| Course Unit Code | 460-4048/02 |
|---|
| Number of ECTS Credits Allocated | 4 ECTS credits |
|---|
| Type of Course Unit * | Optional |
|---|
| Level of Course Unit * | Second Cycle |
|---|
| Year of Study * | Second Year |
|---|
| Semester when the Course Unit is delivered | Summer Semester |
|---|
| Mode of Delivery | Face-to-face |
|---|
| Language of Instruction | Czech |
|---|
| Prerequisites and Co-Requisites | Course succeeds to compulsory courses of previous semester |
|---|
| Name of Lecturer(s) | Personal ID | Name |
|---|
| JEZ04 | Ing. David Ježek, Ph.D. |
| Summary |
|---|
| The goal of the course is to introduce the paradigm of neural networks. The basic model on neuron is introduced as well as architectures of how the artificial neural networks are composed, adapted and used. The fundamental models like multilayered, self-adapting and recurrent neural networks are described. |
| Learning Outcomes of the Course Unit |
|---|
| The goal of the course Neural networks is to indroduce trends in paradigm of artificial neural networks. |
| Course Contents |
|---|
Lectures:
1. Neuron models. Neurons of the 1st generation. Neurons of the 2nd generation - Perceptron.
2. Neuron adaptation. Hebb's Algorithm. Widrwo-Hoff learning of linear neuron.
3. Multilayered architectures. Backpropagation and its parametric modification.
4. Implemenation of neuron with interval based excitation. Generalized Backpropagation.
5. Recurrent neural networks.
6. Kohonen learning and Self Organized Maps. Counter-propagation.
7. Hopfield networks. Boltzmann Machine. Bidirectional Associative Memory.
8. Využití Hopfieldových sítí v úlohách s omezujícími podmínkami.
9. Adaptive Resonance Theory.
10. Usage of genetic algorithm for neural netwok adaptation. Object-Oriented Design of Neural Networks.
Exercises (PC classroom):
1. Neuron models. Neurons of the 1st generation. Neurons of the 2nd generation - Perceptron.
2. Neuron adaptation. Hebb's Algorithm. Widrwo-Hoff learning of linear neuron.
3. Multilayered architectures. Backpropagation and its parametric modification.
4. Implemenation of neuron with interval based excitation. Generalized Backpropagation.
5. Recurrent neural networks.
6. Kohonen learning and Self Organized Maps. Counter-propagation.
7. Hopfield networks. Boltzmann Machine. Bidirectional Associative Memory.
8. Využití Hopfieldových sítí v úlohách s omezujícími podmínkami.
9. Adaptive Resonance Theory.
10. Usage of genetic algorithm for neural netwok adaptation. Object-Oriented Design of Neural Networks.
|
| Recommended or Required Reading |
|---|
| Required Reading: |
|---|
Mandatory:
1. Hecht-Nielsen: Neurocomputing, Addison-Wesley 1989
2. Wasserman, P.D.: Neural Computing, Theory and Practice. Van Nostrand Reinhold, NY, 1989
Recommended:
3. Rojas, R. Neural Networks: A Systematic Introduction Springer-Verlag New York, Inc., 1996, ISBN: 3-540-60505-3
|
1. Hecht-Nielsen: Neurocomputing, Addison-Wesley 1989
2. Wasserman, P.D.: Neural Computing, Theory and Practice. Van Nostrand Reinhold, NY, 1989
3. Vondrák, I.: Umělá inteligence a neuronové sítě. Skriptum VŠB - TU Ostrava,
1994
|
| Recommended Reading: |
|---|
| Hecht-Nielsen: Neurocomputing, Addison-Wesley 1989 |
Vondrák, I.: Umělá inteligence a neuronové sítě. Skriptum VŠB - TU Ostrava,
1994 |
| Planned learning activities and teaching methods |
|---|
| Lectures, Seminars |
| Assesment methods and criteria |
|---|
| Task Title | Task Type | Maximum Number of Points
(Act. for Subtasks) | Minimum Number of Points for Task Passing |
|---|
| Credit and Examination | Credit and Examination | 100 (100) | 51 |
| Credit | Credit | 40 (40) | 20 |
| Učení Hebbova perceptronu | Other task type | 10 | 5 |
| Učení metodou Backpropagation | Other task type | 30 | 15 |
| Examination | Examination | 60 | 30 |