Neural Networks and Evolution Methods
FSI-VSC-KAcad. year: 2019/2020
The course introduces basic approaches to Soft Computing and classical methods used in the field. Practical use of the methods is demonstrated on solving simple engineering problems.
Learning outcomes of the course unit
Understanding of basic methods of Soft Computing and ability of their implementation.
The knowledge of basic relations of the optimization, statistics, graphs theory and programming.
Recommended optional programme components
Recommended or required reading
Aliev,R.A, Aliev,R.R.: Soft Computing and its Application, World Scientific Publishing Co. Pte. Ltd., 2001, ISBN 981-02-4700-1
Sima,J., Neruda,R.: Theoretical questions of neural networks, MATFYZPRESS, 1996, ISBN 80-85863-18-9
Munakata, T.: Fundamentals of the New Artificial Intelligence, Springer-Verlag New York, Inc., 1998. ISBN 0-387-98302-3
Švarc, I., Matoušek, R., Šeda, M., Vítečková, M.: Automatizace-Automatické řízení, skriptum VUT FSI v Brně, CERM 2011.
Planned learning activities and teaching methods
The course is taught through lectures explaining the basic principles and theory of the discipline. Exercises are focused on practical topics presented in lectures.
Assesment methods and criteria linked to learning outcomes
Course-unit credit requirements: submitting a functional software project which uses implementation of selected AI method. Project is specified in the first seminar. Systematic checks and consultations are performed during the semester. Each student has to get through one test and complete all given tasks. Student can obtain 100 marks, 40 marks during seminars (20 for project and 20 for test; he needs at least 20), 60 marks during exam (he needs at least 30).
Language of instruction
The course objective is to make students familiar with basic resources of Soft Computing, potential and adequacy of their use in engineering problems solving.
Specification of controlled education, way of implementation and compensation for absences
The attendance at lectures is recommended, at seminars it is obligatory. Education runs according to week schedules. The form of compensation of missed seminars is fully in the competence of a tutor.
Type of course unit
Guided consultation in combined form of studies
17 hours, optionally
Teacher / Lecturer
1. Introduction to Machine Learning and Soft Computing in the Context of Artificial Intelligence.
2. Evolutionary algorithms I. (genetic algorithms, evolutionary strategies, differential evolution).
3. Evolutionary algorithms II. (grammatical evolution, genetic programming).
4. Selected optimization metaheuristics (HC, HC12, THC, simulated annealing).
5. SWARM Intelligence (PSO, ACO, SOMA).
6. Architectures and classification of neural networks. Perceptron.
7. Feedforward neural networks, single and multilayer networks. ADALINE. Back Propagation Algorithm. Optimization methods used in ANN design.
8. RBF and RCE neural networks. Topologically organized neural networks (competitive learning, Kohonen maps).
9. Cluster analysis. Task dimension reduction. Principal component analysis. LVQ neural networks, neural networks ART.
10. Associative neural networks (Hopfield, BAM), behavior, state diagram, attractors, learning. and Neocognitron.
11. Deep Neural Network. CNN. Transfer Learning.
12. Spiking neural Network.
13. Case studies. Deterministic chaos and its control.
35 hours, compulsory
Teacher / Lecturer
Seminars related to the lectures in the previous week. Solution Topics:
- Implementation of basic metaheuristics
- solving global optimization problems
- use of global optimization toolbox
- use of deep neural network toolbox
- creation of nonlinear models using neural networks
- deep learning in computer vision for image classification
- detection of objects in Image using Deep Learning (R-CNN)
- Semantic Image Segmentation using Deep Learning (SegNet)
- validation of CNN learning and control of learned networks using deep dream method
eLearning: currently opened course