A Transition System Abstraction Framework for Neural Network Dynamical System Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914684877144064 |
|---|---|
| author | Yang, Yejiang Mo, Zihao Tran, Hoang-Dung Xiang, Weiming |
| author_facet | Yang, Yejiang Mo, Zihao Tran, Hoang-Dung Xiang, Weiming |
| contents | This paper proposes a transition system abstraction framework for neural network dynamical system models to enhance the model interpretability, with applications to complex dynamical systems such as human behavior learning and verification. To begin with, the localized working zone will be segmented into multiple localized partitions under the data-driven Maximum Entropy (ME) partitioning method. Then, the transition matrix will be obtained based on the set-valued reachability analysis of neural networks. Finally, applications to human handwriting dynamics learning and verification are given to validate our proposed abstraction framework, which demonstrates the advantages of enhancing the interpretability of the black-box model, i.e., our proposed framework is able to abstract a data-driven neural network model into a transition system, making the neural network model interpretable through verifying specifications described in Computational Tree Logic (CTL) languages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11739 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Transition System Abstraction Framework for Neural Network Dynamical System Models Yang, Yejiang Mo, Zihao Tran, Hoang-Dung Xiang, Weiming Systems and Control Machine Learning This paper proposes a transition system abstraction framework for neural network dynamical system models to enhance the model interpretability, with applications to complex dynamical systems such as human behavior learning and verification. To begin with, the localized working zone will be segmented into multiple localized partitions under the data-driven Maximum Entropy (ME) partitioning method. Then, the transition matrix will be obtained based on the set-valued reachability analysis of neural networks. Finally, applications to human handwriting dynamics learning and verification are given to validate our proposed abstraction framework, which demonstrates the advantages of enhancing the interpretability of the black-box model, i.e., our proposed framework is able to abstract a data-driven neural network model into a transition system, making the neural network model interpretable through verifying specifications described in Computational Tree Logic (CTL) languages. |
| title | A Transition System Abstraction Framework for Neural Network Dynamical System Models |
| topic | Systems and Control Machine Learning |
| url | https://arxiv.org/abs/2402.11739 |