Study unit

Show courses/exams
3621675 Deep Learning, 5-6 Cp 
Code 3621675  Validity 01.01.1950 -
Name Deep Learning  Abbreviation DEL 
Credits5-6 Cp  Date of expiry  
TypeAdvanced Studies Subject0530 Computer Science 
ClassStudy Unit  Hours  
Study right   Grading0-5 
Recommended scheduling 
Organisation Computer Science (J,K) 

Learning outcomes 

Students understand the theory of neural networks, Nature-Inspired Computing (NIC) methods, and deep learning algorithms. Students get familiar with the most popular neural networks models (Perceptron, Adaline, multilayer neural networks, Self-Organizing Map (SOM), etc.) and their learning algorithms (Widrow-Hoff rule, Back-Propagation (BP) training, Back-propagation Through Time (BTT) training, competitive learning, etc.). Students master the essential knowledge of deep learning techniques, such as regularization, momentum, batch normalization, and dropout. Students understand the principles, structures, and algorithms of typical deep learning neural networks, e.g., Convolutional Neural Networks (CNN). Students know how to build up deep learning algorithms from scratch. Students gain the hand-on experiences in using deep learning techniques to deal with practical problems


Elementary concepts and challenges of machine learning. Neural networks models (linear neural networks, feedforward neural networks, recurrent neural networks, Self-Organizing Map (SOM), etc.). Deep reinforcement learning. Concepts and challenges of deep learning. Deep learning models and techniques (deep neural networks, Convolutional Neural Networks (CNN), AutoEncoder, Long Short Term Memory (LSTM), etc.). Applications of deep learning in classification, prediction, pattern recognition, etc.

Modes of study 

Lectures, teaching materials, exercises, and examination

Teaching methods 

distance teaching and study                           

Study materials 

I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2017, A. P. Engelbrecht, Fundamentals of Computational Swarm Intelligence, John Wiley & Sons Ltd, 2005, S. Haykin, Neural Networks, A Comprehensive Foundation, Prentice Hall, 2008, lecture slides and notes, selected papers from journals and conference proceedings

Evaluation criteria 

Grading (80% examination and 20% computer exercises): 0-5


Basic knowledge of linear algebra and probability theory              


Fall semester

Offering data 

This course is open to everyone

Further information 

Teaching language: English


Letter (J, K) in front of the name of the course/exam indicates the campus on which teaching or exam takes place: J = Joensuu, K = Kuopio.

Present and future teaching
No teaching

Future exams
No exams