Advances in Machine Learning, Optimization, and Control Applications
|
Organizer(s): |
Name:
|
Affiliation:
|
Country:
|
Wanquan Liu
|
Sun Yat-sen University
|
Peoples Rep of China
|
Xuefang Li
|
Sun Yat-sen University
|
Peoples Rep of China
|
Ping Wang
|
Sun Yat-sen University
|
Peoples Rep of China
|
|
|
|
|
|
|
|
|
Introduction:
| | Over the past decades, data science and machine learning have demonstrated tremendous success in many areas of science and engineering, such as large-scale pattern recognition, computer vision, multi-agent control, industrial engineering, etc. The connection between machine learning and control theory is becoming a popular research topic, which may endow control systems with learning ability and thus improve the control ability and performance of conventional control approaches. Furthermore, the coupling of a learning algorithm with a control loop however requires a combined treatment as a dynamic process, which raises fundamental questions about stability, robustness, and safety for control systems. Additionally, the insights from robust control theory may, in turn, help to enhance robustness of machine learning algorithms. In order to leverage the potential of data-based and learning methods for control and optimization, we therefore believe that principled approaches integrating with machine learning and control theory are needed urgently, which therefore put forward new demands for novel mathematical theory, new optimization algorithms and statistical techniques behind machine learning. This session aims to present the latest theoretical and technical advancements in the broad areas of machine learning, optimization and control applications, and also to explore potential challenges in connections of these techniques. |
|
|
|
|
|
