The Physics Is the Network: Fast, Training-Free Neural Emulation
This work investigates PolyNets that couple a continuous-time neural representation of polynomial dynamics with a simple recurrent network for discrete-time integration and achieves accuracy comparable to the numerical solvers, including at amplitudes outside the learned models'training conditions.
L. Todorović, Kaushal Gianchandani, S. Ravela
· 0 citations