When: Thursday 18th of Sept, 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: Patricia Pauli
Title: Analysis and design of Lipschitz bounded convolutional neural networks – a control perspective
Abstract:
Despite the numerous successful applications of convolutional neural networks across various fields including image and natural language processing, they are black-box models that are not fully understood and lack robustness guarantees. This limits their use in safety-critical applications such as autonomous driving. In this talk, I address this problem by leveraging well-established concepts and principles from control theory to derive and enforce robustness guarantees for convolutional neural networks. One key measure for robustness of a neural network is its Lipschitz constant, yet finding the Lipschitz constant of a neural network is an NP-hard problem. Therefore, we are interested in (i) obtaining accurate upper bounds on the Lipschitz constant for convolutional neural networks and in (ii) designing convolutional neural networks with user enforced Lipschitz bounds, i.e., with robustness guarantees. In doing so, we exploit properties of the underlying building blocks of neural networks, for instance the fact that nonlinear activation functions are slope-restricted and that convolutions can be represented in state space, to develop semidefinite programming-based methods for the robustness analysis and robust design of convolutional neural networks.
Bio:
Patricia Pauli received M.Sc. degrees in Mechanical Engineering and Computational Engineering from the Technical University of Darmstadt, Germany, in 2019. During her M.Sc., she spent one year at the University of California, Berkeley, and conducted her master’s thesis research at Massachusetts Institute of Technology under the supervision of Dr. Anuradha Annaswamy. From 2019 to 2025, she pursued her Ph.D. at the Institute for Systems Theory and Automatic Control under Prof. Frank Allgöwer’s supervision at the University of Stuttgart and was a member of the International Max Planck Research School for Intelligent Systems. In 2022, she spent a research stay at the University of Sydney with Ian Manchester. On October 1 2025, Patricia will start a position as an Assistant Professor in the Control Systems Technology group at Eindhoven University of Technology. Her research interests lie in the area of safe AI-based control.