5 ECTS credits/135 hours of work
|Language of instruction
autumn, period 2
Upon completion of this course, the students will be able to:
- learn the theories, models, algorithms, implementation and recent progress of deep learning, and obtain empirical experience on training deep neural networks.
- will learn about linear classifiers, multilayer neural networks, back propagation and stochastic gradient descent, convolutional neural networks, recurrent neural networks, generative adversarial networks, deep network compression, deep transfer learning techniques and deep reinforcement learning (tentative).
- know about applications of deep learning to typical computer vision problems such as image classification, object detection and segmentation.
- learn to implement, train and debug their own neural networks with PyTorch.
Students should be comfortable taking derivatives and understanding matrix vector operations and notations.
Basic Probability and Statistics, Linear Algebra, basics of probabilities, Gaussian distributions, mean, standard deviation, etc.
have knowledge of Machine Learning course and digital image processing course
|Mode of delivery
|Learning activities and teaching methods
20h lectures, 12h exercise sessions, independent studying 95 hours.
B.Sc. and M.Sc. students of Computer Science and Engineering. The course fits also for Statistics and Math M.Sc. students interested in learning deep learning techniques.
|Prerequisites and co-requisites
The Bachelor level knowledge of Computer science and engineering study programmes. Good programming skills in a chosen language.
|Recommended optional programme components
The course is an independent entity and does not require additional studies carried out at the same time.
|Recommended or required reading
Lecture hand-out, complementary reading list, and exercise material will be provided.
|Assessment methods and criteria
Attending lectures and exercise sessions, and returning the weekly exercises and final project.
Read more about assessment criteria at the University of Oulu webpage.
The course utilizes a numerical grading scale 1-5. In the numerical scale zero stands for a fail.
|Working life cooperation
The course may include the invited guest lectures from industry and other top universities.