Matthew Turner (Anti-windup and aircraft control)

In this episode we interview Professor Matthew Turner, professor in the Cyber Physical Systems group at the university of Southampton, about his fascinating work on aircraft control, anti-windup, Lur’e systems, and his recent research into applying techniques from control theory to the analysis of neural networks.The transcript for this episode is available at: https://docs.google.com/document/d/1r41Lcpv4MtxnqfMn8ZFfnAqiK5rlfcPZ19NQhfeqaFI/edit?usp=sharing  Contact me at: [email protected] have an Instagram now!References:PhD ThesisNationalResearch Council of Canada Aerospace Research CentreNonlinear High Gain FeedbackLMIs in ControlAW for Model-Reference Adaptive ControlAW for ILCAnti-Windup ReviewTwo-Stage Anti-WindupAnti-Windup in Anticipation of Saturation (Zongli Lin)Matt TurnerChris RichardsAizerman ConjectureIan PostlethwaiteJorge SofronyMurray KerrOliver BriegerCircle and Popov CriterionKhalil Nonlinear Control BookZames and Sakkary Gap Metric PaperGeorge ZamesZames-Falb Multipliers Summary ArticleO’ShearZames-Falb Multipliers: Don’t PanicEarly Neural Network Work (with Guido Hermann)Additional NN ResearchRoss DrummondReLU Network Analysis Using Lur’e SystemsAntonis PapachristodolouExploiting Sparsity in Neural NetworksRobust Control PaperMalcolm SmithGlenn VinnicombeOther cool neural network/ control papersSynthesis of MPC Algorithms that Robustly Approximate Neural NetworksShrinking Down Neural Networks Using Inspiration from ControlDesigning Neural Networks that are More Robust