Course Identification

Seminar on Deep Learning Theory
20194242

Lecturers and Teaching Assistants

Prof. Ohad Shamir
N/A

Course Schedule and Location

2019
Second Semester
Wednesday, 09:15 - 11:00, Ziskind, Rm 1
27/03/2019

Field of Study, Course Type and Credit Points

Mathematics and Computer Science: Seminar; 2.00 points

Comments

On May 15th the lecture will be held at Botnar Auditorium.

Prerequisites

No

Restrictions

30

Language of Instruction

English

Attendance and participation

Expected and Recommended

Grade Type

Pass / Fail

Grade Breakdown (in %)

20%
80%

Evaluation Type

Seminar

Scheduled date 1

N/A
N/A
-
N/A

Estimated Weekly Independent Workload (in hours)

2

Syllabus

In this seminar, students will read, present and discuss recent research papers on the theory of deep learning. The focus will be on rigorous results, pertaining to questions such as why neural networks are successfully trained with simple gradient based methods; why large-scale neural networks are able to generalize well; and how does the network's architecture affects the types of predictors it can express. Students will be able to choose a paper from a predefined list, or present a paper of their own choice (in coordination with the lecturer). 

Learning Outcomes

Upon succesful completion of this course:

The students will gain familiarity with the current state-of-the-art in deep learning theory.

Reading List

N/A

Website

N/A