Academy of Mathematics and Systems Science, CAS
Colloquia & Seminars

Speaker:	Ruigang Wang, University of Sydney
Inviter:
Title:	Deep Neural Networks with Guaranteed Input- Output Behaviors
Language:	Chinese
Time & Venue:	2023.12.29 13:30-14:30 南楼N514
Abstract:	Deep learning has demonstrated impressive results on a variety of problems, however, many of these results have not translated to applications in safety-critical applications, partly due to the cost of system failure and partly due to the difficulty of ensuring reliable and robust model behaviour. In this talk, I will present new approaches to training models that have built-in stability and robustness guarantees. This approach has deep connection with robust control theory, in particular, the integral quadratic constraint (IQC) framework. Finally, I will illustrate the applications of the proposed models in supervised learning, system identification, state estimation and learning for control.