Saved in:
Bibliographic Details
Main Authors: Zimmering, Bernd, Coelho, Cecília, Gupta, Vaibhav, Maleshkova, Maria, Niggemann, Oliver
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.13158
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908567652532224
author Zimmering, Bernd
Coelho, Cecília
Gupta, Vaibhav
Maleshkova, Maria
Niggemann, Oliver
author_facet Zimmering, Bernd
Coelho, Cecília
Gupta, Vaibhav
Maleshkova, Maria
Niggemann, Oliver
contents Modelling forced dynamical systems - where an external input drives the system state - is critical across diverse domains such as engineering, finance, and the natural sciences. In this work, we propose Laplace-Net, a decoupled, solver-free neural framework for learning forced and delay-aware systems. It leverages a Laplace transform-based approach to decompose internal dynamics, external inputs, and initial values into established theoretical concepts, enhancing interpretability. Laplace-Net promotes transferability since the system can be rapidly re-trained or fine-tuned for new forcing signals, providing flexibility in applications ranging from controller adaptation to long-horizon forecasting. Experimental results on eight benchmark datasets - including linear, non-linear, and delayed systems - demonstrate the method's improved accuracy and robustness compared to state-of-the-art approaches, particularly in handling complex and previously unseen inputs.
format Preprint
id arxiv_https___arxiv_org_abs_2503_13158
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Breaking Free: Decoupling Forced Systems with Laplace Neural Networks
Zimmering, Bernd
Coelho, Cecília
Gupta, Vaibhav
Maleshkova, Maria
Niggemann, Oliver
Machine Learning
Systems and Control
Modelling forced dynamical systems - where an external input drives the system state - is critical across diverse domains such as engineering, finance, and the natural sciences. In this work, we propose Laplace-Net, a decoupled, solver-free neural framework for learning forced and delay-aware systems. It leverages a Laplace transform-based approach to decompose internal dynamics, external inputs, and initial values into established theoretical concepts, enhancing interpretability. Laplace-Net promotes transferability since the system can be rapidly re-trained or fine-tuned for new forcing signals, providing flexibility in applications ranging from controller adaptation to long-horizon forecasting. Experimental results on eight benchmark datasets - including linear, non-linear, and delayed systems - demonstrate the method's improved accuracy and robustness compared to state-of-the-art approaches, particularly in handling complex and previously unseen inputs.
title Breaking Free: Decoupling Forced Systems with Laplace Neural Networks
topic Machine Learning
Systems and Control
url https://arxiv.org/abs/2503.13158