Neural Ordinary Differential Equations

Re:Neural Ordinary Differential Equations by chombier on Saturday December 15, 2018 @07:40AM (#18688153)

> We just took this idea to its logical extreme: What if we _define_ a deep net as a continuously evolving system?

What about symmetries of the underlying continuous system?

I'm under the impression that having deep nets as ODEs should make it possible to enforce a certain geometry on the information flow (like incompressible fluid, Hamiltonian, etc..) which would correspond to some invariant of the whole network.

Does this idea make sense?

[ Parent | on HN ]

Re:Neural Ordinary Differential Equations by thanatropism on Saturday December 15, 2018 @10:15AM (#18688638)

My dissertation was about energy- and symplecticity preserving methods for Hamiltonian ODEs. Try to find the book by Blanes or the one by Leimkuhler.

[ Parent | on HN ]