CloseHelpPrint
Kies de Nederlandse taal
Course module: JM1100-M-6
JM1100-M-6
Deep Learning
Course info
Course moduleJM1100-M-6
Credits (ECTS)6
CategoryMA (Master)
Course typeCourse
Language of instructionEnglish
Offered byTilburg University; Tilburg School of Humanities and Digital Sciences; TSH Other;
Is part of
M Data Science and Entrepreneurship (joint degree)
Contact personC. de Oliveira Rocha
Lecturer(s)
lecturer
dr. G.A. Chrupala
Other course modules lecturer
Coordinator course
mr. J.M.F. van den Munckhof
Other course modules lecturer
lecturer
N.J.E. van Noord
Other course modules lecturer
Contact person for the course
C. de Oliveira Rocha
Other course modules lecturer
Coordinator course
prof. dr. E.O. Postma
Other course modules lecturer
Starting block
C1
Course mode
Full-time
RemarksThis information is not up to date. Check the Course Catalog 2018 or select the course via “Register”.
Registration opennot known yet
Aims
The objective of the course is to provide students with: (1) theoretical knowledge of convolutional and recurrent neural networks, (2) practical skills for performing experiments with deep learning, (3) understanding ways to (pre-)process signals, images, and texts for data science applications in general and for deep learning specifically.

Specifics

Deep Learning revolutionized machine learning by yielding the best performances in a large variety of application domains such as: speech recognition, image recognition, object detection, drug discovery and genomics. This course provides students with the understanding and skills to apply deep learning to signals, images, videos and textual sources. The course includes a training to run deep learning algorithms on special hardware.

Recommended Prerequisites

Basic understanding of machine learning / data mining. Elementary Statistics
Content
The lectures of the course start with a historical overview of deep learning. After a review of the formal basics, deep feedforward networks are explained in terms of (nonlinear) transformations and the backpropagation training procedure. Subsequently, the importance of regularization to prevent overfitting is explained and procedures for optimizing the induced model are outlined. Then, the notions of convolution and convolutional neural networks are explained. Sequence learning is addressed next by means of recurrent neural networks and their applications. This is followed by a review of the practical methodology of deep learning methods. Finally, applications are reviewed and recent scientific progress on the development of deep learning methods is discussed.
During skill classes, students are trained on applying the concepts addressed in the lectures.

Type of instructions

lab sessions; self study; MOOC session (occasionally)

Type of exams

Presentation 20% and Paper 80%. There will be interim tests with which students can earn bonus points (to a max. of 20%)

Compulsory Reading
  1. Goodfellow, I., Bengio, Y. and Courville, A., Deep Learning, Cambridge MA: MIT Press, 2016.
Required materials
-
Recommended materials
-
CloseHelpPrint
Kies de Nederlandse taal