TIEP1820 Introduction to the mathematics of artificial intelligence (2 cr)

Study level:
Basic studies
Grading scale:
Pass - fail
Responsible organisation:
Faculty of Information Technology
Curriculum periods:
2017-2018, 2018-2019, 2019-2020



The course contains basic facts about machine learning, especially about artificial neural networks. We study the structure, the parameters, the activation functions and error functions used in neural networks and the mathematics behind them. The choice of the parameters and functions and the minimization of the error during the learning phase of the network is based on differential calculus and linear algebra. We learn the basic things about differential calculus and linear algebra.

Learning outcomes

After the course the student

* knows the structure of the artificial neural network, the parameters and the activation functions and knows how the neural network learnst

* knows the basic things about linear algebra (for example matrix operations, eigenvalues)

* knows the basic things of differential calculus: derivatives and partial derivatives, the geometric interpretation of partial derivatives and gradient, extreme values using the gradient

Description of prerequisites

High school mathematics.

Completion methods

Method 1

Select all marked parts
Parts of the completion methods

Teaching (2 cr)

Participation in teaching
Grading scale:
Pass - fail
No published teaching