Title:
Lecture 5: Mathematics for Deep Neural Networks: Energy landscape and open problems
Lecture 5: Mathematics for Deep Neural Networks: Energy landscape and open problems
Author(s)
Schmidt-Hieber, Johannes
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
Abstract
To derive a theory for gradient descent methods, it is important to have some understanding of the energy landscape. In this lecture, an overview of existing results is given. The second part of the lecture is devoted to future challenges in the field. We describe important future steps needed for the future development of the statistical theory of deep networks.
Sponsor
Date Issued
2019-03-18
Extent
62:40 minutes
Resource Type
Moving Image
Resource Subtype
Lecture