State Derivative Normalization for Continuous-Time Deep Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Weigand, Jonas, Beintema, Gerben I., Ulmen, Jonas, Görges, Daniel, Tóth, Roland, Schoukens, Maarten, Ruskowski, Martin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909201388797952
author Weigand, Jonas
Beintema, Gerben I.
Ulmen, Jonas
Görges, Daniel
Tóth, Roland
Schoukens, Maarten
Ruskowski, Martin
author_facet Weigand, Jonas
Beintema, Gerben I.
Ulmen, Jonas
Görges, Daniel
Tóth, Roland
Schoukens, Maarten
Ruskowski, Martin
contents The importance of proper data normalization for deep neural networks is well known. 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. This results in a reduced model quality. In this contribution, we show that these three normalization tasks are inherently coupled. Due to the existence of this coupling, we propose a solution to all three normalization challenges by introducing a normalization constant at the state derivative level. We show that the appropriate choice of the normalization constant is related to the dynamics of the to-be-identified system and we derive multiple methods of obtaining an effective normalization constant. We compare and discuss all the normalization strategies on a benchmark problem based on experimental data from a cascaded tanks system and compare our results with other methods of the identification literature.
format Preprint
id arxiv_https___arxiv_org_abs_2401_02902
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle State Derivative Normalization for Continuous-Time Deep Neural Networks
Weigand, Jonas
Beintema, Gerben I.
Ulmen, Jonas
Görges, Daniel
Tóth, Roland
Schoukens, Maarten
Ruskowski, Martin
Systems and Control
Machine Learning
The importance of proper data normalization for deep neural networks is well known. 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. This results in a reduced model quality. In this contribution, we show that these three normalization tasks are inherently coupled. Due to the existence of this coupling, we propose a solution to all three normalization challenges by introducing a normalization constant at the state derivative level. We show that the appropriate choice of the normalization constant is related to the dynamics of the to-be-identified system and we derive multiple methods of obtaining an effective normalization constant. We compare and discuss all the normalization strategies on a benchmark problem based on experimental data from a cascaded tanks system and compare our results with other methods of the identification literature.
title State Derivative Normalization for Continuous-Time Deep Neural Networks
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2401.02902