for the sublexica and, thereby, that such sublexica are learnable. The model is able to recover phonotactic properties of sublexica previously discussed in the literature, and also reveals hitherto unnoticed phonotactic properties that are characteristic of sublexical membership and can serve as a basis for future experimental investigations. The proposed approach is general and based purely on phonotactic information and thus can be applied to other languages.
2022-01-04
Linguistic Inquiry (publié)
doi.org
AI-based modeling of brain and behavior: Combining neuroimaging, imitation learning and video games
Anirudha Kemtur
François Paugam
Basile Pinsard
Pravish Sainath
Yann Harel
Maximilien Le Clei
Julie Boyle
Karim Jerbi
Pierre Bellec
2021-12-31
Conference on Cognitive Computational Neuroscience (publié)
doi.org
Appendix: On the Expressivity of Markov Reward
David Abel
Will Dabney
Anna Harutyunyan
Mark K. Ho
Michael L. Littman
Doina Precup
Satinder Singh
(Q1) What does it mean for Bob to *solve* one of these tasks? That is, if Alice chooses a SOAP, PO, or TO for Bob to learn to solve, when ca… (voir plus)n Alice determine Bob has solved the task? A: Bob can be said to be doing better on a given task if his behavior improves, as is typical in evaluating behavior under reward. The difference with SOAPs, POs, and TOs is that we measure improvement relative to the task rather than reward. For instance, given a SOAP, we might say that Bob has solved the task once he has found one of the good policies, and we might measure Bob’s progress on a task in terms of the distance of his greedy policy to one of the good policies (as done in our learning experiments). The same reasoning applies to POs and TOs: Bob is doing better on a task in so far as his greedy policy (or trajectories) is (are) higher up the ordering.
2021-12-31
(publié)
www.semanticscholar.org
Approximate information state for approximate planning and reinforcement learning in partially observed systems
Jayakumar Subramanian
Amit Sinha
Raihan Seraj
Aditya Mahajan
We propose a theoretical framework for approximate planning and learning in partially observed systems. Our framework is based on the fundam… (voir plus)ental notion of information state. We provide two equivalent definitions of information state---i) a function of history which is sufficient to compute the expected reward and predict its next value; ii) equivalently, a function of the history which can be recursively updated and is sufficient to compute the expected reward and predict the next observation. An information state always leads to a dynamic programming decomposition. Our key result is to show that if a function of the history (called approximate information state (AIS)) approximately satisfies the properties of the information state, then there is a corresponding approximate dynamic program. We show that the policy computed using this is approximately optimal with bounded loss of optimality. We show that several approximations in state, observation and action spaces in literature can be viewed as instances of AIS. In some of these cases, we obtain tighter bounds. A salient feature of AIS is that it can be learnt from data. We present AIS based multi-time scale policy gradient algorithms. and detailed numerical experiments with low, moderate and high dimensional environments.
2021-12-31
Journal of Machine Learning Research (publié)
arxiv.org
arxiv.org
Approximate minimization of weighted tree automata
Borja Balle
Guillaume Rabusseau
2021-12-31
Information and Computation (publié)
doi.org
Aspirations and Practice of Model Documentation: Moving the Needle with Nudging and Traceability
Avinash Bhat
Austin Coursey
Grace Hu
Sixian Li
Nadia Nahar
Shurui Zhou
Christian Kästner
Jin L.C. Guo
2021-12-31
(publié)
doi.org