Direkt zum Inhalt springen
Computer Vision Group
TUM Department of Informatics
Technical University of Munich

Technical University of Munich

Menu
Home Teaching Summer Semester 2019 Seminar: Optimization and Generalization in Deep Learning

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
teaching:ss2019:dltheory_ss19 [2019/04/12 12:42]
Thomas Frerix
teaching:ss2019:dltheory_ss19 [2019/04/23 14:59] (current)
Thomas Frerix
Line 9: Line 9:
 As stated in the pre-meeting and on this website, preference is given to students who showed prior exposure to the prerequisites. As stated in the pre-meeting and on this website, preference is given to students who showed prior exposure to the prerequisites.
  
-<​html><​font color=red><​b>​Initial meeting: April 24, 4pm-6pm, room 02.09.023</​b></​font></​html>​+<​html><​font color=red><​b>​Initial meeting: April 24, 4.15pm-5.45pm, room 02.09.023</​b></​font></​html>​
  
 <​html><​font color=red><​b>​Update (April 12): Due to room constraints,​ the time of the initial meeting had to be shifted to 4-6pm</​b></​font></​html>​ <​html><​font color=red><​b>​Update (April 12): Due to room constraints,​ the time of the initial meeting had to be shifted to 4-6pm</​b></​font></​html>​
Line 18: Line 18:
 Modern deep learning methods have shown remarkable success in various domains of machine learning. However, our theoretical understanding of such methods remains rather shallow. Recently, novel ideas to better understand aspects of optimization and generalization in these models have emerged that require rethinking classical concepts in these domains. A prominent example is the implicit bias of optimization methods in an overparameterized regime. We will discuss such ideas from the computational and statistical viewpoint. Modern deep learning methods have shown remarkable success in various domains of machine learning. However, our theoretical understanding of such methods remains rather shallow. Recently, novel ideas to better understand aspects of optimization and generalization in these models have emerged that require rethinking classical concepts in these domains. A prominent example is the implicit bias of optimization methods in an overparameterized regime. We will discuss such ideas from the computational and statistical viewpoint.
  
 +==== Material and Schedule ====¬†
 +Seminar material and the schedule can be accessed [[teaching:​ss2019:​dltheory_ss19:​internal|here]].
 ==== Organization ==== ==== Organization ====
  

Rechte Seite

Informatik IX
Chair for Computer Vision & Artificial Intelligence

Boltzmannstrasse 3
85748 Garching

info@vision.in.tum.de