Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore advanced techniques for accelerating atomic-scale simulations beyond traditional machine-learned interatomic potentials in this 19-minute seminar. Learn how direct prediction of interatomic forces can achieve two- to threefold speedup compared to computing forces as derivatives of energy models, while maintaining full fidelity in reproducing physical observables. Discover both symmetry-preserving and symmetry-free strategies for long-time-step molecular dynamics that directly predict future atomic positions and momenta. Understand how this emerging paradigm enables up to two orders of magnitude acceleration relative to standard machine-learned potentials, dramatically extending accessible time scales in atomistic modeling. Gain insights into cutting-edge computational methods that are revolutionizing the efficiency and scope of molecular dynamics simulations, presented by Filippo Bigi from EPFL as part of the Lennard-Jones Centre discussion group series.
