An AI Quantum Breakthrough: ANAKIN-ME
Join researchers from the University of Florida and the University of North Carolina to learn how GPU-accelerated deep learning techniques are advancing molecular energetics studies. The development of a new methodology, known as Accurate NeurAI networK engINe for Molecular Energies (ANAKIN-ME, or ANI for short) is able to describe the forces in molecules as accurately as density functional theory (DFT), but hundreds of thousands of times faster. This combination of speed and accuracy could allow researchers to tackle problems that were previously impossible, leading to breakthroughs in the arenas of drug discovery and materials science.
By watching this webinar replay, you' will learn about:
- Using GPU deep learning to advance molecular energetics studies.
- Adapting the ANAKIN-ME method, which provides the tools to build a new class of neural network potentials (NNP) that is fully transferable and has chemical accuracy within an entire class of molecules.
- Optimizing GPU computing resources to speed up computing approaches.
ON DEMAND WEBINAR REGISTRATION
Presented By
Adrian Roitberg
Full Professor, University of Florida
Adrian Roitberg is a Full professor in the Chemistry department at the University of Florida. His research focuses on the development and application of methods to study materials and biomolecules, using advanced computational techniques. He is one of the core developers of the suite of programs AMBER and has recently been involved in developing machine learning techniques for energy and force evaluation in large systems. Adrian has received numerous awards, including being named the Ulam Scholar from Los Alamos National Laboratories in the Fall of 2017.
Olexandr Isayev
Research Assistant Professor, University of North Carolina
Olexandr Isayev is a research assistant professor at UNC Eshelman School of Pharmacy, University of North Carolina at Chapel Hill. His research interests focus on making sense of chemical data with molecular modeling and machine learning. Before joining UNC in 2013, Olexandr was a postdoctoral research fellow at Case Western Reserve University and a scientist at a government research lab. In 2008, he received his Ph.D. in computational chemistry. He received the "Emerging Technology Award" from the American Chemical Society and the GPU computing award from NVIDIA in 2014.
Justin Smith
Ph.D Candidate in Computational Chemistry, University of Florida
Justin S. Smith is currently a Ph.D. candidate in computational chemistry at the University of Florida (UF) funded by the UF Foundation Graduate Fellowship. He conducts research in applying machine learning techniques for chemistry problems. He is supervised by Dr. Adrian Roitberg (UF) and collaborator Dr. Olexandr Isayev (UNC Chapel Hill). Their research has led to a breakthrough method (ANAKIN-ME), based on deep learning, and an in-house NVIDIA GPU accelerated software (NeuroChem) for developing molecular inter-atomic potentials with quantum mechanical accuracy at significantly lower computational cost. Currently, Justin is continuing his dissertation research to improve the ANAKIN-ME method and development of the NeuroChem software suite. Additionally he collaborates with Dr. Kipton Barros and Dr. Nick Lubbers at Los Alamos National Laboratory to advance machine learning architectures for molecular potentials and the use of active learning in biochemical space.
 "Add Presenter 4's Title (ex: CMO, ABC Company)")
Add Presenter 4's Name (John Smith)
Add Presenter 4's Title (ex: CMO, ABC Company)
Add Presenter 4's Bio (2-3 Sentences)
HOSTED BY
