论文标题
使用带有扰动顺序输入的复发神经网络对分类的鲁棒性分析
Robustness Analysis of Classification Using Recurrent Neural Networks with Perturbed Sequential Input
论文作者
论文摘要
对于给定稳定的复发性神经网络（RNN），该神经网络（RNN）经过训练以使用顺序输入执行分类任务，我们将明确的鲁棒性界限量化为可训练的重量矩阵的函数。顺序输入可以通过各种方式扰动，例如，由于机器人运动或不完善的相机镜头，流式图像可以变形。使用稳定RNN的Voronoi图和Lipschitz属性的概念，我们提供了彻底的分析并表征了最大允许的扰动，同时保证了分类任务的全部精度。我们使用带有云以及MNIST数据集的地图数据集说明和验证我们的理论结果。
For a given stable recurrent neural network (RNN) that is trained to perform a classification task using sequential inputs, we quantify explicit robustness bounds as a function of trainable weight matrices. The sequential inputs can be perturbed in various ways, e.g., streaming images can be deformed due to robot motion or imperfect camera lens. Using the notion of the Voronoi diagram and Lipschitz properties of stable RNNs, we provide a thorough analysis and characterize the maximum allowable perturbations while guaranteeing the full accuracy of the classification task. We illustrate and validate our theoretical results using a map dataset with clouds as well as the MNIST dataset.
