Showing cs.LGShow all
2 papers · 1 filter
cs.LG2022
Standalone Neural ODEs with Sensitivity Analysis
Rym Jaroudi, Lukáš Malý, Gabriel Eilertsen +3
This paper presents the Standalone Neural ODE (sNODE), a continuous-depth neural ODE model capable of describing a full deep neural network. This uses a novel nonlinear conjugate g…
cs.LG2022
Learning via nonlinear conjugate gradients and depth-varying neural ODEs
George Baravdish, Gabriel Eilertsen, Rym Jaroudi +3
The inverse problem of supervised reconstruction of depth-variable (time-dependent) parameters in a neural ordinary differential equation (NODE) is considered, that means finding t…