Abstract

Online adaptive systems cannot be certified using traditional testing and proving methods, because these methods rely on assumptions that do not hold for such systems. In this paper, we discuss a framework for reasoning about online adaptive systems, and see how this framework can be used to perform the verification of these systems. In addition to the framework, we present some preliminary results on concrete neural network models.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call