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
Investigation of the Dosimetry Characteristics of the GAFCHROMIC® EBT3 Film Response to Alpha Particle Irradiation
Aiming to build foundation models for time-series forecasting and study their scaling behavior, we present here our work-in-progress on Lag-… (voir plus)Llama, a general-purpose univariate probabilistic time-series forecasting model trained on a large collection of time-series data. The model shows good zero-shot prediction capabilities on unseen "out-of-distribution" time-series datasets, outperforming supervised baselines. We use smoothly broken power-laws to fit and predict model scaling behavior. The open source code is made available at
https://github.com/kashif/pytorch-transformer-ts.
The current mainstream software for peptide-centric tandem mass spectrometry data analysis can be categorized as either database-driven, whi… (voir plus)ch rely on a library of mass spectra to identify the peptide associated with novel query spectra, or de novo sequencing-based, which aim to find the entire peptide sequence by relying only on the query mass spectrum. While the first paradigm currently produces state-of-the-art results in peptide identification tasks, it does not inherently make use of information present in the query mass spectrum itself to refine identifications. Meanwhile, de novo approaches attempt to solve a complex problem in one go, without any search space constraints in the general case, leading to comparatively poor results. In this paper, we decompose the de novo problem into putatively easier subproblems, and we show that peptide identification rates of database-driven methods may be improved in terms of peptide identification rate by solving one such subsproblem without requiring a solution for the complete de novo task. We demonstrate this using a de novo peptide length prediction task as the chosen subproblem. As a first prototype, we show that a deep learning-based length prediction model increases peptide identification rates in the ProteomeTools dataset as part of an Pepid-based identification pipeline. Using the predicted information to better rank the candidates, we show that combining ideas from the two paradigms produces clear benefits in this setting. We propose that the next generation of peptide-centric tandem mass spectrometry identification methods should combine elements of these paradigms by mining facts “de novo; about the peptide represented in a spectrum, while simultaneously limiting the search space with a peptide candidates database.
Consciousness has been proposed to be supported by electrophysiological patterns poised at criticality, a dynamical regime which exhibits ad… (voir plus)aptive computational properties, maximally complex patterns and divergent sensitivity to perturbation. Here, we investigated dynamical properties of the resting-state electroencephalogram of healthy subjects undergoing general anesthesia with propofol, xenon or ketamine. We then studied the relation of these dynamic properties with the perturbational complexity index (PCI), which has shown remarkably high sensitivity in detecting consciousness independent of behavior. All participants were unresponsive under anesthesia, while consciousness was retained only during ketamine anesthesia (in the form of vivid dreams)., enabling an experimental dissociation between unresponsiveness and unconsciousness. We estimated (i) avalanche criticality, (ii) chaoticity, and (iii) criticality-related measures, and found that states of unconsciousness were characterized by a distancing from both the edge of activity propagation and the edge of chaos. We were then able to predict individual subjects’ PCI (i.e., PCImax) with a mean absolute error below 7%. Our results establish a firm link between the PCI and criticality and provide further evidence for the role of criticality in the emergence of consciousness. 2 Significance Statement Complexity has long been of interest in consciousness science and had a fundamental impact on many of today’s theories of consciousness. The perturbational complexity index (PCI) uses the complexity of the brain’s response to cortical perturbations to quantify the presence of consciousness. We propose criticality as a unifying framework underlying maximal complexity and sensitivity to perturbation in the conscious brain. We demonstrate that criticality measures derived from resting-state electroencephalography can distinguish conscious from unconscious states, using propofol, xenon and ketamine anesthesia, and from these measures we were able to predict the PCI with a mean error below 7%. Our results support the hypothesis that critical brain dynamics are implicated in the emergence of consciousness and may provide new directions for the assessment of consciousness.
Physics-informed neural networks (PINNs) have been recognized as a viable alternative to conventional numerical solvers for Partial Differen… (voir plus)tial Equations (PDEs). The main appeal of PINNs is that since they directly enforce the PDE equation, one does not require access to costly ground truth solutions for training the model. However, a key challenge is their limited generalization across varied initial conditions. Addressing this, our study presents a novel Physics-Informed Transformer (PIT) model for learning the solution operator for PDEs. Using the attention mechanism, PIT learns to leverage the relationships between its initial condition and query points, resulting in a significant improvement in generalization. Moreover, in contrast to existing physics-informed networks, our model is invariant to the discretization of the input domain, providing great flexibility in problem specification and training. We validated our proposed method on the 1D Burgers’ and the 2D Heat equations, demonstrating notable improvement over standard PINN models for operator learning with negligible computational overhead.
Soil phosphorus (P) is a growth-limiting nutrient in tropical ecosystems, driving diverse P-acquisition strategies among plants. Particularl… (voir plus)y, mining for inorganic P through phosphomonoesterase (PME) activity is essential, given the substantial proportion of organic P in soils. Yet the relationship between PME activity and other P-acquisition root traits remains unclear. We measured root PME activity and commonly-measured root traits, including root diameter, specific root length (SRL), root tissue density (RTD), and nitrogen concentration ([N]) in 18 co-occurring trees across soils with varying P availability to better understand trees response to P supply. Root [N] and RTD were inversely related, and that axis was related to soil P supply. Indeed, both traits correlated positively and negatively to PME activity, which responded strongly to P supply. Conversely, root diameter was inversely related to SRL, but this axis was not related to P supply. Suggesting that limiting similarity influenced variation along the diameter-SRL axis, explaining high local trait diversity. Meanwhile, environmental filtering tended to impact trait values along the root [N]-RTD axis. Overall, P availability indicator traits like PME activity and root hairs only tended to be associated with these axes, highlighting limitations of these axes in describing convergent adaptations at local sites.