Simplifying Neural Networks Using Formal Verification.
NFM(2020)
摘要
Deep neural network (DNN) verification is an emerging field, with diverse verification engines quickly becoming available. Demonstrating the effectiveness of these engines on real-world DNNs is an important step towards their wider adoption. We present a tool that can leverage existing verification engines in performing a novel application: neural network simplification, through the reduction of the size of a DNN without harming its accuracy. We report on the work-flow of the simplification process, and demonstrate its potential significance and applicability on a family of real-world DNNs for aircraft collision avoidance, whose sizes we were able to reduce by as much as 10%.
更多查看译文
关键词
Deep neural networks, Simplification, Verification, Marabou
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