Publications

Agnostic Physics-Driven Deep Learning
Benjamin Scellier
Siddhartha Mishra
Yoshua Bengio
Yann Ollivier
2022-05-29
ArXiv (prépublication)
doi.org
arxiv.org
Multi-language design smells: a backstage perspective
Mouna Abidi
Md Saidur Rahman
Moses Openja
Foutse Khomh
2022-05-29
Empirical Software Engineering (publié)
doi.org
Works for Me! Cannot Reproduce – A Large Scale Empirical Study of Non-reproducible Bugs
Mohammad Masudur Rahman
Foutse Khomh
Marco Castelluccio
2022-05-29
Empirical Software Engineering (publié)
doi.org
Adaptive Confidence Calibration
David Meger
Jonathan W. Pearce
2022-05-26
Applied Informatics (publié)
doi.org
Contextual bandit optimization of super-resolution microscopy
Anthony Bilodeau
Renaud Bernatchez
Albert Michaud-Gagnon
Flavie Lavoie-Cardinal
Audrey Durand
2022-05-26
Applied Informatics (publié)
doi.org
Efficient Fine-Tuning of BERT Models on the Edge
Danilo Vucetic
Mohammadreza Tayaranian
Maryam Ziaeefard
James J. Clark
Brett H. Meyer
Warren J. Gross
Resource-constrained devices are increasingly the deployment targets of machine learning applications. Static models, however, do not always… (voir plus) suffice for dynamic environments. On-device training of models allows for quick adaptability to new scenarios. With the increasing size of deep neural networks, as noted with the likes of BERT and other natural language processing models, comes increased resource requirements, namely memory, computation, energy, and time. Furthermore, training is far more resource intensive than inference. Resource-constrained on-device learning is thus doubly difficult, especially with large BERT-like models. By reducing the memory usage of fine-tuning, pre-trained BERT models can become efficient enough to fine-tune on resource-constrained devices. We propose Freeze And Reconfigure (FAR), a memory-efficient training regime for BERT-like models that reduces the memory usage of activation maps during fine-tuning by avoiding unnecessary parameter updates. FAR reduces fine-tuning time on the DistilBERT model and CoLA dataset by 30%, and time spent on memory operations by 47%. More broadly, reductions in metric performance on the GLUE and SQuAD datasets are around 1% on average.
2022-05-26
2022 IEEE International Symposium on Circuits and Systems (ISCAS) (publié)
doi.org
arxiv.org
Evaluating Multimodal Interactive Agents
Josh Abramson
Arun Ahuja
Federico Carnevale
Petko Georgiev
Alex Goldin
Alden Hung
Jessica Landon
Timothy P Lillicrap
Alistair M. Muldal
Blake Aaron Richards
Adam Santoro
Tamara von Glehn
Greg Wayne
Nathaniel Wong
Chen Yan
Creating agents that can interact naturally with humans is a common goal in artificial intelligence (AI) research. However, evaluating these… (voir plus) interactions is challenging: collecting online human-agent interactions is slow and expensive, yet faster proxy metrics often do not correlate well with interactive evaluation. In this paper, we assess the merits of these existing evaluation metrics and present a novel approach to evaluation called the Standardised Test Suite (STS). The STS uses behavioural scenarios mined from real human interaction data. Agents see replayed scenario context, receive an instruction, and are then given control to complete the interaction offline. These agent continuations are recorded and sent to human annotators to mark as success or failure, and agents are ranked according to the proportion of continuations in which they succeed. The resulting STS is fast, controlled, interpretable, and representative of naturalistic interactions. Altogether, the STS consolidates much of what is desirable across many of our standard evaluation metrics, allowing us to accelerate research progress towards producing agents that can interact naturally with humans. A video may be found at https://youtu.be/YR1TngGORGQ.
2022-05-25
ArXiv (prépublication)
doi.org
arxiv.org
Assessing the Quality of Direct-to-Consumer Teleconsultation Services in Canada
Jean Noel Nikiema
Eleah Stringer
Marie-Pierre Moreault
Priscille Pana
Marco Laverdiere
Catherine Régis
Jean-Louis Denis
Béatrice Godard
Mylaine Breton
Guy Paré
Aviv Shachak
Claudia Lai
Elizabeth M. Borycki
Andre W. Kushniruk
Aude Motulsky
The objective of this study was to describe and assess the quality of the direct-to-consumer medical teleconsultation landscape in three Can… (voir plus)adian provinces. An environmental scan of primary care teleconsultation platforms was conducted in January 2022 to identify medical teleconsultation platforms in Quebec (Qc), Ontario, and British Columbia (BC). The quality of each teleconsultation platform was assessed using a modified version of the HONcode principles. Nineteen different direct-to-consumer medical teleconsultation platforms were identified across the three provinces. The quality of these teleconsultation platforms was very heterogeneous. The landscape of virtual primary care is changing rapidly in the Canadian ecosystem, and the transparency of current teleconsultation platforms could be improved.
2022-05-24
Studies in Health Technology and Informatics (publié)
doi.org
A Conceptual Framework for Representing Events Under Public Health Surveillance.
Anya Okhmatovskaia
Yannan Shen
Iris Ganser
Nigel Collier
Nicholas B. King
Zaiqiao Meng
David L. Buckeridge
Information integration across multiple event-based surveillance (EBS) systems has been shown to improve global disease surveillance in expe… (voir plus)rimental settings. In practice, however, integration does not occur due to the lack of a common conceptual framework for encoding data within EBS systems. We aim to address this gap by proposing a candidate conceptual framework for representing events and related concepts in the domain of public health surveillance.
2022-05-24
Studies in Health Technology and Informatics (publié)
doi.org
Correlated Read Noise Reduction in Infrared Arrays Using Deep Learning
Guillaume Payeur
Étienne Artigaud
Laurence Perreault Levasseur
René Doyon
We present a new procedure rooted in deep learning to construct science images from data cubes collected by astronomical instruments using H… (voir plus)xRG detectors in low-flux regimes. It improves on the drawbacks of the conventional algorithms to construct 2D images from multiple readouts by using the readout scheme of the detectors to reduce the impact of correlated readout noise. We train a convolutional recurrent neural network on simulated astrophysical scenes added to laboratory darks to estimate the flux on each pixel of science images. This method achieves a reduction of the noise on constructed science images when compared to standard flux-measurement schemes (correlated double sampling, up-the-ramp sampling), which results in a reduction of the error on the spectrum extracted from these science images. Over simulated data cubes created in a low signal-to-noise ratio regime where this method could have the largest impact, we find that the error on our constructed science images falls faster than a
2022-05-24
Astronomical Journal (publié)
doi.org
arxiv.org
MaskEval: Weighted MLM-Based Evaluation for Text Summarization and Simplification
Yu Lu Liu
Rachel Bawden
Thomas Scaliom
Benoı̂t Sagot
Jackie CK Cheung
2022-05-23
ArXiv (prépublication)
doi.org
arxiv.org
AB0393 SURVIVAL ON JANUS KINASE INHIBITORS VERSUS OTHER ADVANCED THERAPIES IN RHEUMATOID ARTHRITIS
N. Bakhtiar
Leanne Gray
S. Bilgrami
Lesley Lesley Ottewell
Frank N. Wood
Mohsin Bukhari
2022-05-22
Annals of the Rheumatic Diseases (publié)
doi.org