Le traitement du langage naturel à l'ère de l'IA générative
Rejoignez-nous à Mila en octobre pour un atelier de trois jour visant à explorer le potentiel de transformation des technologies langagières et leurs implications pour la société.
Ce programme est conçu pour fournir aux professionnel·le·s travaillant dans le domaine de la politique une compréhension fondamentale de la technologie de l'IA.
Nous utilisons des témoins pour analyser le trafic et l’utilisation de notre site web, afin de personnaliser votre expérience. Vous pouvez désactiver ces technologies à tout moment, mais cela peut restreindre certaines fonctionnalités du site. Consultez notre Politique de protection de la vie privée pour en savoir plus.
Paramètre des cookies
Vous pouvez activer et désactiver les types de cookies que vous souhaitez accepter. Cependant certains choix que vous ferez pourraient affecter les services proposés sur nos sites (ex : suggestions, annonces personnalisées, etc.).
Cookies essentiels
Ces cookies sont nécessaires au fonctionnement du site et ne peuvent être désactivés. (Toujours actif)
Cookies analyse
Acceptez-vous l'utilisation de cookies pour mesurer l'audience de nos sites ?
Multimedia Player
Acceptez-vous l'utilisation de cookies pour afficher et vous permettre de regarder les contenus vidéo hébergés par nos partenaires (YouTube, etc.) ?
Publications
Quality of Service-Constrained Online Routing in High Throughput Satellites
High throughput satellites (HTSs) outpace traditional satellites due to their multi-beam transmission. The rise of low Earth orbit mega cons… (voir plus)tellations amplifies HTS data rate demands to terabits/second with acceptable latency. This surge in data rate necessitates multiple modems, often exceeding single device capabilities. Consequently, satellites employ several processors, forming a complex packet-switch network. This can lead to potential internal congestion and challenges in adhering to strict quality of service (QoS) constraints. While significant research exists on constellation-level routing, a literature gap remains on the internal routing within a single HTS. The intricacy of this internal network architecture presents a significant challenge to achieve high data rates. This paper introduces an online optimal flow allocation and scheduling method for HTSs. The problem is presented as a multi-commodity flow instance with different priority data streams. An initial full time horizon model is proposed as a benchmark. We apply a model predictive control (MPC) approach to enable adaptive routing based on current information and the forecast within the prediction time horizon while allowing for deviation of the latter. Importantly, MPC is inherently suited to handle uncertainty in incoming flows. Our approach minimizes the packet loss by optimally and adaptively managing the priority queue schedulers and flow exchanges between satellite processing modules. Central to our method is a routing model focusing on optimal priority scheduling to enhance data rates and maintain QoS. The model's stages are critically evaluated, and results are compared to traditional methods via numerical simulations. Through simulations, our method demonstrates performance nearly on par with the hindsight optimum, showcasing its efficiency and adaptability in addressing satellite communication challenges.
Deep Learning Benchmark for First Break Detection from Hardrock Seismic Reflection Data
Pierre-Luc St-Charles
Bruno Rousseau
Joumana Ghosn
Gilles Bellefleur
E. Schetselaar
Deep learning techniques are used to tackle a variety of tasks related to seismic data processing and interpretation. While many works have … (voir plus)shown the benefits of deep learning, assessing the generalization capabilities of proposed methods to data acquired in different conditions and geological environments remains challenging. This is especially true for applications in hardrock environments where seismic surveys are still relatively rare. The primary factors that impede the adoption of machine learning in geosciences include the lack of publicly available and labeled datasets, and the use of inadequate evaluation methodologies. Since machine learning models are prone to overfit and underperform when the data used to train them is site-specific, the applicability of these models on new survey data that could be considered “out-of-distribution” is rarely addressed. This is unfortunate, as evaluating predictive models in out-of-distribution settings can provide a good insight into their usefulness in real-world use cases. To tackle these issues, we propose a simple benchmarking methodology for first break picking to evaluate the transferability of deep learning models that are trained across different environments and acquisition conditions. For this, we consider a reflection seismic survey dataset acquired at five distinct hardrock mining sites combined with annotations for first break picking. We train and evaluate a baseline deep learning solution based on a U-Net for future comparisons, and discuss potential improvements to this approach.
Deep learning models can perform well in complex medical imaging classification tasks, even when basing their conclusions on spurious correl… (voir plus)ations (i.e. confounders), should they be prevalent in the training dataset, rather than on the causal image markers of interest. This would thereby limit their ability to generalize across the population. Explainability based on counterfactual image generation can be used to expose the confounders but does not provide a strategy to mitigate the bias. In this work, we introduce the first end-to-end training framework that integrates both (i) popular debiasing classifiers (e.g. distributionally robust optimization (DRO)) to avoid latching onto the spurious correlations and (ii) counterfactual image generation to unveil generalizable imaging markers of relevance to the task. Additionally, we propose a novel metric, Spurious Correlation Latching Score (SCLS), to quantify the extent of the classifier reliance on the spurious correlation as exposed by the counterfactual images. Through comprehensive experiments on two public datasets (with the simulated and real visual artifacts), we demonstrate that the debiasing method: (i) learns generalizable markers across the population, and (ii) successfully ignores spurious correlations and focuses on the underlying disease pathology.
2023-10-09
Clinical Image-Based Procedures, Fairness of AI in Medical Imaging, and Ethical and Philosophical Issues in Medical Imaging (publié)
Image-based precision medicine aims to personalize treatment decisions based on an individual's unique imaging features so as to improve the… (voir plus)ir clinical outcome. Machine learning frameworks that integrate uncertainty estimation as part of their treatment recommendations would be safer and more reliable. However, little work has been done in adapting uncertainty estimation techniques and validation metrics for precision medicine. In this paper, we use Bayesian deep learning for estimating the posterior distribution over factual and counterfactual outcomes on several treatments. This allows for estimating the uncertainty for each treatment option and for the individual treatment effects (ITE) between any two treatments. We train and evaluate this model to predict future new and enlarging T2 lesion counts on a large, multi-center dataset of MR brain images of patients with multiple sclerosis, exposed to several treatments during randomized controlled trials. We evaluate the correlation of the uncertainty estimate with the factual error, and, given the lack of ground truth counterfactual outcomes, demonstrate how uncertainty for the ITE prediction relates to bounds on the ITE error. Lastly, we demonstrate how knowledge of uncertainty could modify clinical decision-making to improve individual patient and clinical trial outcomes.
In this study, we highlight the importance of enhancing the quality of pretraining data in multilingual language models.
Existing web crawl… (voir plus)s have demonstrated quality issues, particularly in the context of low-resource languages.
Consequently, we introduce a new multilingual pretraining corpus for
Accelerating material discovery holds the potential to greatly help mitigate the climate crisis. Discovering new solid-state materials such … (voir plus)as electrocatalysts, super-ionic conductors or photovoltaic materials can have a crucial impact, for instance, in improving the efficiency of renewable energy production and storage. In this paper, we introduce Crystal-GFN, a generative model of crystal structures that sequentially samples structural properties of crystalline materials, namely the space group, composition and lattice parameters. This domain-inspired approach enables the flexible incorporation of physical and structural hard constraints, as well as the use of any available predictive model of a desired physicochemical property as an objective function. To design stable materials, one must target the candidates with the lowest formation energy. Here, we use as objective the formation energy per atom of a crystal structure predicted by a new proxy machine learning model trained on MatBench. The results demonstrate that Crystal-GFN is able to sample highly diverse crystals with low (median -3.1 eV/atom) predicted formation energy.
In the age of artificial intelligence, the role of large language models (LLMs) is becoming increasingly central. Despite their growing prev… (voir plus)alence, their capacity to consolidate knowledge from different training documents—a crucial ability in numerous applications—remains unexplored. This paper presents the first study examining the capability of LLMs to effectively combine such information within their parameter space. We introduce EpiK-Eval, a novel question-answering benchmark tailored to evaluate LLMs' proficiency in formulating a coherent and consistent knowledge representation from segmented narratives. Evaluations across various LLMs reveal significant weaknesses in this domain. We contend that these shortcomings stem from the intrinsic nature of prevailing training objectives. Consequently, we advocate for refining the approach towards knowledge consolidation, as it harbors the potential to dramatically improve their overall effectiveness and performance. The findings from this study offer insights for developing more robust and reliable LLMs. Our code and benchmark are available at https://github.com/chandar-lab/EpiK-Eval