arXiv · 1708.03322
Output Reachable Set Estimation and Verification for Multi-Layer Neural Networks
Abstract
In this paper, the output reachable estimation and safety verification problems for multi-layer perceptron neural networks are addressed. First, a conception called maximum sensitivity in introduced and, for a class of multi-layer perceptrons 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 proposed approaches.
Explore related subjects
Keep this discovery
Weiming Xiang, Hoang-Dung Tran, Taylor T. Johnson. 2017-08-09. Output Reachable Set Estimation and Verification for Multi-Layer Neural Networks. https://arxiv.org/abs/1708.03322
Cite the original work for its findings. Save a collection to share your selection of sources.