4 papers
Steerable Neural ODEs on Homogeneous Spaces
Emma Andersdotter, Daniel Persson, Fredrik Ohlsson
We introduce steerable neural ordinary differential equations on homogeneous spaces . These models constitute a novel geometric extension of manifold neural ordinary differe…
Framing structural identifiability in terms of parameter symmetries
Johannes G Borgqvist, Alexander P Browning, Fredrik Ohlsson +1
A key step in mechanistic modelling of dynamical systems is to conduct a structural identifiability analysis. This entails deducing which parameter combinations can be estimated fr…
Framing local structural identifiability and observability in terms of parameter-state symmetries
Johannes G. Borgqvist, Alexander P. Browning, Fredrik Ohlsson +1
We introduce a subclass of Lie symmetries, called parameter-state symmetries, to analyse the local structural identifiability and observability of mechanistic models consisting of…
PolyNODE: Variable-dimension Neural ODEs on M-polyfolds
Per à hag, Alexander Friedrich, Fredrik Ohlsson +1
Neural ordinary differential equations (NODEs) are geometric deep learning models based on dynamical systems and flows generated by vector fields on manifolds. Despite numerous suc…