460-4048/01 – Neural Networks (NS)
Gurantor department | Department of Computer Science | Credits | 4 |
Subject guarantor | prof. Ing. Ivo Vondrák, CSc. | Subject version guarantor | prof. Ing. Ivo Vondrák, CSc. |
Study level | undergraduate or graduate | Requirement | Optional |
Year | 2 | Semester | summer |
| | Study language | Czech |
Year of introduction | 2010/2011 | Year of cancellation | 2014/2015 |
Intended for the faculties | FEI | Intended for study types | Follow-up Master |
Subject aims expressed by acquired skills and competences
The goal of the course Neural networks is to indroduce trends in paradigm of artificial neural networks.
Teaching methods
Lectures
Seminars
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.
Compulsory literature:
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
Recommended literature:
Hecht-Nielsen: Neurocomputing, Addison-Wesley 1989
Way of continuous check of knowledge in the course of semester
Podmínky udělení zápočtu:
Samostatný projekt a aktivita na cvičeních
E-learning
Other requirements
Additional requirements are placed on the student.
Prerequisities
Subject has no prerequisities.
Co-requisities
Subject has no co-requisities.
Subject syllabus:
Neuron models. Neurons of the 1st generation. Neurons of the 2nd generation - Perceptron. Neuron adaptation. Hebb's Algorithm. Widrwo-Hoff learning of linear neuron. Multilayered architectures. Backpropagation and its parametric modification. Implemenation of neuron with interval based excitation. Generalized Backpropagation. Recurrent neural networks. Kohonen learning and Self Organized Maps. Counter-propagation. Hopfield networks. Boltzmann Machine. Bidirectional Associative Memory. Adaptive Resonance Theory. Object-Oriented Design of Neural Networks.
Projects:
Design and implementation of a simple perceptron
Design and implementation of multilayer neural networks
Conditions for subject completion
Conditions for completion are defined only for particular subject version and form of study
Occurrence in study plans
Occurrence in special blocks
Assessment of instruction