BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Vrije Universiteit Amsterdam//NONSGML v1.0//EN NAME:PhD defence D.D. Baum METHOD:PUBLISH BEGIN:VEVENT DTSTART:20261116T114500 DTEND:20261116T131500 DTSTAMP:20261116T114500 UID:phd-defense-d-d-baum@8F96275E-9F55-4B3F-A143-836282E12573 CREATED:20261104T161626 LOCATION:Main building VU, 1105, Auditorium, De Boelelaan, 1081 HV, Amsterdam SUMMARY:PhD defence D.D. Baum X-ALT-DESC;FMTTYPE=text/html:

Machine Learning for the Acceleration of Quantum Chemical Simulations

AI and Machine Learning can accelerate quantum chemical simulations even on a budget

'For many applications, it is not necessary t o use very large and complex AI models. My research shows that relati vely simple models for specific quantum chemical problems can already yield good results.

My work is at the intersection of computational chemistry, quantum chemistry and artificial intelligen ce. Quantum chemical simulations can be used to investigate the prope rties of molecules without the need for a laboratory experiment for e very question. Such simulations can support research, but accurate ca lculations often require a lot of computing time and computer power.< /p>

Therefore, I focused on the question of how artificial intellig ence can be used to perform certain quantum chemical calculations mor e efficiently. The goal was to obtain results of similar quality with less computational work.

My research shows that the most compl ex AI method is not automatically the best choice. Which approach is most suitable depends on the problem, the available data and the desi red accuracy. For some quantum chemical applications, simple models m ay be sufficient. For other applications, a combination of artificial intelligence and existing scientific models works better.'

Mor e information on the thesi s

DESCRIPTION: Machine Learning for the Acceleration of Quantum Chemical Simulations

AI and Machine Learning can accelerate quantum chemi cal simulations even on a budget

'For many applications, it is not necessary to use very large and complex AI models. My resea rch shows that relatively simple models for specific quantum chemical problems can already yield good results.My work is at the i ntersection of computational chemistry, quantum chemistry and artific ial intelligence. Quantum chemical simulations can be used to investi gate the properties of molecules without the need for a laboratory ex periment for every question. Such simulations can support research, b ut accurate calculations often require a lot of computing time and co mputer power.Therefore, I focused on the question of how artificial i ntelligence can be used to perform certain quantum chemical calculati ons more efficiently. The goal was to obtain results of similar quali ty with less computational work.My research shows that the most compl ex AI method is not automatically the best choice. Which approach is most suitable depends on the problem, the available data and the desi red accuracy. For some quantum chemical applications, simple models m ay be sufficient. For other applications, a combination of artificial intelligence and existing scientific models works better.'More infor mation on the thesis END:VEVENT END:VCALENDAR