Deep Learning
Faculteit  Science and Engineering 
Jaar  2019/20 
Vakcode  WMAI18002 
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 this course, the student is able to:  Explain the theory of deep neural networks  Explain different methods for optimizing deep neural networks  Explain the workings of different kinds of networks such as convolutional neural networks and recurrent neural networks  Explain the workings of generative neural network models  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 though convolutional neural networks and recurrent neural networks and ending with generative models. There will be a practical project 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 etc.  
Uren per week  
Onderwijsvorm  Bijeenkomst (S), Hoorcollege (LC), Practisch werk (PRC)  
Toetsvorm 
Presentatie (P), Schriftelijk tentamen (WE), Verslag (R)
(40% Written Exam, 50% Project Report, 10% Presentation. Students need to score at least a 5.0 on the Written Exam.) 

Vaksoort  master  
Coördinator  dr. M.A. Wiering  
Docent(en)  dr. M.A. Wiering  
Verplichte literatuur 


Entreevoorwaarden  Prior knowledge is assumed about linear algebra and calculus. Because the course is for AI students, the students are supposed to have this prior knowledge.  
Opmerkingen  The course unit prepares students to do their graduation project if they choose to do it in deep learning. This course might only be for Artificial Intelligence / HumanMachine Communication students this year, depending on the number of enrollments. Enrolling to the course unit as a nonAI/HMC student is not a guarantee that you will get in. 

Opgenomen in 
