BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Analysis and design of materials with machine learning: from proba
 bilistic methods to quantum computing opportunities - Dr Miguel Bessa\,  M
 aterials Science and Engineering\, Delft University of Technology 
DTSTART:20210604T130000Z
DTEND:20210604T140000Z
UID:TALK155038@talks.cam.ac.uk
CONTACT:Hilde Hambro
DESCRIPTION:Analysis and design of materials can be significantly empowere
 d by machine learning. This talk discusses how three novel machine learnin
 g methods can be used to design new materials and analyze history-dependen
 t physics. In the first example\, Bayesian machine learning is shown to gu
 ide the design of a new lightweight\, recoverable and super-compressible m
 etamaterial achieving more than 90% compressive strain without damage. The
  second example focuses on how deep learning can predict path-dependent ma
 terial plasticity. And the final example presents a new quantum machine le
 arning algorithm that can break the curse of dimensionality that plagues G
 aussian processes.
LOCATION:Zoom Meeting ID: 819 1682 8857
END:VEVENT
END:VCALENDAR