Abstract
This article proposes a neural network hybrid modeling framework for dynamics learning to promote an interpretable, computationally efficient method of dynamics learning and system identification. First, a low-level model is 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 is trained to abstract the low-level neural hybrid system model into a transition system that allows computational tree logic (CTL) verification to promote model’s ability to handle human interaction and verification efficiency.
References
1.
Wang
, Y.
, Wang
, W.
, Chen
, Q.
, Huang
, K.
, Nguyen
, A.
, De
, S.
, and Hussain
, A.
, 2023
, “Fusing External Knowledge Resources for Natural Language Understanding Techniques: A Survey
,” Inf. Fusion
, 92
, pp. 190
–204
. 2.
Stefenon
, S. F.
, Corso
, M. P.
, Nied
, A.
, Perez
, F. L.
, Yow
, K. -C.
, Gonzalez
, G. V.
, and Leithardt
, V. R. Q.
, 2022
, “Classification of Insulators Using Neural Network Based on Computer Vision
,” IET Generation, Transm. Distrib.
, 16
(6
), pp. 1096
–1107
. 3.
Zhang
, X.
, Zheng
, X.
, and Mao
, W.
, 2021
, “Adversarial Perturbation Defense on Deep Neural Networks
,” ACM Comput. Surv. (CSUR)
, 54
(8
), pp. 1
–36
. 4.
Yang
, Y.
, Wang
, T.
, Woolard
, J. P.
, and Xiang
, W.
, 2022
, “Guaranteed Approximation Error Estimation of Neural Networks and Model Modification
,” Neural Netw.
, 151
, pp. 61
–69
. 5.
Brix
, C.
, Müller
, M. N.
, Bak
, S.
, Johnson
, T. T.
, and Liu
, C.
, 2023
, “First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)
,” Int. J. Softw. Tools Technol. Transf.
, 25
(3
), pp. 1
–11
. 6.
Wang
, T.
, Yang
, Y.
, and Xiang
, W.
, 2023
, “Computationally Efficient Neural Hybrid Automaton Framework for Learning Complex Dynamics
,” Neurocomputing
, 562
, p. 126879
. 7.
Xiang
, W.
, Tran
, H.-D.
, and Johnson
, T. T.
, 2018
, “Output Reachable Set Estimation and Verification for Multilayer Neural Networks
,” IEEE Trans. Neural Netw. Learn. Syst.
, 29
(11
), pp. 5777
–5783
. 8.
Wang
, S.
, Zhang
, H.
, Xu
, K.
, Lin
, X.
, Jana
, S.
, Hsieh
, C.-J.
, and Kolter
, J. Z.
, 2021
, “Beta-CROWN: Efficient Bound Propagation With Per-Neuron Split Constraints for Neural Network Robustness Verification
,” Adv. Neural Inf. Process. Syst.
, 34
, pp. 29909
–29921
.9.
Tran
, H.-D.
, Musau
, P.
, Lopez
, D. M.
, Yang
, X.
, Nguyen
, L. V.
, Xiang
, W.
, and Johnson
, T. T.
, 2019
, “Parallelizable Reachability Analysis Algorithms for Feed-forward Neural Networks
,” IEEE/ACM 7th International Conference on Formal Methods in Software Engineering (FormaliSE)
, Montreal, QC, Canada
, May 27
, IEEE, pp. 51
–60
.10.
Feng
, R.
, Leung
, C.-S.
, and Sum
, J.
, 2018
, “Robustness Analysis on Dual Neural Network-Based WTA With Input Noise
,” IEEE Trans. Neural Netw. Learn. Syst.
, 29
(4
), pp. 1082
–1094
. 11.
Lopez
, D. M.
, Choi
, S. W.
, Tran
, H. -D.
, and Johnson
, T. T.
, 2023
, “NNV 2.0: The Neural Network Verification Tool
,” International Conference on Computer Aided Verification (CAV)
, Paris, France
, July 17–22
, Springer, pp. 397
–412
.12.
Vincent
, J. A.
, and Schwager
, M.
, 2021
, “Reachable Polyhedral Marching (RPM): A Safety Verification Algorithm for Robotic Systems With Deep Neural Network Components
,” IEEE International Conference on Robotics and Automation (ICRA)
, Xi'an, China
, May 30–June 5
, IEEE, pp. 9029
–9035
.13.
Yang
, Y.
, and Xiang
, W.
, 2023
, “Modeling Dynamical Systems With Neural Hybrid System Framework via Maximum Entropy Approach
,” 2023 American Control Conference (ACC)
, San Diego, CA
, May 31–June 2
, pp. 3907
–3912
.14.
Reinhart
, R. F.
, and Steil
, J. J.
, 2011
, “Neural Learning and Dynamical Selection of Redundant Solutions for Inverse Kinematic Control
,” 11th IEEE-RAS International Conference on Humanoid Robots
, Bled, Slovenia
, Oct. 26–28
, IEEE, pp. 564
–569
.15.
Kanazawa
, A.
, Zhang
, J. Y.
, Felsen
, P.
, and Malik
, J.
, 2019
, “Learning 3D Human Dynamics From Video
,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
, Long Beach, CA
, June 15–20
, pp. 5614
–5623
.16.
Khansari-Zadeh
, S. M.
, and Billard
, A.
, 2011
, “Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models
,” IEEE Trans. Rob.
, 27
(5
), pp. 943
–957
. 17.
Pan
, H.
, Li
, Y.
, Cao
, Y.
, and Ma
, Z.
, 2016
, “Model Checking Computation Tree Logic Over Finite Lattices
,” Theor. Comput. Sci.
, 612
, pp. 45
–62
. 18.
Hajdu
, Á.
, and Micskei
, Z.
, 2020
, “Efficient Strategies for CEGAR-Based Model Checking
,” J. Autom. Reason.
, 64
(6
), pp. 1051
–1091
. Copyright © 2024 by ASME
You do not currently have access to this content.
