Neural Networks 1

Garant předmětu:

Lecturer:

Zuzana Petříčková

Tutor:

Zuzana Petříčková

Supervisor:

Department of Software Engineering

Synopsis:

The aim of the course „Neural Networks 1“ is to acquaint students with basic models of artificial neural networks, algorithms for their learning, and other related machine learning techniques. The goal is to teach students how to apply these models and methods to solve practical tasks.

Requirements:

Basic knowledge of algebra, calculus and programming techniques.

Syllabus of lectures:

1. Introduction to Artificial Neural Networks:

History, biological motivation, learning, and machine learning.

2. Basic Concepts:

Formal model of a neuron, basic types, and topologies of neural networks.

3. Perceptron:

Description of the model, learning algorithms, threshold circuit, and implementation of logical functions.

4. Linear Neuron:

Model description, learning algorithms, linear neural network, relationship with linear regression, linear classification.

5. Support Vector Machine:

6. Feedforward Neural Network:

Model description, activation functions, types of tasks, training data.

7. Backpropagation Algorithm:

Derivation of the algorithm, variants, analysis, practical applications.

8. Associative Networks:

Models of associative networks (AM, BAM, Hopfield, simulated annealing, Boltzmann machine), Hebbian learning, practical examples.

9. Clustering Analysis:

K-means algorithm, hierarchical clustering, meanshift.

10. Self-Organizing Artificial Neural Networks:

Competitive models, Kohonen maps, learning algorithms.

11. Hybrid Models:

LVQ, Counter-propagation, RBF model, cascade correlation, and modular neural networks.

12. Introduction to Deep Neural Networks:

13. Convolutional Neural Networks:

Architecture, activation functions, learning, practical examples.

Syllabus of tutorials:

The syllabus corresponds to the structure of the lectures.

Study Objective:

Students shall learn various fundamental models of artificial neural networks, algorithms for their learning, and other related machine learning methods (perceptrons, linear models, support vector machines, feed-forward neural networks, clustering, self-organizing neural networks, associative networks, basics of deep learning).

They will learn how to implement and apply the discussed models and methods to solve practical tasks.

Study materials:

Recommended literature:

[1] M. Šnorek: Neuronové sítě a neuropočítače, ČVUT, Praha, 2002.

[2] E. Volná, Neuronové sítě 1, Ostrava, 2008 

[3] J. Šíma, R. Neruda: Teoretické otázky neuronových sítí, Matfyzpress, Praha, 1996.

[4] S. Haykin: Neural Networks, Macmillan, New York, 1994.

[5] L.V. Fausett: Fundamentals of Neural Networks: Architectures, Algorithms and Applications, Prentice Hall, New Jersey, 1994.

[6] I. Goodfellow, Y. Bengio, A. Courville: Deep Learning, MIT Press, 2016.

[7] R. Rojas: Neural Networks: A Systematic Introduction, Springer-Verlag, Berlin, 1996

Note:

Time-table for winter semester 2023/2024:

Time-table is not available yet

Time-table for summer semester 2023/2024:

Time-table is not available yet

The course is a part of the following study plans: