arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.09527cs.LG
收藏

基于抽象的神经网络输出范围分析

Abstraction based Output Range Analysis for Neural Networks

Kansas State University(堪萨斯州立大学)

Pavithra Prabhakar, Zahra Rahimi Afzal

摘要:

在本文中,我们考虑了带有ReLU激活函数的前馈神经网络的输出范围分析问题。现有的方法将输出范围分析问题归结为可满足性和优化求解问题,这是NP难问题,其计算复杂性随着网络中神经元数目的增加而增加。为了解决计算复杂性,我们提出了一种新的抽象技术,构建了一个更简单的神经网络与更少的神经元,虽然与区间权重称为区间神经网络(INN),过度近似给定的神经网络的输出范围。我们减少了对INNs的输出范围分析,以解决一个混合整数线性规划问题。我们的实验结果突出了计算时间和计算输出范围的精度之间的权衡。

英文摘要:

In this paper, we consider the problem of output range analysis for feed-forward neural networks with ReLU activation functions. The existing approaches reduce the output range analysis problem to satisfiability and optimization solving, which are NP-hard problems, and whose computational complexity increases with the number of neurons in the network. To tackle the computational complexity, we present a novel abstraction technique that constructs a simpler neural network with fewer neurons, albeit with interval weights called interval neural network (INN), which over-approximates the output range of the given neural network. We reduce the output range analysis on the INNs to solving a mixed integer linear programming problem. Our experimental results highlight the trade-off between the computation time and the precision of the computed output range.

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。

↑