Publications

Efficient Epistemic Uncertainty Estimation in Regression Ensemble Models Using Pairwise-Distance Estimators
Lucas Berry
David Meger
This work introduces an efficient novel approach for epistemic uncertainty estimation for ensemble models for regression tasks using pairwis… (voir plus)e-distance estimators (PaiDEs). Utilizing the pairwise-distance between model components, these estimators establish bounds on entropy. We leverage this capability to enhance the performance of Bayesian Active Learning by Disagreement (BALD). Notably, unlike sample-based Monte Carlo estimators, PaiDEs exhibit a remarkable capability to estimate epistemic uncertainty at speeds up to 100 times faster while covering a significantly larger number of inputs at once and demonstrating superior performance in higher dimensions. To validate our approach, we conducted a varied series of regression experiments on commonly used benchmarks: 1D sinusoidal data,
2023-08-24
ArXiv (prépublication)
arxiv.org
arxiv.org
A comparison of reinforcement learning frameworks for software testing tasks
Paulina Stevia Nouwou Mindom
Amin Nikanjam
Foutse Khomh
2023-08-23
Empirical Software Engineering (publié)
doi.org
arxiv.org
Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?
Salah Zaiem
Youcef Kemiche
Titouan Parcollet
Slim Essid
Mirco Ravanelli
Self-supervised learning (SSL) has recently allowed leveraging large datasets of unlabeled speech signals to reach impressive performance on… (voir plus) speech tasks using only small amounts of annotated data. The high number of proposed approaches fostered the need and rise of extended benchmarks that evaluate their performance on a set of downstream tasks exploring various aspects of the speech signal. However, and while the number of considered tasks has been growing, most rely upon a single decoding architecture that maps the frozen SSL representations to the downstream labels. This work investigates the robustness of such benchmarking results to changes in the decoder architecture. Interestingly, it appears that varying the architecture of the downstream decoder leads to significant variations in the leaderboards of most tasks. Concerningly, our study reveals that benchmarking using limited decoders may cause a counterproductive increase in the sizes of the developed SSL models.
2023-08-19
INTERSPEECH 2023 (publié)
doi.org
arxiv.org
MARCO: A Memory-Augmented Reinforcement Framework for Combinatorial Optimization
Andoni I. Garmendia
Quentin Cappart
Josu Ceberio
Alexander Mendiburu
2023-08-18
Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence (publié)
doi.org
arxiv.org
Open, Closed, or Small Language Models for Text Classification?
Hao Yu
Zachary Yang
Kellin Pelrine
Jean-François Godbout
Reihaneh Rabbany
Recent advancements in large language models have demonstrated remarkable capabilities across various NLP tasks. But many questions remain, … (voir plus)including whether open-source models match closed ones, why these models excel or struggle with certain tasks, and what types of practical procedures can improve performance. We address these questions in the context of classification by evaluating three classes of models using eight datasets across three distinct tasks: named entity recognition, political party prediction, and misinformation detection. While larger LLMs often lead to improved performance, open-source models can rival their closed-source counterparts by fine-tuning. Moreover, supervised smaller models, like RoBERTa, can achieve similar or even greater performance in many datasets compared to generative LLMs. On the other hand, closed models maintain an advantage in hard tasks that demand the most generalizability. This study underscores the importance of model selection based on task requirements
2023-08-18
ArXiv (prépublication)
doi.org
arxiv.org
Pontomedullary junction as a reference for spinal cord cross-sectional area: validation across neck positions
Sandrine Bédard
Maxime Bouthillier
Julien Cohen-Adad
Spinal cord cross-sectional area (CSA) is an important MRI biomarker to assess spinal cord atrophy in various neurodegenerative and traumati… (voir plus)c spinal cord diseases. However, the conventional method of computing CSA based on vertebral levels is inherently flawed, as the prediction of spinal levels from vertebral levels lacks reliability, leading to considerable variability in CSA measurements. Computing CSA from an intrinsic neuroanatomical reference, the pontomedullary junction (PMJ), has been proposed in previous work to overcome limitations associated with using a vertebral reference. However, the validation of this alternative approach, along with its variability across and within participants under variable neck extensions, remains unexplored. The goal of this study was to determine if the variability of CSA across neck flexions/extensions is reduced when using the PMJ, compared to vertebral levels. Ten participants underwent a 3T MRI T2w isotropic scan at 0.6 mm3 for 3 neck positions: extension, neutral and flexion. Spinal cord segmentation, vertebral labeling, PMJ labeling, and CSA were computed automatically while spinal segments were labeled manually. Mean coefficient of variation for CSA across neck positions was 3.99 ± 2.96% for the PMJ method vs. 4.02 ± 3.01% for manual spinal segment method vs. 4.46 ± 3.10% for the disc method. These differences were not statistically significant. The PMJ method was slightly more reliable than the disc-based method to compute CSA at specific spinal segments, although the difference was not statistically significant. This suggests that the PMJ can serve as a valuable alternative and reliable method for estimating CSA when a disc-based approach is challenging or not feasible, such as in cases involving fused discs in individuals with spinal cord injuries.
2023-08-18
Scientific Reports (publié)
doi.org
GTM-decon: guided-topic modeling of single-cell transcriptomes enables sub-cell-type and disease-subtype deconvolution of bulk transcriptomes
Lakshmipuram Seshadri Swapna
Michael Huang
Yuemei Li
2023-08-17
Genome Biology (publié)
doi.org
YORC: Yoruba Reading Comprehension dataset
Aremu Anuoluwapo
Jesujoba Oluwadara Alabi
David Ifeoluwa Adelani
In this paper, we create YORC: a new multi-choice Yoruba Reading Comprehension dataset that is based on Yoruba high-school reading comprehen… (voir plus)sion examination. We provide baseline results by performing cross-lingual transfer using existing English RACE dataset based on a pre-trained encoder-only model. Additionally, we provide results by prompting large language models (LLMs) like GPT-4.
2023-08-17
ArXiv (prépublication)
doi.org
arxiv.org
Age-related bias and artificial intelligence: a scoping review
Charlene H Chu
Simon Donato-Woodger
Shehroz S Khan
Rune Nyrup
Kathleen Leslie
Alexandra Lyn
Tianyu Shi
Andria Bianchi
S. A. Rahimi
Amanda Grenier
2023-08-16
Humanities and Social Sciences Communications (publié)
doi.org
Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
Patrick Mark Butlin
Run Long
Eric Elmoznino
Yoshua Bengio
Jonathan C. P. Birch
Axel Constant
George Deane
S. Fleming
C. Frith
Xuanxiu Ji
Ryota Kanai
C. Klein
Grace W. Lindsay
Matthias Michel
Liad Mudrik
Megan A. K. Peters
Eric Schwitzgebel
Jonathan Simon
Rufin Vanrullen
2023-08-16
ArXiv (prépublication)
doi.org
arxiv.org
ASTROPHOT: fitting everything everywhere all at once in astronomical images
Connor J. Stone
Stéphane Courteau
Jean-Charles Cuillandre
Yashar Hezaveh
Laurence Perreault-Levasseur
Nikhil Arora
We present AstroPhot, a fast, powerful, and user-friendly Python based astronomical image photometry solver. AstroPhot incorporates automati… (voir plus)c differentiation and GPU (or parallel CPU) acceleration, powered by the machine learning library PyTorch. Everything: AstroPhot can fit models for sky, stars, galaxies, PSFs, and more in a principled Chi^2 forward optimization, recovering Bayesian posterior information and covariance of all parameters. Everywhere: AstroPhot can optimize forward models on CPU or GPU; across images that are large, multi-band, multi-epoch, rotated, dithered, and more. All at once: The models are optimized together, thus handling overlapping objects and including the covariance between parameters (including PSF and galaxy parameters). A number of optimization algorithms are available including Levenberg-Marquardt, Gradient descent, and No-U-Turn MCMC sampling. With an object-oriented user interface, AstroPhot makes it easy to quickly extract detailed information from complex astronomical data for individual images or large survey programs. This paper outlines novel features of the AstroPhot code and compares it to other popular astronomical image modeling software. AstroPhot is open-source, fully Python based, and freely accessible here: https://github.com/Autostronomy/AstroPhot
2023-08-15
Monthly Notices of the Royal Astronomical Society (inconnu)
doi.org
arxiv.org
BamQuery: a proteogenomic tool to explore the immunopeptidome and prioritize actionable tumor antigens
Maria Virginia Ruiz Cuevas
Marie-Pierre Hardy
Jean-David Larouche
Anca Apavaloaei
Eralda Kina
Krystel Vincent
Patrick Gendron
Jean-Philippe Laverdure
Chantal Durette
Pierre Thibault
Sébastien Lemieux
Claude Perreault
Gregory Ehx
MHC-I-associated peptides (MAPs) derive from selective yet highly diverse genomic regions, including allegedly non-protein-coding sequences,… (voir plus) such as endogenous retroelements (EREs). Quantifying canonical (exonic) and non-canonical MAPs-encoding RNA expression in malignant and benign cells is critical for identifying tumor antigens (TAs) but represents a challenge for immunologists. We present BamQuery, a computational tool attributing an exhaustive RNA expression to MAPs of any origin (exon, intron, UTR, intergenic) from bulk and single-cell RNA-sequencing data. We show that non-canonical MAPs (including TAs) can derive from multiple different genomic regions (up to 35,343 for EREs), abundantly expressed in normal tissues. We also show that supposedly tumor-specific mutated MAPs, viral MAPs, and MAPs derived from proteasomal splicing can arise from different unmutated non-canonical genomic regions. The genome-wide approach of BamQuery allows comprehensive mapping of all MAPs in healthy and cancer tissues. BamQuery can also help predict MAP immunogenicity and identify safe and actionable TAs.
2023-08-14
Genome Biology (publié)
doi.org