Using Neural Networks to Accelerate Molecular Dynamics
Event Start:
2025-04-17T10:00:00
Event End:
2025-04-17T11:00:00
Event Information:
When running molecular dynamics simulations, typically timesteps must be on the order of 2fs to preserve numerical stability. This sharply limits our ability to generate trajectories for processes such as protein folding that can take on the order of milliseconds. In this talk, we'll discuss training a neural net to predict the configuration of the protein many timesteps in the future (conditional on its current configuration) in order to save computation.
Event Location:
BRIM 311
Speaker:
Philip Bement (UBC)
Related Upcoming Events:
Add to Calendar
Event Start:
2025-04-17T10:00:00
Event End:
2025-04-17T11:00:00
Using Neural Networks to Accelerate Molecular Dynamics
Event Information:
When running molecular dynamics simulations, typically timesteps must be on the order of 2fs to preserve numerical stability. This sharply limits our ability to generate trajectories for processes such as protein folding that can take on the order of milliseconds. In this talk, we'll discuss training a neural net to predict the configuration of the protein many timesteps in the future (conditional on its current configuration) in order to save computation.
Event Location:
BRIM 311