ATLAS-NN augments Hamiltonian Neural Networks with learnable temporal scaling and transfer learning from short to long intervals, claiming nearly an order of magnitude lower long-time prediction error on nonlinear oscillators and the Hénon-Heiles system.
Transfer learn- ing with physics-informed neural networks for efficient simulation of branched flows.arXiv preprint arXiv:2211.00214, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.comp-ph 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ATLAS-NN: Adaptive Transfer Learnable Symplectic-aware Neural Network for Long-Time Hamiltonian Dynamics
ATLAS-NN augments Hamiltonian Neural Networks with learnable temporal scaling and transfer learning from short to long intervals, claiming nearly an order of magnitude lower long-time prediction error on nonlinear oscillators and the Hénon-Heiles system.