Output Reachable Set Estimation and Verification for Multilayer Neural Networks
Output Reachable Set Estimation and Verification for Multilayer Neural Networks
复制标题
DOI：
10.1109/tnnls.2018.2808470
复制
发表时间：
2018-11-01
影响因子：
10.4
通讯作者：
Johnson, Taylor T.
中科院分区：
文献类型：
--
作者：
Xiang, Weiming;Hoang-Dung Tran;Johnson, Taylor T.
本文讨论了多层感知器（MLP）神经网络的输出可达估计和安全验证问题。首先，引入最大灵敏度的概念，对于一类激活函数为单调函数的mlp，可以通过求解凸优化问题来计算最大灵敏度。然后，采用基于仿真的方法，将神经网络的输出可达集估计问题转化为一系列优化问题。最后，基于输出的可达集估计结果，开发了一种自动安全验证方法。最后，通过对具有两个关节的机械臂模型进行安全性验证，验证了所提方法的有效性。
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.