AISEC seminar: Neural Network Robustness – Careful what you verify!

This week's seminar is:
 
Matthew Daggitt, Heriot-Watt University
Title: Learning weighted automata
Wednesday, 5th of May, 9:00 GMT.

Abstract: Verifying the robustness of neural networks is a hot topic in Machine Learning at the moment. As is often common in active areas of research, there has been a proliferation in the number of definitions of robustness out there. However as of yet, the consequences of the differences in these definitions do not seem to be widely discussed in the literature.

In this talk I will compare four different definitions of robustness, and in particular look at: their motivation, mathematical properties, assumptions about the underlying distribution of data, and interpretability. In particular we highlight that if not used with care, the popular definition of classification robustness may result in a contradictory specification! This work is the result of the collaboration of various members of LAIV.

Generally, all AISEC seminars are open for all interested colleagues, see http://laiv.uk/laiv-seminars/ 
There is a mailing list to join, if you wish to get seminar reminders and updates.