On the Connection between Neural Networks and Kernels: a Modern Perspective -Simon Du
Workshop on Theory of Deep Learning: Where next?
Topic: On the Connection between Neural Networks and Kernels: a Modern Perspective
Speaker: Simon Du
Affiliation: Member, School of Mathematics
Date: October 16, 2019
For more video please visit http://video.ias.edu
Видео On the Connection between Neural Networks and Kernels: a Modern Perspective -Simon Du канала Institute for Advanced Study
Topic: On the Connection between Neural Networks and Kernels: a Modern Perspective
Speaker: Simon Du
Affiliation: Member, School of Mathematics
Date: October 16, 2019
For more video please visit http://video.ias.edu
Видео On the Connection between Neural Networks and Kernels: a Modern Perspective -Simon Du канала Institute for Advanced Study
Показать
Комментарии отсутствуют
Информация о видео
16 октября 2019 г. 22:37:12
00:30:47
Другие видео канала
Lecture 7 - Deep Learning Foundations: Neural Tangent KernelsDeep Networks Are Kernel Machines (Paper Explained)Making Cross Validation Simple|What,why and types of Cross validationDeep Learning Basics: Introduction and OverviewTowards a theoretical foundation of neural networks - Jason LeeA function space view of overparameterized neural networks - Rebecca Willet, University of ChicagoAndrew Rowan - Bayesian Deep Learning with Edward (and a trick using Dropout)The mystery of over-parametrization in neural networks Behnam NeyshaburIs Optimization the Right Language to Understand Deep Learning? - Sanjeev AroraNeural Tangent Kernel: Convergence and Generalization in Neural NetworksSolving Inverse Problems with Deep Learning by Lexing YingGeoffrey Hinton: The Foundations of Deep LearningRademacher Complexity & VC DimensionThe Institute for Advanced Study Campus TourLearning and Generalization in Over-parametrized Neural Networks, Going Beyond Kernels16. Learning: Support Vector MachinesOWOS: Francis Bach - "On the Convergence of Gradient Descent for Wide Two-Layer Neural Networks"Designing Next-Generation Numerical Methods with Physics-Informed Neural Networks1W-MINDS: Gitta Kutyniok, June 18, 2020, Understanding Deep Neural Networks: From Generalization...A visual guide to Bayesian thinking