arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1802.03557eess.SYcs.SY
收藏

神经网络非线性动态系统可达集估计与验证

Reachable Set Estimation and Verification for Neural Network Models of Nonlinear Dynamic Systems

Vanderbilt University(范德堡大学)

Weiming Xiang, Diego Manzanas Lopez, Patrick Musau, Taylor T. Johnson

AI总结:

本文针对神经网络模型的可达集估计与验证问题,提出分层计算算法和迭代方法,通过细胞划分和安全区域检查,提升非线性自回归移动平均模型的安全性。

摘要:

神经网络已被广泛用于解决复杂现实问题。由于神经网络的复杂、非线性和非凸性质,为确保其在安全关键系统中的行为安全性,必须提供正式的安全保证。本文针对非线性自回归移动平均(NARMA)模型的可达集估计与验证问题,提出基于多层感知机(MLP)的分层计算算法和迭代方法。通过将MLP的输入集划分为有限数量的单元,开发了逐层计算算法以估计每个单元的可达集。所有单元估计可达集的并集形成MLP可达集的上界近似。此外,针对NARMA模型开发了基于MLP可达集估计的迭代可达集估计算法。通过检查不安全区域与估计可达集的交集来执行安全性验证。提供了多个数值示例以说明该方法。

英文摘要:

Neural networks have been widely used to solve complex real-world problems. Due to the complicate, nonlinear, non-convex nature of neural networks, formal safety guarantees for the behaviors of neural network systems will be crucial for their applications in safety-critical systems. In this paper, the reachable set estimation and verification problems for Nonlinear Autoregressive-Moving Average (NARMA) models in the forms of neural networks are addressed. The neural network involved in the model is a class of feed-forward neural networks called Multi-Layer Perceptron (MLP). By partitioning the input set of an MLP into a finite number of cells, a layer-by-layer computation algorithm is developed for reachable set estimation for each individual cell. The union of estimated reachable sets of all cells forms an over-approximation of reachable set of the MLP. Furthermore, an iterative reachable set estimation algorithm based on reachable set estimation for MLPs is developed for NARMA models. The safety verification can be performed by checking the existence of intersections of unsafe regions and estimated reachable set. Several numerical examples are provided to illustrate our approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑