Machine Learning and Control Theory Research Cluster by E. Zuazua
On October 6th, our Head Enrique Zuazua will be talking about Machine Learning and Control Theory as a session organized by the DCII – Dedman College Interdisciplinary Institute‘ on the Research cluster programs this academic year 2020-2021.
Abstract. Multi-layer neural networks have been shown to be the most powerful models in machine learning. However, the fundamental reasons for this success remains not well understood and for that it will require mathematical tools and expertise. One of the most important mathematical tools that can be used to study neural networks is Control/Mean Field theory that deals with the behavior of dynamical systems with inputs, and how their behavior is modified by feedback. By this Cluster, we would like to create a forum for faculties and researchers at regional universities and companies working on this important topic.