BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Département de mathématiques et applications - ECPv6.2.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://www.math.ens.psl.eu
X-WR-CALDESC:évènements pour Département de mathématiques et applications
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20251026T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20250123T120000
DTEND;TZID=Europe/Paris:20250123T130000
DTSTAMP:20260403T204437
CREATED:20250117T125403Z
LAST-MODIFIED:20250117T125404Z
UID:18877-1737633600-1737637200@www.math.ens.psl.eu
SUMMARY:ENS-Data Science colloquium - Michele Ceriotti (EPFL)
DESCRIPTION:Michele Ceriotti (EPFL) \n\n\n\nTitle: Between physics and scaling: inductive biases in atomistic machine learningAbstract: Machine-learning techniques are often applied to perform « end-to-end » predictions\, making black-box estimatesof a property of interest using only a coarse description of the corresponding inputs.In contrast\, atomic-scale modeling of matter is most useful when it allows one to gather a mechanistic insightinto the microscopic processes that underlie the behavior of molecules and materials.In this talk I will provide an overview of the progress that has been made combining these two philosophies\,using data-driven techniques to build surrogate models of the quantum mechanical behavior of atoms\, enabling« bottom-up » simulations that reveal the behavior of matter in realistic conditions with uncompromising accuracy.I will critically discuss two ways by which physical-chemical ideas can be integrated into a machine-learningframework. One way involves using physical priors\, such as smoothness or symmetry of the structure-propertyrelations\, to inform the mathematical structure of a generic ML approximation – an approach that has becomeubiquitous in the field\, but that is increasingly challenged by the emergence of unconstrained models that candirectly learn physical constraints from large amounts of data. The other entails a deeper level of integration\,in which explicit physics-based models and approximations are built into the model architecture.I will discuss several examples of the application of these ideas\, from the calculation of electronic excitationsto the design of solid-state electrolyte materials for batteries and high-entropy alloys for catalysis\, emphasizingboth the accuracy and the interpretability that can be achieved with a hybrid modeling approach\, and providing anoverview of the exciting research directions that are made available by these new modeling tools. \n\n\n\n  \n\n\n\nThese seminars are being made possible through the support of the CFM-ENS Chair « Modèles et Sciences des Données ». \n\n\n\nThe organizers: Giulio Biroli\, Alex Cayco Gajic\, Bruno Loureiro\, Stéphane Mallat\, Gabriel Peyré.
URL:https://www.math.ens.psl.eu/evenement/ens-data-science-colloquium-michele-ceriotti-epfl/
LOCATION:ENS Salle Dussane
CATEGORIES:Séminaire Data de l’ENS
END:VEVENT
END:VCALENDAR