Subject: Subject Sylbus: Deep Learning and Approximation Theory - 196014 (Current)

Deep Learning and Approximation Theory - 196014
Credit
Points
3.0
Given In
Semester
b
Lecture Exercise Laboratory Project or
Seminar
House
Work
Weekly
Hours
3

Determination of the grade according to progress during the semester and the submission of the final thesis


Prerequisites: ( Probability Theory 104222
and Infinitesimal Calculus 3 104295 )
or ( Probability (Advanced) 094412
and Calculus 2M 104032 )
or ( Differential and Integral Calculus 2T 104013
and Introduction to Probability H 104034 )
or ( Probability (Ie) 094411
and Differential and Integral Calculus 2M 104022 )


The First Part of the Course Will Be a Short Introduction to Machine Part of the Course Will Focus Solely on the Approximation Aspect of Connected Networks, Universality of Convolutional Networks and Invariant Networks, Approximation Rates for Smooth Functions, Relationship Between Neural Networks and More Classical Function Bases (Finite Elements, Splines, Wavelets), and "Power of Depth" Results Which Point to Functions That Can Be Approximated More Efficiently by Deep Neural Nets Than by Other Models. Be Able to:
Theory. B. Be Skilled to Read a State of the Art Research on Approximation Properties of Deep Neural Networks and Will Be Able to Conduct Independent Research in This Field.




Times and places of examinations 02/2021 2021/2022 Spring Semester
examination timedaydateSeason
Monday18.07.2022
Thursday29.09.2022

Timetable to semester 02/2021 2021/2022 Spring Semester
RoomBuildingHourdayLecturerExercise
Lecture
no.Registering
Group
08:30-11:30TuesdayDr. Dym NadavLecture1010


Textbooks
PublishedPublisherAuthorsBook
2014cambridge university pressshai shalev-shwartz and shai ben-davidunderstanding machine learning: from theory to algorithem

Created in 24/01/2022 Time 20:56:58