Coverage-Guided Testing for Recurrent Neural Networks



Huang, Wei, Sun, Youcheng, Zhao, Xingyu ORCID: 0000-0002-3474-349X, Sharp, James, Ruan, Wenjie, Meng, Jie and Huang, Xiaowei ORCID: 0000-0001-6267-0366
(2022) Coverage-Guided Testing for Recurrent Neural Networks. IEEE TRANSACTIONS ON RELIABILITY, 71 (3). pp. 1191-1206.

This is the latest version of this item.

[img] Text
Test_Metrics_for__Recurrent_Neural_Networks_journal.pdf - Author Accepted Manuscript

Download (3MB) | Preview

Abstract

This article proposes an adaptive neural-network command-filtered tracking control scheme of nonlinear systems with multiple actuator constraints. An equivalent transformation method is introduced to address the impediment from actuator nonlinearity. By utilizing the command filter method, the explosion of complexity problem is addressed. With the help of neural-network approximation, an adaptive neural-network tracking backstepping control strategy via the command filter technique and the backstepping design algorithm is proposed. Based on this scheme, the boundedness of all variables is guaranteed and the output tracking error fluctuates near the origin within a small bounded area. Simulations testify the availability of the designed control strategy.

Item Type: Article
Additional Information: Accepted by IEEE Transactions on Reliability
Uncontrolled Keywords: Measurement, Testing, Tools, Semantics, Recurrent neural networks, Software, Logic gates, Coverage-guided testing, coverage metrics, recurrent neural networks (RNNs), test case generation
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 20 May 2021 09:20
Last Modified: 18 Jan 2023 22:46
DOI: 10.1109/TR.2021.3080664
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3123327

Available Versions of this Item