Year: 2018
Type: article
Abstract: In this brief, the output reachable estimation and safety verification problems for multilayer perceptron (MLP) neural networks are addressed. First, a conception called maximum sensitivity is introduced, and for a class of MLPs whose activation functions are monotonic functions, the maximum sensitivity can be computed via solving convex optimization problems. Then, using a simulation-based method, the output reachable set estimation problem for neural networks is formulated into a chain of optimization problems. Finally, an automated safety verification is developed based on the output reachable set estimation result. An application to the safety verification for a robotic arm model with two joints is presented to show the effectiveness of the proposed approaches.
Institution: Vanderbilt University
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: G129050612, SHF: Small: Automating Improvement of Development Environments for Cyber-Physical Systems (AIDE-CPS), G1522347985, CRII: CPS: Safe Cyber-Physical Systems Upgrades, G36914211, SHF: Small: Automating Improvement of Development Environments for Cyber-Physical Systems (AIDE-CPS), CRII: CPS: Safe Cyber-Physical Systems Upgrades
OpenAlex ID: W2962692913
