Deep Learning

Faculteit Science and Engineering
Jaar 2021/22
Vakcode WMAI017-05
Vaknaam Deep Learning
Niveau(s) master
Voertaal Engels
Periode semester II a
ECTS 5
Rooster rooster.rug.nl

Uitgebreide vaknaam Deep Learning
Leerdoelen At the end of the course, the student is able to:
1) Explain the theory of deep neural networks
2) Explain different methods for optimizing deep neural networks and their performance
3) Explain the workings of different kinds of networks such as convolutional neural networks and recurrent neural networks
4) Explain the workings of generative neural network models
5) Train deep neural networks and use them for a particular application
Omschrijving Deep learning receives a lot of attention from the machine learning community nowadays. In this course we will study different deep learning algorithms, starting from training feedforward neural networks with multiple layers, going to convolutional neural networks and recurrent neural networks and ending with generative models. There will be practical projects where a group of students will work to implement, optimize and test their own deep learning system for a particular application such as object recognition, object detection, speech recognition, text generation, etc.
Uren per week
Onderwijsvorm Hoorcollege (LC), Practisch werk (PRC)
Toetsvorm Schriftelijk tentamen (WE), Verslag (R)
(The final grade is based on the Written Exam (45%), Report 1 (22%), and Report 2 (33%). The grade of the written exam should be > 5.0. The final average grade should be >= 5.5)
Vaksoort master
Docent(en) H. Maathuis, MSc. , S.H. Mohades Kasaei, PhD. , M. Sabatelli, MSc. , J. Visser
Verplichte literatuur
Titel Auteur ISBN Prijs
Deep Learning 2016 Ian Goodfellow, Yoshua Bengio and Aaron Courville 9780262035613 ca. €  80,00
Entreevoorwaarden Mandatory: No prior knowledge is assumed. Please note that the student is expected to have a relevant BSc degree.
Advised: Prior knowledge about Linear Algebra and Calculus is assumed. Because the course is intended for AI students, participants are supposed to have this prior knowledge.
Opmerkingen This course unit has a capacity limit. More information about capacity-limit courses can be found here. This course has an intended limit of 100 participants. If there are more AI MSc students than 100, they are all permitted to take the course.

The course unit prepares students to do their graduation project if they choose to do it in deep learning.
Opgenomen in
Opleiding Jaar Periode Type
MSc Artificial Intelligence  (A - General Mandatory Course Units) - semester II a verplicht
MSc Human Machine Communication - per 21-22 Computational Cognitive Science  (C - Elective Course Units) - semester II a keuze