Please use this identifier to cite or link to this item:

TitlePrior knowledge meets neural odes: a two stage training method for improved explainability
Author(s)Coelho, C.
Costa, M. Fernanda P.
Ferrás, Luís Jorge Lima
Issue date2023
Abstract(s)Neural Ordinary Differential Equations (ODEs) have been used extensively to model physical systems because they represent a continuous-time function that can make predictions over the entire time domain. However, most of the time, the parameters of these physical systems are subject to strict laws/constraints. But there is no guarantee that the Neural ODE model satisfies these constraints. Therefore, we propose a two-stage training for Neural ODE. The first stage aims at find ing feasible parameters by minimizing a loss function defined by the constraints violation. The second stage aims at improving the feasible solution by minimiz ing the distance between the predicted and ground-truth values. By training the Neural ODE in two stages, we ensure that the governing laws of the system are satisfied and the model fits the data.
TypeConference paper
AccessOpen access
Appears in Collections:CMAT - Artigos em atas de conferências e capítulos de livros com arbitragem / Papers in proceedings of conferences and book chapters with peer review

Files in This Item:
File Description SizeFormat 
paper_revised.pdf498,03 kBAdobe PDFView/Open

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu ORCID