Entry requirements

The course requires that the students have

previously taken courses on algebra,

computer programming methods and algorithms,

mathematical analysis and linear algebra.

Courses in computer architecture, mathematical

statistics and artificial intelligence are

recommended, but not required.

Aims

The aim of the course is to give a broad overview

of the neural networks field, with an emphasis on

practical problem solving with artificial neural

networks.

Content

The course covers basic neural network

architectures and learning algorithms, for

applications in pattern recognition,

classification, function approximation and

sequential decision problems. Three forms of

learning (supervised, unsupervised and

reinforcement learning) are introduced and

applications of these are discussed. A final

assignment, defined by the students themselves,

gives opportunity to go deeper into a selected

sub-area.

Instruction

Lectures, lab assignments and a final

student-defined assignment.