Deep learning

Master's level course on Deep learning

The course will cover (among other things): Feed-forward neural networks, backpropagation, regularization and optimization of neural networks, Convolutional Neural Networks (CNN) and images, word embeddings and Recurrent Neural Networks (RNN) with applications for text, residual learning, attention. We will also briefly cover autoencoders, GANs, and other advanced topics.

Lectures are held on Monday and Thursday at 14:15 in C222, starting on October 29.

Exercise sessions are on Fridays at 12:15 in B120. The first exercise will be November 9. The first exercise will be released on the first lecture week and will be due Sunday, Nov 11 at 23:59. The exercises will in general be programming tasks in Python (numpy and pytorch).

Towards the end of the course there will be a group project work. More details about this later.

Lectures, exercises and any course news and updates will all be in Moodle.



Here is the course’s teaching schedule. Check the description for possible other schedules.

Mon 29.10.2018
14:15 - 16:00
Thu 1.11.2018
14:15 - 16:00
Mon 5.11.2018
14:15 - 16:00
Thu 8.11.2018
14:15 - 16:00
Mon 12.11.2018
14:15 - 16:00
Thu 15.11.2018
14:15 - 16:00
Mon 19.11.2018
14:15 - 16:00
Thu 22.11.2018
14:15 - 16:00
Mon 26.11.2018
14:15 - 16:00
Thu 29.11.2018
14:15 - 16:00
Mon 3.12.2018
14:15 - 16:00
Mon 10.12.2018
14:15 - 16:00
Thu 13.12.2018
14:15 - 16:00

Other teaching

02.11. - 14.12.2018 Fri 12.15-14.00
Roman Yangarber
Teaching language: Finnish


Prerequisites in terms of knowledge

Multivariate calculus: partial derivatives, gradients, Jacobians. Linear algebra: matrices, eigenvalues, matrix norms. Fundamentals of probability calculus. Basic information theory: cross-entropy. Machine learning: good grasp of the process of building models, training, testing / evaluating performance.

Prerequisites for students in the Data Science programme, in terms of courses

DATA11002 Introduction to Machine Learning

Prerequisites for other students in terms of courses

DATA11002 Introduction to Machine Learning

Recommended preceding courses


After completing the course, the students should know the general principles of neural networks and deep learning, understand the central methods covered in the course, and be able to apply them to solve real-world problems.
The course will cover, among other things:
  • Background and history of neural networks
  • The backpropagation algorithm
  • Regularization and optimization of neural networks
  • Feed-forward neural networks
  • Convolutional neural networks
  • Recurrent neural networks
  • Various advanced topics in brief: GANs, autoencoders and deep generative models
  • Practical vision and natural language applications with Python-based deep learning frameworks

Lecture slides and computer exercise materials will be provided during the course.

Course book: Deep Learning, Ian Goodfellow, Yoshua Bengio, and Aaron Courville, MIT Press 2016. Online version:

Lectures, and weekly exercise sessions.

​​Grading is based on the exam, exercises and group project.

All of the following parts of the course have to be completed successfully (above minimum threshold): exam, exercises and group project.