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
Handling Black Swan Events in Deep Learning with Diversely Extrapolated Neural Networks
By virtue of their expressive power, neural networks (NNs) are well suited to fitting large, complex datasets, yet they are also known to
… (voir plus)produce similar predictions for points outside the training distribution.
As such, they are, like humans, under the influence of the Black Swan theory: models tend to be extremely "surprised" by rare events, leading to potentially disastrous consequences, while justifying these same events in hindsight.
To avoid this pitfall, we introduce DENN, an ensemble approach building a set of Diversely Extrapolated Neural Networks that fits the training data and is able to generalize more diversely when extrapolating to novel data points.
This leads DENN to output highly uncertain predictions for unexpected inputs.
We achieve this by adding a diversity term in the loss function used to train the model, computed at specific inputs.
We first illustrate the usefulness of the method on a low-dimensional regression problem.
Then, we show how the loss can be adapted to tackle anomaly detection during classification, as well as safe imitation learning problems.
2020-07-01
International Joint Conference on Artificial Intelligence (publié)
When an agent has limited information on its environment, the suboptimality of an RL algorithm can be decomposed into the sum of two terms: … (voir plus)a term related to an asymptotic bias (suboptimality with unlimited data) and a term due to overfitting (additional suboptimality due to limited data). In the context of reinforcement learning with partial observability, this paper provides an analysis of the tradeoff between these two error sources. In particular, our theoretical analysis formally characterizes how a smaller state representation increases the asymptotic bias while decreasing the risk of overfitting.
2020-07-01
International Joint Conference on Artificial Intelligence (publié)
Visual referring expression recognition is a challenging task that requires natural language understanding in the context of an image. We cr… (voir plus)itically examine RefCOCOg, a standard benchmark for this task, using a human study and show that 83.7% of test instances do not require reasoning on linguistic structure, i.e., words are enough to identify the target object, the word order doesn’t matter. To measure the true progress of existing models, we split the test set into two sets, one which requires reasoning on linguistic structure and the other which doesn’t. Additionally, we create an out-of-distribution dataset Ref-Adv by asking crowdworkers to perturb in-domain examples such that the target object changes. Using these datasets, we empirically show that existing methods fail to exploit linguistic structure and are 12% to 23% lower in performance than the established progress for this task. We also propose two methods, one based on contrastive learning and the other based on multi-task learning, to increase the robustness of ViLBERT, the current state-of-the-art model for this task. Our datasets are publicly available at https://github.com/aws/aws-refcocog-adv.
2020-07-01
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (publié)
This compendium gathers all the accepted extended abstracts from the Third International Conference on Medical Imaging with Deep Learning (M… (voir plus)IDL 2020), held in Montreal, Canada, 6-9 July 2020. Note that only accepted extended abstracts are listed here, the Proceedings of the MIDL 2020 Full Paper Track are published in the Proceedings of Machine Learning Research (PMLR).
Multimorbidity increases care needs among people with chronic diseases. In order to support communication between patients, their informal c… (voir plus)aregivers and their healthcare teams, we developed CONCERTO+, a patient portal for chronic disease management in primary care. A user-centered design comprising 3 iterations with patients and informal caregivers was performed. Clinicians were also invited to provide feedback on the feasibility of the solution. Several improvements were brought to CONCERTO+, and it is now ready to be implemented in real-life setting.
We study the implicit regularization of optimization methods for linear models interpolating the training data in the under-parametrized and… (voir plus) over-parametrized regimes. Since it is difficult to determine whether an optimizer converges to solutions that minimize a known norm, we flip the problem and investigate what is the corresponding norm minimized by an interpolating solution. Using this reasoning, we prove that for over-parameterized linear regression, projections onto linear spans can be used to move between different interpolating solutions. For under-parameterized linear classification, we prove that for any linear classifier separating the data, there exists a family of quadratic norms ||.||_P such that the classifier's direction is the same as that of the maximum P-margin solution. For linear classification, we argue that analyzing convergence to the standard maximum l2-margin is arbitrary and show that minimizing the norm induced by the data results in better generalization. Furthermore, for over-parameterized linear classification, projections onto the data-span enable us to use techniques from the under-parameterized setting. On the empirical side, we propose techniques to bias optimizers towards better generalizing solutions, improving their test performance. We validate our theoretical results via synthetic experiments, and use the neural tangent kernel to handle non-linear models.
Public health surveillance is the ongoing systematic collection, analysis and interpretation of data, closely integrated with the timely dis… (voir plus)semination of the resulting information to those responsible for preventing and controlling disease and injury. With the rapid development of data science, encompassing big data and artificial intelligence, and with the exponential growth of accessible and highly heterogeneous health-related data, from healthcare providers to user-generated online content, the field of surveillance and health monitoring is changing rapidly. It is, therefore, the right time for a short glossary of key terms in public health surveillance, with an emphasis on new data-science developments in the field.
2020-06-10
Journal of Epidemiology and Community Health (publié)