NWI-IMC058
Deep Learning
Course infoSchedule
Course moduleNWI-IMC058
Credits (ECTS)3
CategoryMA (Master)
Language of instructionEnglish
Offered byRadboud University; Faculty of Science; Informatica en Informatiekunde;
Lecturer(s)
Coordinator
dr. T.M. van Laarhoven
Other course modules lecturer
Examiner
dr. T.M. van Laarhoven
Other course modules lecturer
Lecturer
dr. T.M. van Laarhoven
Other course modules lecturer
Contactperson for the course
dr. T.M. van Laarhoven
Other course modules lecturer
Lecturer
dr. ir. G. van Tulder
Other course modules lecturer
Academic year2020
Period
KW1  (31/08/2020 to 01/11/2020)
Starting block
KW1
Course mode
full-time
RemarksThis is a new elective for the master Data Science
Registration using OSIRISYes
Course open to students from other facultiesYes
Pre-registrationNo
Waiting listNo
Placement procedure-
Aims
After taking this course you will be able to train and use deep neural networks, and you will be able to understand and develop more complicated deep architectures and learning algorithms.
 
After completing this course, the student
* is able to implement deep learning algorithms from scratch.
* will be able to train and use deep neural networks.
* knows different network architectures and training algorithms, and knows when they are appropriate to use.
* is able to read and understand academic literature about deep learning.
Content
Deep Learning is a flavor of machine learning that uses deep artificial
neural networks, meaning networks with many layers and often millions of
parameters. Over the last couple of years Deep Learning has shown huge
successes in different applications such as image and speech
recognition, game playing agents, image synthesis, computational
biology, etc.
 
In this course you will learn both how to apply Deep Learning to solve
problems, as well as how these deep neural networks are implemented and
how they work. We will treat many different architectures, and show
which ones are appropriate in which situations. Because this is a very
broad field that is continuously developing, we will not be focusing on
any specific application, but rather lay the groundwork on which all
deep learning techniques are built.
Level

Presumed foreknowledge
The student is expected to have a working knowledge of
 
* Linear algebra (vectors, matrices, matrix multiplication)
* Calculus (derivatives, chain rule)
* Probability theory
 
Some programming experience is required, but experience with python is
not expected.
 
Test information
The final grade is determined by
* Written exam (80%)
* Practical exercises (20%)
 
The grade for the written exam must be at least a 5.
 
Specifics

Required materials
Book
Dive into Deep Learning Aston Zhang, Zack C. Lipton, Mu Li, Alex J. Smola Available online at http://d2l.ai/
Title:Dive into Deep Learning
Author:Aston Zhang, Zack C. Lipton, Mu Li, Alex J. Smola

Recommended materials
Book
Deep Learning Ian Goodfellow, Yoshua Bengio, Aaron Courville https://www.deeplearningbook.org/
Title:Deep Learning
Author:Ian Goodfellow, Yoshua Bengio, Aaron Courville
Book
Theory of Deep Learning https://www.cs.princeton.edu/courses/archive/fall19/cos597B/lecnotes/bookdraft.pdf
Title:Theory of Deep Learning

Instructional modes
Course
Attendance MandatoryYes

Tests
Tentamen
Test weight1
OpportunitiesBlock KW1, Block KW2