Universal differential equations for scientific machine learning

Christopher Rackauckas, Yingbo Ma, Julius Martensen, Collin Warner, Kirill Zubov, Rohit Supekar, Dominic Skinner, Ali Ramadhan, Alan Edelman
Paper From BibTeX import
arXiv preprint arXiv:2001.04385, 2020

Notes

Once a trajectory has been recovered, riva2026random proposes fitting Universal Differential Equations from Rackauckas et al. so that the polynomial RDPG architecture supplies known mechanistic structure while a neural component absorbs residual dynamics, with adjoint sensitivities providing gradients through the ODE solver.

References

No references yet.