Skip to main content
. Author manuscript; available in PMC: 2021 Jul 29.
Published in final edited form as: Proc Mach Learn Res. 2020 Jul;119:9526–9536.

Figure 1.

Figure 1.

TrajectoryNet learns trajectories of particles from distributions sampled over time. We use a Neural ODE to learn the derivative of the dynamics function. To find the output at time t1 for a given input at time t0 we integrate T times letting the ODE solver choose the integration timepoints.