Course objectives:
|
The goal of the course is to familiarise students with basic types of artificial neural networks and their learning, and with the fundamentals of evolutionary techniques.
|
Requirements on student
|
Credit: independent solution of the assigned task in the field of neural networks and evolutionary techniques
Exam: adequate knowledge of the lectured and practiced material
|
Content
|
1. Biological foundation of neural networks, models of neuron.
2. Models of neural networks, principles of learning of neural networks.
3. Multilayered perceptrons.
4. Algorithm of backpropagation.
5. Hopfield network.
6. Kohonen network.
7. Simulated annealing.
8.-9. Genetic algorithms.
10. Evolutional strategies.
11. Evolutional algorithms.
12.-13. Practical examples of the application of neural networks and evolutional strategies.
|
Activities
|
|
Fields of study
|
|
Guarantors and lecturers
|
|
Literature
|
|
Time requirements
|
All forms of study
|
Activities
|
Time requirements for activity [h]
|
Practical training (number of hours)
|
26
|
Preparation for an examination (30-60)
|
51
|
Undergraduate study programme term essay (20-40)
|
40
|
Contact hours
|
39
|
Total
|
156
|
|
Prerequisites
|
Knowledge - students are expected to possess the following knowledge before the course commences to finish it successfully: |
utilize the knowledge from mathematical analysis and linear algebra |
Skills - students are expected to possess the following skills before the course commences to finish it successfully: |
apply the knowledge from mathematical analysis and linear algebra |
Competences - students are expected to possess the following competences before the course commences to finish it successfully: |
N/A |
N/A |
|
Learning outcomes
|
Knowledge - knowledge resulting from the course: |
explain the operation of the basic types of artificial neural networks
explain the principle of evolutional techniques and genetic algorithms
explain the results obtained by artificial neural networks and genetic algorithms in specific tasks
justify the appropriateness of the application of a specific artificial neural network for solving a specific practical task |
Skills - skills resulting from the course: |
analyze the operation of the basic types of artificial neural networks
apply evolutional techniques and genetic algorithms for solving real tasks
apply a suitable type of artificial neural network for solving a specific practical task
evaluate and analyze the results obtained by artificial neural networks and genetic algorithms in specific tasks |
Competences - competences resulting from the course: |
N/A |
|
Assessment methods
|
Knowledge - knowledge achieved by taking this course are verified by the following means: |
Combined exam |
Seminar work |
Skills - skills achieved by taking this course are verified by the following means: |
Skills demonstration during practicum |
Combined exam |
Seminar work |
Competences - competence achieved by taking this course are verified by the following means: |
Skills demonstration during practicum |
Combined exam |
Seminar work |
|
Teaching methods
|
Knowledge - the following training methods are used to achieve the required knowledge: |
Lecture |
Practicum |
Lecture with visual aids |
Self-study of literature |
Individual study |
Skills - the following training methods are used to achieve the required skills: |
Lecture |
Practicum |
Lecture with visual aids |
Task-based study method |
Competences - the following training methods are used to achieve the required competences: |
Lecture |
Practicum |
Lecture with visual aids |
Individual study |
|