BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Advanced Machine Learning Methods to Accelerate Materials Discover
 y
DTSTART:20230321T153000
DTEND:20230321T163000
DTSTAMP:20260407T055533Z
UID:b305ef9498a2eb9b147e35fbf64075b3ab5851b74284249244bbfddd
CATEGORIES:Conferences - Seminars
DESCRIPTION:Santiago Miret is an AI Researcher at Intel Labs where he focu
 ses on applying AI for scientific problems with an emphasis on materials d
 iscovery and materials understanding. Through this effort\, Santiago manag
 es a wide range of academic collaborations focused on applying AI for scie
 ntific application. Among these collaboration\, there have been notable en
 gagements with the Matter Lab led by Alán Aspuru-Guzik at the University 
 of Toronto and various AI laboratories at MILA in Montreal that have led t
 o cross-institutional publications at various machine learning venues. San
 tiago was a primary organizer of the 1st AI for Accelerated Materials Dis
 covery (AI4Mat) workshop at NeurIPS 2022\, which brought together domain e
 xperts from various fields of materials science and AI to exchange researc
 h work and ideas in an interdisciplinary forum. Prior to working at Intel 
 Labs\, Santiago obtained his PhD in Materials Science and Engineering from
  the University of California\, Berkeley.\nThe ability to apply advanced m
 achine learning (ML) to process large amounts of heterogenous data can gre
 atly aid in the understanding\, discovery and design of new materials for 
 advanced application like clean energy\, sustainable semiconductor manufac
 turing and drug discovery. The heterogenous nature of data encompasses mat
 erials structural data\, material property data and qualitative descriptio
 ns across various types of materials\, including solid-state (e.g.\, semic
 onductors\, batteries) and molecules. This multitude of multi-modal data t
 ypes necessitates the application of a diverse of advanced ML techniques a
 cross different fields. Additionally\, computational materials design is o
 nly the first step in the materials creation process\, which involves a la
 rge range of experimental synthesis and analysis techniques creating addit
 ional technical challenges and uncertainties. Overall\, applying ML to mat
 erials discovery provides a notable platform for interdisciplinary ML rese
 arch with real-world impactful applications. \nIn this talk\, I will pres
 ent an overview of Intel Labs’ research efforts focused on applying ML t
 o materials discovery through a closed-loop discovery paradigm spanning au
 tomated materials design\, automated material synthesis and automated mate
 rials characterization. Based on the closed-loop discovery framework\, I w
 ill illustrate some example research efforts detailing materials property 
 modeling using geometric deep learning\, materials discovery using new gen
 erative algorithms and materials understanding through natural language pr
 ocessing.\n 
LOCATION:CH G1 495 https://plan.epfl.ch/?room==CH%20G1%20495
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR