Category: featuredposts

 

Name	Oded Gottlieb
Date	24.11.19
Faculty	Mechanical Eng.
Title	The onset of chaos in nonlinear nano- resonators
Web page	https://ncds.technion.ac.il/
Email	oded@technion.ac.il
Study materials	Oded Gottlieb 24.11.19

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

 

Name	Dan Garber
Date	3-11-19
Faculty	IE&M
Title	Projection-free Optimization and Learning
Web page	https://dangar.net.technion.ac.il/
Email	dangar@technion.ac.il
Study materials	Dan Graber 3.11

 

Name	Nir gavish
Date	27-10-19
Faculty	Mathematics
Title	Intro
Web page	ngavish.net.technion.ac.il
Email	ngavish@technion.ac.il
Study materials	Intro