Control Theory and Deep Learning: Synergistic Partners in Theory and Applications

Dr. Claire Walton

University of Texas San Antonio

Friday, October 22, 2021

11 AM – 12 PM CST

https://utsa.zoom.us/j/98953233499

Abstract: Recent research has revealed significant connections between deep learning infrastructures such as neural networks and the modelling and control of complex dynamic systems.  Dynamic systems describe applications from self-driving cars to energy conservation to SpaceX rockets. Control of these systems brings up many challenges, such as nonlinearity, uncertainty, high dimensionality, and real-time decision-making demands. Application of neural nets to dynamic system control problems is an exciting current research area, which has already provided promising examples. However, perhaps a more surprising direction of impact has been the application of dynamic systems insights to deep learning itself. Equivalencies have been found between neural networks and the optimal control of dynamic systems, suggesting the computational tools of the latter can be used for the former. This has opened the door to many exciting possibilities driven by these equivalencies, such as the use of computational control algorithms to train neural networks, and development of network architectures developed from discretized control and dynamics models. This talk will provide a survey of these topics and of the cross-fertilization underway between control theory and deep learning.