PeN-ODE training is reformulated as a direct collocation NLP, giving fast, stable training of small neural surrogates on two benchmark systems.
Closing the sim-to-real gap with physics-enhanced neural odes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Efficient Training of Physics-enhanced Neural ODEs via Direct Collocation and Nonlinear Programming
PeN-ODE training is reformulated as a direct collocation NLP, giving fast, stable training of small neural surrogates on two benchmark systems.