Salvato in:
Dettagli Bibliografici
Autori principali: Yang, Yejiang, Mo, Zihao, Xiang, Weiming
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2411.10240
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909391487238144
author Yang, Yejiang
Mo, Zihao
Xiang, Weiming
author_facet Yang, Yejiang
Mo, Zihao
Xiang, Weiming
contents This paper proposes a neural network hybrid modeling framework for dynamics learning to promote an interpretable, computationally efficient way of dynamics learning and system identification. First, a low-level model will be trained to learn the system dynamics, which utilizes multiple simple neural networks to approximate the local dynamics generated from data-driven partitions. Then, based on the low-level model, a high-level model will be trained to abstract the low-level neural hybrid system model into a transition system that allows Computational Tree Logic Verification to promote the model's ability with human interaction and verification efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10240
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Neural Hybrid System Learning and Transition System Abstraction for Dynamical Systems
Yang, Yejiang
Mo, Zihao
Xiang, Weiming
Systems and Control
Machine Learning
This paper proposes a neural network hybrid modeling framework for dynamics learning to promote an interpretable, computationally efficient way of dynamics learning and system identification. First, a low-level model will be trained to learn the system dynamics, which utilizes multiple simple neural networks to approximate the local dynamics generated from data-driven partitions. Then, based on the low-level model, a high-level model will be trained to abstract the low-level neural hybrid system model into a transition system that allows Computational Tree Logic Verification to promote the model's ability with human interaction and verification efficiency.
title Efficient Neural Hybrid System Learning and Transition System Abstraction for Dynamical Systems
topic Systems and Control
Machine Learning
url https://arxiv.org/abs/2411.10240