Course syllabus - Deep Learning and Neural Networks

Objectives

The aim of this course is to cover the basis of deep learning, including essential part of this topic such as Feedforward neural networks, Convolutional neural networks, and Recurrent neural network. Deep learning has emerged recently and belongs to machine learning, which is part of artificial intelligence. Thus, this course will also provide insight into more recent theoretical developments in the field of AI.

Learning outcomes

After completing the course, the student should be able to: 

1. understand the different types of algorithms within Deep Learning,
2. apply Deep Feedforward Networks for solving problems,
3. apply Convolutional Neural Networks for solving problems in computer vision,
4. apply Recurrent and Recursive Neural Networks for solving time-series problems,
5. apply Autoencoders on Unsupervised Learning problems,
6. apply Deep Generative Networks on different problem types and also
7. analyze and explain the importance of hyperparameters in Deep Learning, as well as being able to relate different configurations to each other in the context of solving different problems.

Course content

- Introduction to deep learning through a general overview and an analysis of the algorithms of central importance.
- Introduction to Deep Learning and the importance of it on different applications areas.
- A review of specific deep learning algorithms, such as Deep learning neural networks, Feedfordward networks, Autoencoders and Generative networks.

Specific requirements

Completed courses of  60 credits in computer science, of which includes Programming 7,5 credits, Data Structures, Algorithms and Program Development 7,5 credits and Artificial Intelligence 1 7,5 credits. In addition basic vector algebra 7,5 credits and  basic calculus 7,5 credits are needed.

Examination

Laboratory work 1 (LAB1), An assignment that is presented with a report and a demonstration to the teacher, 1.5 credits, examines the learning goals 1, 2 and 7, marks Fail (U), 3, 4 or 5.  

Laboratory work 2 (LAB2), An assignment that is presented with a report and a demonstration to the teacher, 1.5 credits, examines the learning goals 1, 3 and 7, marks Fail (U), 3, 4 or 5.  

Laboratory work 3 (LAB3), An assignment that is presented with a report and a demonstration to the teacher, 1.5 credits, examines the learning goals 1, 4 and 7, marks Fail (U), 3, 4 or 5.  

Laboratory work 4 (LAB4), An assignment that is presented with a report and a demonstration to the teacher, 1.5 credits, examines the learning goals 1, 5 and 7, marks Fail (U), 3, 4 or 5.  

Laboratory work 5 (LAB5), An assignment that is presented with a report and a demonstration to the teacher, 1.5 credits, examines the learning goals 1, 6 and 7, marks Fail (U), 3, 4 or 5.

A student who has a certificate from MDU regarding a disability has the opportunity to submit a request for supportive measures during written examinations or other forms of examination, in accordance with the Rules and Regulations for Examinations at First-cycle and Second-cycle Level at Mälardalen University (2020/1655). It is the examiner who takes decisions on any supportive measures, based on what kind of certificate is issued, and in that case which measures are to be applied.

Suspicions of attempting to deceive in examinations (cheating) are reported to the Vice-Chancellor, in accordance with the Higher Education Ordinance, and are examined by the University’s Disciplinary Board. If the Disciplinary Board considers the student to be guilty of a disciplinary offence, the Board will take a decision on disciplinary action, which will be a warning or suspension.

Grade

Pass with distinction, Pass with credit, Pass, Fail

Interim Regulations and Other Regulations

The course contributes to fulfill the degree requirement of at least 75 credits in the main area of computer science with specialisation in intelligent systems for technology bachelor's degree in computer science with specialisation in intelligent systems.