DOE OSTI · code-67085
pnnl/neural_ODE_ICLR2020
Abstract
We show how to model discrete ordinary differential equations (ODE) with algebraic nonlinearities as deep neural networks with varying degrees of prior knowledge. We derive the stability guarantees of the network layers based on the implicit constraints imposed on the weight's eigenvalues. Moreover, we show how to use barrier methods to generically handle additional inequality constraints. We demonstrate the prediction accuracy of learned neural ODEs evaluated on open-loop simulations compared to ground truth dynamics with bi-linear terms.
Keep this discovery
Explore connections, maps & timelines
Tuor, Aaron, Drgona, Jan. 2021-11-16. pnnl/neural_ODE_ICLR2020. https://doi.org/10.11578/dc.20240614.197. https://engineeringpapers.com/record/osti%3Acode-67085/pnnl-neural-ode-iclr2020
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Engineering Papers by Indiciae: BibTeX · RIS.