Analytical methods in differential equations – Technical details

  1. A four-hour lecture course which provides four academic points.
  2. A weekly homework assignment will be provided.
  3. There will be a final exam.
  4. One of the questions at the final exam will be similar to one of the questions in the homework.
  5. The lecturer will prepare formula sheets for use at the final exam. These formula sheets will be available on the course website throughout the semester.
  6. A large collection of old exam will be available for students on the course website.

 

Why Neural Networks converge to “simple” solutions?

Abstract:

Since 2012, deep neural networks are having an impressive practical success in many domains, yet their theoretical properties are not well understood. I will discuss why does neural network optimization, which based on local greedy steps, tend to converge to:

1) A global minimum, while many local minima exist.

2) A specific “good” global minimum in which the network function is surprisingly “simple” (while many “bad” global minima exist).

Name Daniel Soudry
Date 10-11-19
Faculty  EE
Title  Why Neural Networks converge to “simple” solutions?
Web page https://sites.google.com/site/danielsoudry/
Email daniel.soudry@gmail.com
Study materials About the deep learning era