Branch and Bound Methods for Neural Network Verification

点击翻译按钮获取中文摘要

This project mainly falls within EPSRC "theoretical computer science" research area. However, there are numerous other research areas which are also relevant to my project such as "artificial intelligence technologies", "image and vision computing", and to a lesser degree "natural language processing".Despite the recent success Deep Learning has had in a variety of scientific fields its use in safety-critical settings is still limited by the lack of formal verification. However, even though neural networks are generally being treated as a black-box method, some progress has been made on verifying straight-forward properties in simple networks. In my research I will focus on improving existing branch and bound methods that exploit the piecewise linear structure of neural networks with the aim of being able to apply them to larger networks. Improvements can be made to all three parts of the branch and bound algorithm: the search strategy, which picks the next domain to branch on, the branching rule, which given a domain divides it into non-intersecting subdomains, and finally the bounding methods, which estimate lower and upper bounds for each subdomain.