论文标题
神经网络的近似分配关系和确保神经网络压缩的应用
Approximate Bisimulation Relations for Neural Networks and Application to Assured Neural Network Compression
论文作者
论文摘要
在本文中，我们提出了馈电神经网络的近似分拟合关系的概念。在近似分配关系的框架中，开发了一种新型的神经网络合并方法，以根据神经网络的可及性分析来计算两个神经网络之间的近似分解误差。开发的方法能够定量测量具有相同输入的两个神经网络的输出之间的距离。然后，我们将近似的三拟合关系结果应用于进行神经网络模型降低并计算压缩精度，即确保的神经网络压缩。最后，使用确保的神经网络压缩，我们加速了ACAS XU神经网络的验证过程，以说明我们提出的近似分配方法的有效性和优势。
In this paper, we propose a concept of approximate bisimulation relation for feedforward neural networks. In the framework of approximate bisimulation relation, a novel neural network merging method is developed to compute the approximate bisimulation error between two neural networks based on reachability analysis of neural networks. The developed method is able to quantitatively measure the distance between the outputs of two neural networks with the same inputs. Then, we apply the approximate bisimulation relation results to perform neural networks model reduction and compute the compression precision, i.e., assured neural networks compression. At last, using the assured neural network compression, we accelerate the verification processes of ACAS Xu neural networks to illustrate the effectiveness and advantages of our proposed approximate bisimulation approach.
