Explore the mathematics behind deep neural networks in this final lecture of the TRIAD Distinguished Lecture Series by Johannes Schmidt-Hieber. Delve into the energy landscape of gradient descent methods and gain insights into existing research findings. Discover the future challenges in developing statistical theories for deep networks and learn about crucial steps needed for advancing the field. Engage with this comprehensive overview of current knowledge and potential research directions in the mathematical foundations of deep learning.
Mathematics for Deep Neural Networks: Energy Landscape and Open Problems - Lecture 5
Georgia Tech Research via YouTube
Overview
Syllabus
TRIAD Distinguished Lecture Series | Johannes Schmidt-Hieber Lecture 5 (of 5)
Taught by
Georgia Tech Research
Related Courses
-
Mathematics for Deep Neural Networks: Statistical Theory for Deep ReLU Networks - Lecture 4
-
Mathematics for Deep Neural Networks: Theory for Shallow Networks - Lecture 2 of 5
-
Mathematics for Deep Neural Networks: Introduction - Lecture 1 of 5
-
Mathematics for Deep Neural Networks: Advantages of Additional Layers - Lecture 3
-
Deep Neural Network for Beginners Using Python
-
Deep Learning - IIT Ropar
