Neurocomputing, Lectures

After passing the course a student is able to understand and utilize basic methods of neurocomputing for various problems and applications.

The course contains background and introductory information for the use of elementary computing elements (nodes) within layers of nodes to build feedforward neural networks to be trained in the supervised way. It also presents the method of self-organizing map based on unsupervised learning and Boltzmann machine, and gives a brief introduction to deep learning.

Alternative learning events among themselves

Exercise:

04.11.2021 08:00 - 10:00
11.11.2021 08:00 - 10:00
18.11.2021 08:00 - 10:00
25.11.2021 08:00 - 10:00
02.12.2021 08:00 - 10:00

Lecture:

26.10.2021 10:00 - 12:00
27.10.2021 10:00 - 12:00
02.11.2021 10:00 - 12:00
03.11.2021 10:00 - 12:00
09.11.2021 10:00 - 12:00
10.11.2021 10:00 - 12:00
16.11.2021 10:00 - 12:00
17.11.2021 10:00 - 12:00
23.11.2021 10:00 - 12:00
24.11.2021 10:00 - 12:00
30.11.2021 10:00 - 12:00
01.12.2021 10:00 - 12:00

Prerequisites

Data structures, basic programming skills and basic studies in mathematics (vector and matrix) and statistics

Recommended Prerequisites

• Data Structures, TIETA6, 10 cr

Jeff Heaton, Artificial Intelligence for Humans, Volume 3:
Deep Learning and Neural Networks, Heaton Research, Inc., USA,
2015

I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, The
MIT Press, 2016

M.T. Hagan, H.B. Demuth, M.H. Beale and O. De
Jesus, Neural Network Design, 2nd ed., 2016

R. Beale and T. Jackson, Neural Computing, IOP Publishing, 1997

L. Fu, Neural Networks in Computer Intelligence, 1994

General scale, 0-5