Verifying Binarized Neural Networks by Angluin-Style Learning.
SAT(2019)
摘要
We consider the problem of verifying the behavior of binarized neural networks on some input region. We propose an Angluin-style learning algorithm to compile a neural network on a given region into an Ordered Binary Decision Diagram (OBDD), using a SAT solver as an equivalence oracle. The OBDD allows us to efficiently answer a range of verification queries, including counting, computing the probability of counterexamples, and identifying common characteristics of counterexamples. We also present experimental results on verifying binarized neural networks that recognize images of handwritten digits.
更多查看译文
关键词
Verification, Neural networks, Decision Diagrams
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要