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.
Original language | English (US) |
---|---|
Article number | 8318388 |
Pages (from-to) | 5777-5783 |
Number of pages | 7 |
Journal | IEEE Transactions on Neural Networks and Learning Systems |
Volume | 29 |
Issue number | 11 |
DOIs | |
State | Published - Nov 2018 |
Externally published | Yes |
Keywords
- Multilayer perceptron (MLP)
- reachable set estimation
- simulation
- verification
ASJC Scopus subject areas
- Software
- Computer Science Applications
- Computer Networks and Communications
- Artificial Intelligence