BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20220812T074357Z
LOCATION:Nairobi Room
DTSTART;TZID=Europe/Stockholm:20220628T110000
DTEND;TZID=Europe/Stockholm:20220628T130000
UID:submissions.pasc-conference.org_PASC22_sess143@linklings.com
SUMMARY:MS3F - Computation Powered by Machine Learning in Material Science
DESCRIPTION:Minisymposium\n\nMachine learning (ML) methods have been widel
 y adopted in material science in recent years. While these approaches have
  been used for years in engineering and science in general, the widespread
  application in computational materials science is relatively new [1]. For
  modeling computationally heavy quantum-chemistry calculations, two major 
 approaches can be discriminated. In the first, one tries to replace certai
 n parts of already established frameworks with ML models, e.g., the parame
 terization of molecular forcefields [2] or the functionals in density-func
 tional theory [3]. The second approach tries to create a surrogate model f
 or prediction of materials properties given only the fingerprints as an in
 put. Recent efforts also focus on the prospects of creating "new" material
 s from generative models or directly feeding the structural graph to a neu
 ral-network approximator [4]. This minisymposium aims to give an overview 
 on some of the most relevant developments concerning ML methods in materia
 l science.\nReferences:\n[1] Rogers, D.; Hahn, M.; J. Chem. Inf. Model. 20
 10, 50, 742−754.\n[2] Behler, J.; Parrinello, M.; Phys. Rev. Lett. 2007, 9
 8, No. 146401.\n[3] Rupp, M.; et al..; Phys. Rev. Lett. 2012, 108, No. 058
 301.\n[4] Xie, T.; Grossman, J. C.; Phys. Rev. Lett. 2018, 120, No. 145301
 .\n\nRepresentation and Optimization of Materials with Deep Learning\n\nGo
 mez-Bombarelli\n\nGiven adequate training data, machine learning models tr
 ained over experimental or theoretical outcomes enable virtual screening a
 nd inverse design of molecules and materials. However, activity data is ty
 pically expensive and slow to acquire. Thus, finding representations of at
 omistic structure that...\n\n---------------------\nMachine Learning to In
 vestigate Material Properties: How to Improve Machine Performance\n\nGagli
 ardi\n\nMachine learning (ML) is emerging as a new tool for many different
  fields which now span, among the others, chemistry, physics and material 
 science [1]. The idea is to use ML algorithms to identify, starting from b
 ig data analysis, subtle correlations between simple elemental quantities 
 and complex ...\n\n---------------------\nEfficient Top-Down Parameterizat
 ion of Machine Learning-Based Models\n\nZavadlav\n\nMolecular modeling has
  become a cornerstone of many disciplines, including material science. How
 ever, the quality of predictions critically depends on the employed potent
 ial energy model. A class of models with tremendous success in recent year
 s are neural network (NN) potentials due to their flexib...\n\n-----------
 ----------\nDesigning Molecular Models by Machine Learning and Experimenta
 l Data\n\nClementi\n\nThe last years have seen an immense increase in high
 -throughput and high-resolution technologies for experimental observation 
 as well as high-performance techniques to simulate molecular systems at a 
 microscopic level, resulting in vast and ever-increasing amounts of high-d
 imensional data. However, ...\n\n\nDomain: Chemistry and Materials, Physic
 s
END:VEVENT
END:VCALENDAR