The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here:

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

Computational science: Introduction to Artificial Neural Networks and Deep Learning (BERN04), 7.5 credits

Deep learning with artificial neural networks has become very popular in recent years, with impressive results on difficult problems such as classifying objects in images, interpreting human speech and generating informative text. This course provides an introduction to artificial neural networks and deep learning, with both theoretical and practical aspects.

Recent developments in machine learning have led to a surge of interest in artificial neural networks (ANN). New efficient algorithms and increasingly powerful hardware have made it possible to create very complex and high-performing ANNs. The process of training such complex networks has become known as deep learning, and the complex networks are typically called deep neural networks. A possibility that arises in such networks is to feed them with unprocessed or almost unprocessed input information and let the algorithms automatically combine the inputs into feature-like aggregates as part of their inherent structure. This is now known as feature learning or representation learning.

The overall aim of the course is to give students a basic knowledge of artificial neural networks and deep learning: both the theoretical background and how to practically use these methods for typical problems in machine learning and data mining. The course covers the most common models in artificial neural networks, with a focus on the multi-layer perceptron. The course contains three computer exercises where the student will train and evaluate different ANN models.

Who can take the course?

The course is designed for students with knowledge in mathematics and some programming after at least a couple of years of bachelor studies. The formal requirements are 90 credits in natural science including at least 45 credits of mathematics.

The course is given at half speed during the second half of the autumn term (note that for 2024 the wrong information is stated at  The course is also given for students on selected Engineering programmes under course code EXTQ41. Doctoral students are also welcome to take the course (course code NTF005F) and are asked to contact the course coordinator well before the course starts. The course has previously had the course codes FYTN14, EXTQ40, FYTN06 and FYS228.

More information about the course content, schedule and course evaluations can be found on the permanent course page on Canvas:

Eligibility & selection, application and admission

On the Lund University central website you will find syllabus, eligibility & selection, application & admission.

Introduction to Artificial Neural Networks and Deep Learning (BERN04)

Course code: BERN04
Credits: 7,5 hp
Cycle: Second cycle
Period: Autumn term, period 2, half speed


Schedule for BERN04 autumn 2024 on TimeEdit –

Course literature

  • Printed lecture notes "Introduction to Artificial Neural Networks and Deep Learning", M. Ohlsson & P. Edén, available at Media-Tryck, and as pdf on course website.
  • Supplemental online literature "Deep Learning Book" (

Course analyses

See the course page on Canvas

Course coordinator

Patrik Edén
Email: patrik [dot] eden [at] cec [dot] lu [dot] se (patrik[dot]eden[at]cec[dot]lu[dot]se)
Phone:+46 46 222 46 49