2 citations · 2 across the 4 of their papers we have counts for
3 papers · 1 filter
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…
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…
Equivariant Manifold Neural ODEs and Differential Invariants
Emma Andersdotter, Daniel Persson, Fredrik Ohlsson
In this paper, we develop a manifestly geometric framework for equivariant manifold neural ordinary differential equations (NODEs) and use it to analyse their modelling capabilitie…