Xiang Weiming, Tran Hoang-Dung, Johnson Taylor T
IEEE Trans Neural Netw Learn Syst. 2018 Nov;29(11):5777-5783. doi: 10.1109/TNNLS.2018.2808470. Epub 2018 Mar 15.
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.
在本简报中，研究了多层感知器（MLP）神经网络的输出可达性估计和安全验证问题。首先，引入了一个称为最大灵敏度的概念，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，使用基于仿真的方法，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，基于输出可达集估计结果开发了一种自动安全验证方法。给出了一个应用于双关节机器人手臂模型安全验证的实例，以展示所提方法的有效性。
