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
Approximate Bayesian Optimisation for Neural Networks
Segmentation of enhancing tumours or lesions from MRI is important for detecting new disease activity in many clinical contexts. However, ac… (voir plus)curate segmentation requires the inclusion of medical images (e.g., T1 post-contrast MRI) acquired after injecting patients with a contrast agent (e.g., Gadolinium), a process no longer thought to be safe. Although a number of modality-agnostic segmentation networks have been developed over the past few years, they have been met with limited success in the context of enhancing pathology segmentation. In this work, we present HAD-Net, a novel offline adversarial knowledge distillation (KD) technique, whereby a pre-trained teacher segmentation network, with access to all MRI sequences, teaches a student network, via hierarchical adversarial training, to better overcome the large domain shift presented when crucial images are absent during inference. In particular, we apply HAD-Net to the challenging task of enhancing tumour segmentation when access to post-contrast imaging is not available. The proposed network is trained and tested on the BraTS 2019 brain tumour segmentation challenge dataset, where it achieves performance improvements in the ranges of 16% - 26% over (a) recent modality-agnostic segmentation methods (U-HeMIS, U-HVED), (b) KD-Net adapted to this problem, (c) the pre-trained student network and (d) a non-hierarchical version of the network (AD-Net), in terms of Dice scores for enhancing tumour (ET). The network also shows improvements in tumour core (TC) Dice scores. Finally, the network outperforms both the baseline student network and AD-Net in terms of uncertainty quantification for enhancing tumour segmentation based on the BraTS 2019 uncertainty challenge metrics. Our code is publicly available at: https://github.com/SaverioVad/HAD_Net
2021-08-25
Proceedings of the Fourth Conference on Medical Imaging with Deep Learning (publié)
Generating community measures of food purchasing activities using store-level electronic grocery transaction records: an ecological study in Montreal, Canada
Elaborate social interaction is a pivotal asset of the human species. The complexity of people’s social lives may constitute the dominatin… (voir plus)g factor in the vibrancy of many individuals’ environment. The neural substrates linked to social cognition thus appear especially susceptible when people endure periods of social isolation: here, we zoom in on the systematic inter-relationships between two such neural substrates, the allocortical hippocampus (HC) and the neocortical default network (DN). Previous human social neuroscience studies have focused on the DN, while HC subfields have been studied in most detail in rodents and monkeys. To bring into contact these two separate research streams, we directly quantified how DN subregions are coherently co-expressed with specific HC subfields in the context of social isolation. A two-pronged decomposition of structural brain scans from ∼40,000 UK Biobank participants linked lack of social support to mostly lateral subregions in the DN patterns. This lateral DN association co-occurred with HC patterns that implicated especially subiculum, presubiculum, CA2, CA3, and dentate gyrus. Overall, the subregion divergences within spatially overlapping signatures of HC-DN co-variation followed a clear segregation divide into the left and right brain hemispheres. Separable regimes of structural HC-DN co-variation also showed distinct associations with the genetic predisposition for lacking social support at the population level.
A modified Thompson sampling-based learning algorithm for unknown linear systems
Yi. Ouyang
Mukul Gagrani
Rahul Jain
We revisit the Thompson sampling-based learning algorithm for controlling an unknown linear system with quadratic cost proposed in [1]. This… (voir plus) algorithm operates in episodes of dynamic length and it is shown to have a regret bound of
In this article, we consider the problem of controlling an unknown linear quadratic Gaussian (LQG) system consisting of multiple subsystems … (voir plus)connected over a network. Our goal is to minimize and quantify the regret (i.e., loss in performance) of our learning and control strategy with respect to an oracle who knows the system model. Upfront viewing the interconnected subsystems globally and directly using existing LQG learning algorithms for the global system results in a regret that increases super-linearly with the number of subsystems. Instead, we propose a new Thompson sampling-based learning algorithm which exploits the structure of the underlying network. We show that the expected regret of the proposed algorithm is bounded by
Forgetting is a normal process in healthy brains, and evidence suggests that the mammalian brain forgets more than is required based on limi… (voir plus)tations of mnemonic capacity. Episodic memories, in particular, are liable to be forgotten over time. Researchers have hypothesized that it may be beneficial for decision making to forget episodic memories over time. Reinforcement learning offers a normative framework in which to test such hypotheses. Here, we show that a reinforcement learning agent that uses an episodic memory cache to find rewards in maze environments can forget a large percentage of older memories without any performance impairments, if they utilize mnemonic representations that contain structural information about space. Moreover, we show that some forgetting can actually provide a benefit in performance compared to agents with unbounded memories. Our analyses of the agents show that forgetting reduces the influence of outdated information and states which are not frequently visited on the policies produced by the episodic control system. These results support the hypothesis that some degree of forgetting can be beneficial for decision making, which can help to explain why the brain forgets more than is required by capacity limitations.
Recent years have seen a dramatic increase in studies measuring brain activity, physiological responses, and/or movement data from multiple … (voir plus)individuals during social interaction. For example, so-called “hyperscanning” research has demonstrated that brain activity may become synchronized across people as a function of a range of factors. Such findings not only underscore the potential of hyperscanning techniques to capture meaningful aspects of naturalistic interactions, but also raise the possibility that hyperscanning can be leveraged as a tool to help improve such naturalistic interactions. Building on our previous work showing that exposing dyads to real-time inter-brain synchrony neurofeedback may help boost their interpersonal connectedness, we describe the biofeedback application Hybrid Harmony, a Brain-Computer Interface (BCI) that supports the simultaneous recording of multiple neurophysiological datastreams and the real-time visualization and sonification of inter-subject synchrony. We report results from 236 dyads experiencing synchrony neurofeedback during naturalistic face-to-face interactions, and show that pairs' social closeness and affective personality traits can be reliably captured with the inter-brain synchrony neurofeedback protocol, which incorporates several different online inter-subject connectivity analyses that can be applied interchangeably. Hybrid Harmony can be used by researchers who wish to study the effects of synchrony biofeedback, and by biofeedback artists and serious game developers who wish to incorporate multiplayer situations into their practice.