Seminar: A Tutorial on Lipschitz-Bounded Neural Networks, 4th July, 1:00pm

When: Thursday 4th of July, 1:00pm AEST

Where: This seminar will be partially presented at the ACFR seminar area, J04 lvl 2 (Rose St Building) and partially online via Zoom. RSVP

Speaker: Ruigang Wang

Title: A Tutorial on Lipschitz-Bounded Neural Networks

Abstract:

In many deep learning based applications, it is desirable to learn neural networks with certifiable Lipschitz bound, i.e., the largest possible output changes under bounded input perturbations are also guaranteed to be bounded by model construction. In this talk, I will give a review of recent advances in Lipschitz-bounded neural networks as well as their applications in robust image classification, 3D modeling and control of dynamical systems. 

Bio:

Ruigang Wang received his Ph.D. degree in chemical engineering from UNSW (Sydney) in 2017. From 2017 to 2018 he worked as a postdoc at UNSW. Since then He is a postdoc at ACFR, University of Sydney. His research interests include control theory and trustworthy machine learning.

Contacts

Australian Centre for Robotics
info@acfr.usyd.edu.au