Previous Events > Plenieres22

The first edition of the GDR IAMAT toke place from

Monday, May 30, 10:45 am to Wednesday, June 01, 2022 noon

Location: Sorbonne University - large amphitheater and annex rooms

4 Place Jussieu

75005, Paris, France

Instructions

Flash lab presentation

Each laboratory has the possibility to present itself in a "flash" format, with a maximum of 5 minutes. The 2 or 3 slides presentation should include clear and succinct information: name of the lab, number of staff, and research themes developed.

The pdf files should be sent before May 20 to the following address: gdr-iamat-presentations@sciencesconf.org

We invite laboratories wishing to further develop their activities to submit a "Poster" contribution.

Oral presentations

The program of presentations will be provided the week of May 16.

Short slots of 12-15min will be offered to accepted contributions.

Program

Monday May 30th Plenaries
Gérald Biau (director SCAI): general introduction
Cosmin Marinica (CEA): (Physics informed) Machine Learning for atomistic materials Science
Vincent Favre-Nicolin (ESRF): AI for automated data collection and analysis-an ESRF perspective
Nicola Marzari (EPFL): Digital infrastructure empwering materials discovery

Tuesday May 31 Plenaries
Gian-Marco Rignanese (UC Louvain): OPTIMADE: A Common REST API for Materials Databases Interoperability
Jean-Luc Parouty (SIMAP): Deep Learning, history and principles, from regression to GANs
Maxime Sangnier (Sorbonne University): A review of classification and clustering algorithms
Sandrine Lyonnard (SyMMES):  Accelerating the characterization of batteries : multimodal and multitechniques integrated workflows
Gérard Ramstein (Nantes university): Solving optimization problems with machine learning - Application to materials science

Conférence Invitée

Cosmin Marinica :
Vincent Favre-Nicolin : AI for automated data collection & analysis - an ESRF perspective
Nicola Marzari : Digital Infrastructures empowering materials discovery
Maxime Sangnier : A concise overview of classification and clustering methods
Jean-Luc Parouty : Deep Learning, histoire et principes... de la régression aux GANs
Gian-Marco Rignanese : OPTIMADE: A Common REST API for Materials Databases Interoperability
Sandrine Lyonnard :
Gérard Ramstein : Solving optimization problems with machine learning Application to materials science
 

Présentations Orales

Maciej Jakub Karcz  : Machine-learning aided calculation of atomic-scale properties in chemically disordered (U, Pu)O2 fuels
Lune Maillard : Nested_fit: developments and tests
Devergne  :
Aloïs Castellano : Ab Initio Canonical Sampling based on Variational Inference
Lam :
Almeida de Mendonca :
Basile Herzog : Gold standard finite temperature simulations of materials via machine learning
Meier :
Swinburne :
Dubois :
Daniel Forster : Analysis of high resolution transmission electron microscopy images by deep learning: Example of AgCo nanoalloys
Monchot :
Redhouane Boudjehem : Deep learning for sparse spectral ptychographicx-ray computed tomography (Spect-PXCT)
Purushottam raj purohit  :
Cao Junhao :
Allera :
Hicham Khodja : Artificial Intelligence for Ion Beam analysis spectroscopies
Lisa Rateau : The recourse to artificial intelligence to design Co-free wear-resistant alloys
Garel :
Aurore Lomet : Symbolic artificial intelligence for new material design
Thibault Charpentier : Modelling NMR Spectroscopy of Oxide Glasses with Machine Learning
Gaëtan Percebois : Determination of the disorder potential from quantum transport data using machine learning methods
Thibault Sohier : Finding and engineering high-conductivity 2D semiconductors from first principles
Marie-Pierre Gaigeot : Graph Theory for Molecular Dynamics Simulations
Demange :