Search Results for author: Jonas Ulmen

Found 1 papers, 0 papers with code

State Derivative Normalization for Continuous-Time Deep Neural Networks

no code implementations5 Jan 2024 Jonas Weigand, Gerben I. Beintema, Jonas Ulmen, Daniel Görges, Roland Tóth, Maarten Schoukens, Martin Ruskowski

However, in continuous-time state-space model estimation, it has been observed that improper normalization of either the hidden state or hidden state derivative of the model estimate, or even of the time interval can lead to numerical and optimization challenges with deep learning based methods.

Cannot find the paper you are looking for? You can Submit a new open access paper.