Kaisa_2012_3_photo by Veikko Somerpuro

Enrol
7.8.2018 at 09:00 - 27.8.2018 at 23:59

Timetable

Description

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

None

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: http://www.deeplearningbook.org

Lectures, and weekly exercise sessions.

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

Separate exams last 3 hours and 30 minutes. Renewal exam (marked with "(U)") is the first separate exam after the course and also a renewal exam of course exam(s). In a renewal exam the points student has earned during the course are taken into account. Exams marked with "(HT)" are allowed only to students who have completed the obligatory projects or other exercises included in those courses. Exams marked with "(HT/U)" are renewals to students who have completed the obligatory projects during the course. Separate exams might cover different area than the lectured course. Check the course web page and contact the responsible teacher if in doubt.

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