Beyond the Black Box: How we can use machine learning to learn new physics and simulate large molecules
Presented by Joshua Rackers (Sandia)
The ability to accurately simulate large molecules like proteins or DNA is a defining challenge for science. Accurate simulations would enable scientists to design new medicines and discover new materials. The fundamental challenge in this endeavor is the many-body nature of electron correlation. This causes current quantum chemistry algorithms to scale very poorly with molecular size. We have developed a set of machine learning models that enable quantum-accurate simulations of large systems by learning the nature of electron correlation in molecular systems. This has immediate impact on classical simulations. It also has the potential to impact the question of how we will use a quantum computer for large-scale molecular simulations in the future.
3:30 pm, Thursday, September 22, 2022
Individuals with disabilities who need an auxiliary aid or service to attend or participate in P&A events should contact the Physics Department (phone: 505-277-2616, email: email@example.com) well in advance to ensure your needs are accomodated. Event handouts can be provided in alternative accessible formats upon request. Please contact the Physics front office if you need written information in an alternative format.
A schedule of talks within the Department of Physics and Astronomy is available on the P&A web site at http://physics.unm.edu/pandaweb/events/index.php