Abstract

Online Adaptive Systems in general, and learning neural nets in particular cannot be validated using traditional verification and validation techniques, because they evolve over time, and past learning data influences their behavior. In this paper we discuss a framework for reasoning about online adaptive systems, and see how this framework can be used to perform V\&V on such systems.

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