BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//THOMAS YOUNG CENTRE - ECPv6.15.17//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:THOMAS YOUNG CENTRE
X-ORIGINAL-URL:https://thomasyoungcentre.org
X-WR-CALDESC:Events for THOMAS YOUNG CENTRE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:20240331T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:20241027T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:20250330T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:20251026T010000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:20260329T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:20261025T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/London:20250723T120000
DTEND;TZID=Europe/London:20250723T133000
DTSTAMP:20260411T085847
CREATED:20250320T115839Z
LAST-MODIFIED:20250721T144532Z
UID:6482-1753272000-1753277400@thomasyoungcentre.org
SUMMARY:MMM Hub Software Spotlight: ML force fields
DESCRIPTION:Venue: ONLINE \n\n\n\n\n\n\n\n\n\n\nMMM Hub Software Spotlight: ML force fields Share on X\n\n\n\n\nVenkat Kapil from UCL and Ilyes Batatiya from the University of Cambridge will give an overview of ML force fields – their generation\, use and software which can enable this (inc. its use on HPC/Young). \n\n\n\nFuture talks aim to include commonly codes used on Young\, such as Quantum ESPRESSO and Casino and include some emerging technologies such as machine learning with Keras\, Tensorflow and Torch \n\n\n\nJoin Zoom Meeting: \n\n\n\nMeeting ID: 991 6854 2304Passcode: TYCSWS
URL:https://thomasyoungcentre.org/event/mmm-hub-software-spotlight-ml-force-fields/
CATEGORIES:Main event
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=Europe/London:20250724T150000
DTEND;TZID=Europe/London:20250724T163000
DTSTAMP:20260411T085847
CREATED:20250626T150750Z
LAST-MODIFIED:20250723T145348Z
UID:6769-1753369200-1753374600@thomasyoungcentre.org
SUMMARY:TYC Junior Research Fellowship visitor talk: Extending Machine Learning Models Beyond Energy and Forces
DESCRIPTION:TYC Junior Research Fellowship talk: Extending Machine Learning Models Beyond Energy and Forces Share on X\n\n\n\n\nNils Gönnheimer\, University of Bayreuth \n\n\n\n\n\n\n\nAbstract: The development of machine‑learning interatomic potentials (MLIPs) has revolutionized computational chemistry by combining the accuracy of first‑principles methods with the computational speed of empirical force fields. Many important properties\, such as heat capacities\, vibrational spectra\, dielectric responses and optical activities\, require either higher‑order derivatives (e.g. Hessians) or direct learning of non‑scalar quantities beyond energies and forces. In the first part of the talk\, Hessian matrix evaluation is addressed: most MLIPs lack analytical second derivatives and must resort to costly\, error‑prone finite differences\, whereas implementing automatic‑differentiation (AD) Hessians within the equivariant MACE framework delivers both efficiency and numerical stability. In the second part\, MACE‑μ‑α\, a polarizability‑and‑dipole model built on the same equivariant architecture\, is trained directly on molecular dipole moments and polarizability tensors\, enabling accurate prediction of both infrared absorption and Raman scattering intensities. Together\, these advances form a unified\, beyond‑scalar MLIP platform for comprehensive spectroscopic characterization and rapid multi‑property prediction of complex materials.
URL:https://thomasyoungcentre.org/event/tyc-junior-research-fellowship-visitor-talk-extending-machine-learning-models-beyond-energy-and-forces/
LOCATION:LG17\, Bentham House\, UCL\, 4-8 ENDSLEIGH GARDENS\, LONDON\, WC1H 0EG
CATEGORIES:Main event
END:VEVENT
END:VCALENDAR