Publications

Playing the System: Can Puzzle Players Teach us How to Solve Hard Problems?
Renata Mutalova
Roman Sarrazin-Gendron
Eddie Cai
Gabriel Richard
Parham Ghasemloo Gheidari
Sébastien Caisse
Rob Knight
Mathieu Blanchette
Attila Szantner
Jérôme Waldispühl
With nearly three billion players, video games are more popular than ever. Casual puzzle games are among the most played categories. These g… (voir plus)ames capitalize on the players’ analytical and problem-solving skills. Can we leverage these abilities to teach ourselves how to solve complex combinatorial problems? In this study, we harness the collective wisdom of millions of players to tackle the classical NP-hard problem of multiple sequence alignment, relevant to many areas of biology and medicine. We show that Borderlands Science players propose solutions to multiple sequence alignment tasks that perform as well or better than standard approaches, while exploring a much larger area of the Pareto-optimal solution space. We also show the strategies of the players, although highly heterogeneous, follow a collective logic that can be mimicked with Behavioral Cloning with minimal performance loss, allowing the players’ collective wisdom to be leveraged for alignment of any sequences.
2023-04-18
International Conference on Human Factors in Computing Systems (publié)
doi.org
Using rare genetic mutations to revisit structural brain asymmetry
Jakub Kopal
Kuldeep Kumar
Kimia Shafighi
Karin Saltoun
Claudia Modenato
Clara A. Moreau
Guillaume Huguet
Martineau Jean-Louis
Charles-Olivier Martin
Charles-Olivier Martin
Zohra Saci
Nadine Younis
Elise Douard
Khadije Jizi
Alexis Beauchamp-Chatel
Leila Kushan
Ana I. Silva
Marianne B. M. van den Bree
David E. J. Linden
Michael J. Owen … (voir 11 de plus)
Jeremy Hall
Sarah Lippé
Bogdan Draganski
Ida E. Sønderby
Ole A. Andreassen
David C. Glahn
Paul M. Thompson
Carrie E. Bearden
Robert Zatorre
Sébastien Jacquemont
Danilo Bzdok
Asymmetry between the left and right brain is a key feature of brain organization. Hemispheric functional specialization underlies some of t… (voir plus)he most advanced human-defining cognitive operations, such as articulated language, perspective taking, or rapid detection of facial cues. Yet, genetic investigations into brain asymmetry have mostly relied on common variant studies, which typically exert small effects on brain phenotypes. Here, we leverage rare genomic deletions and duplications to study how genetic alterations reverberate in human brain and behavior. We quantitatively dissected the impact of eight high-effect-size copy number variations (CNVs) on brain asymmetry in a multi-site cohort of 552 CNV carriers and 290 non-carriers. Isolated multivariate brain asymmetry patterns spotlighted regions typically thought to subserve lateralized functions, including language, hearing, as well as visual, face and word recognition. Planum temporale asymmetry emerged as especially susceptible to deletions and duplications of specific gene sets. Targeted analysis of common variants through genome-wide association study (GWAS) consolidated partly diverging genetic influences on the right versus left planum temporale structure. In conclusion, our gene-brain-behavior mapping highlights the consequences of genetically controlled brain lateralization on human-defining cognitive traits.
2023-04-17
bioRxiv (prépublication)
doi.org
Fast D
<sub>M,M</sub> calculation in LDR brachytherapy using deep learning methods
Francisco Berumen
S. Enger
Luc Beaulieu
2023-04-13
Physics in Medicine and Biology (publié)
doi.org
Meta Pseudo Labels for Anomaly Detection via Partially Observed Anomalies
Sinong Zhao
Zhaoyang Yu
Xiaofei Wang
T. Marbach
Gang Wang
Xiaoguang Liu
2023-04-13
Database Systems for Advanced Applications (publié)
doi.org
VulANalyzeR: Explainable Binary Vulnerability Detection with Multi-task Learning and Attentional Graph Convolution
Litao Li
Steven H. H. Ding
Yuan Tian
Benjamin C. M. Fung
Philippe Charland
Weihan Ou
Leo Song
Congwei Chen
2023-04-13
ACM Transactions on Privacy and Security (publié)
doi.org
SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)
Shamsuddeen Hassan Muhammad
Idris Abdulmumin
Seid Muhie Yimam
David Ifeoluwa Adelani
Ibrahim Ahmad
Nedjma OUSIDHOUM
Abinew Ayele
Saif Mohammad
Meriem Beloucif
2023-04-12
ArXiv (prépublication)
doi.org
arxiv.org
Adaptive patch foraging in deep reinforcement learning agents
Nathan Wispinski
Andrew Butcher
Kory Mathewson
Craig S Chapman
Matthew Botvinick
Patrick M. Pilarski
Patch foraging is one of the most heavily studied behavioral optimization challenges in biology. However, despite its importance to biologic… (voir plus)al intelligence, this behavioral optimization problem is understudied in artificial intelligence research. Patch foraging is especially amenable to study given that it has a known optimal solution, which may be difficult to discover given current techniques in deep reinforcement learning. Here, we investigate deep reinforcement learning agents in an ecological patch foraging task. For the first time, we show that machine learning agents can learn to patch forage adaptively in patterns similar to biological foragers, and approach optimal patch foraging behavior when accounting for temporal discounting. Finally, we show emergent internal dynamics in these agents that resemble single-cell recordings from foraging non-human primates, which complements experimental and theoretical work on the neural mechanisms of biological foraging. This work suggests that agents interacting in complex environments with ecologically valid pressures arrive at common solutions, suggesting the emergence of foundational computations behind adaptive, intelligent behavior in both biological and artificial agents.
2023-04-11
TMLR (accepté)
doi.org
openreview.net
Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
Gandharv Patil
Prashanth L.A.
Dheeraj M. Nagaraj
Doina Precup
We study the finite-time behaviour of the popular temporal difference (TD) learning algorithm, when combined with tail-averaging. We derive … (voir plus)finite time bounds on the parameter error of the tail-averaged TD iterate under a step-size choice that does not require information about the eigenvalues of the matrix underlying the projected TD fixed point. Our analysis shows that tail-averaged TD converges at the optimal O (1/t) rate, both in expectation and with high probability. In addition, our bounds exhibit a sharper rate of decay for the initial error (bias), which is an improvement over averaging all iterates. We also propose and analyse a variant of TD that incorporates regularisation, and show that this variant fares favourably in problems with ill-conditioned features.
2023-04-10
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (publié)
doi.org
proceedings.mlr.press
A Novel Stochastic Gradient Descent Algorithm for LearningPrincipal Subspaces
Charline Le Lan
Joshua Greaves
Jesse Farebrother
Mark Rowland
Fabian Pedregosa
Rishabh Agarwal
Bellemare Marc-Emmanuel
In this paper, we derive an algorithm that learns a principal subspace from sample entries, can be applied when the approximate subspace i… (voir plus)s represented by a neural network, and hence can bescaled to datasets with an effectively infinite number of rows and columns. Our method consistsin defining a loss function whose minimizer is the desired principal subspace, and constructing agradient estimate of this loss whose bias can be controlled.
2023-04-10
Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (publié)
doi.org
proceedings.mlr.press
A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation
Florian Bordes
Samuel Lavoie
Randall Balestriero
Nicolas Ballas
P Vincent
2023-04-10
ArXiv (prépublication)
doi.org
arxiv.org
Conservative objective models are a special kind of contrastive divergence-based energy model
Christopher Beckham
Christopher Pal
In this work we theoretically show that conservative objective models (COMs) for offline model-based optimisation (MBO) are a special kind o… (voir plus)f contrastive divergence-based energy model, one where the energy function represents both the unconditional probability of the input and the conditional probability of the reward variable. While the initial formulation only samples modes from its learned distribution, we propose a simple fix that replaces its gradient ascent sampler with a Langevin MCMC sampler. This gives rise to a special probabilistic model where the probability of sampling an input is proportional to its predicted reward. Lastly, we show that better samples can be obtained if the model is decoupled so that the unconditional and conditional probabilities are modelled separately.
2023-04-06
ArXiv (prépublication)
doi.org
arxiv.org
Approach Intelligent Writing Assistants Usability with Seven Stages of Action
Avinash Bhat
Disha Shrivastava
Jin L.C. Guo
2023-04-05
ArXiv (prépublication)
doi.org
arxiv.org