|
1 |
Course topic |
Neural networks and genetic algorithms |
|
2 |
Specialty |
1-31 03 09 Computer mathematics and systems analysis |
|
3 |
Year of study |
3 |
|
4 |
Academic semester |
5 |
|
5 |
Study credits |
2 |
|
6 |
Lecturer |
Goloubeva Larissa L., Ph.D., Associate Professor |
|
7 |
Course purposes |
Increase the level of professional competence and the formation of the student together with competencies, knowledge, skills and skills to solve problems of classical and modern natural science. As a result of the training, the student must know: – principles of the device and operation of neural networks; basic methods of training neural networks; principles of constructing genetic algorithms; basic concepts of the theory of machine learning; be able to: – use modern methods of computer modeling for the study of information systems; – design, train and use neural networks to solve practical problems; – use genetic algorithms to solve practical problems; – make assessments and compare the quality of training and the functioning of various models built on the basis of artificial neural networks and genetic algorithms; – independently expand computer mathematical knowledge with their further use in the construction and analysis of mathematical and computer models of a wide range of theoretical and applied problems. |
|
8 |
Prerequisite(s) |
Courses of disciplines “Algebra and Number Theory”, “Geometry”, “Programming Methods and Informatics”, “Differential Equations”, “Computer Mathematics”, “Neural networks and genetic algorithms” for the 4th semester. |
|
9 |
Course overview |
Artificial neural networks, basic concepts and definitions. Neural Network Toolbox MATLAB. The tools of MATLAB modeling the INS. Neural network of a general user (network). Introduction to Machine Learning. Perceptron and classification problems. Approximation of functions. Pattern recognition. Cluster analysis. |
|
10 |
Recommended literature |
1. Хайкин, С. Нейронные сети: Полный курс, 2-е издание. М., «Вильямс», 2006. 1104 с. 2. Haykin, S. Neural Networks and Learning Machines Third Edition. Copyright © 2009 by Pearson Education, Inc., Upper Saddle River, New Jersey 07458, 2009. 938 p. 3. Вороновский, Г.К. Генетические алгоритмы, Искусственные нейронные сети и Проблемы виртуальной реальности / Г.К. Вороновский, К.В. Махотило, С.Н. Петрашев, С.А. Cepгeeв. Харьков: «Основа», 1997. 107 с. 4. Померанцев, А. Метод Главных Компонент (PCA) – http://www.chemometrics.ru/materials/textbooks/pca.htm, 2009 5. Голубева, Л. Л. Компьютерная математика. Числовой пакет MATLAB: курс лекций / Л. Л. Голубева, А. Э. Малевич, Н. Л. Щеглова. Минск: БГУ, 2007. 164 с. 6. Голубева, Л. Л. Компьютерная математика. Числовой пакет MATLAB: лабораторный практикум / Л. Л. Голубева, А. Э. Малевич, Н. Л. Щеглова. Минск: БГУ, 2008. 171 с. 7. Голубева, Л. Л. Компьютерная математика. Пакет имитационного моделирования Simulink: лабораторный практикум / Л. Л. Голубева, А. Э. Малевич, Н. Л. Щеглова. Минск: БГУ, 2010. 151 с.: ил. 8. Beale, M.D. Neural Network Toolbox™. Getting Started Guide / M.D. Beale, M.T. Hagan, H.D. Demuth. © COPYRIGHT 1992–2017 by The MathWorks, Inc., 2017. 134 p. 9. Beale, M.D. Neural Network Toolbox™. User’s Guide / M.D. Beale, M.T. Hagan, H.D. Demuth. © COPYRIGHT 1992–2017 by The MathWorks, Inc., 2017. 512 p. 10. Воронцов К.В. Машинное обучение. Курс лекций. http://www.MachineLearning.ru/wiki 11. Воронцов К.В. Машинное обучение. Видеолекции. http://shad.yandex.ru/lectures, https://www.youtube.com |
|
11 |
Teaching methods |
Mixed with elements of distance learning, electronic materials. Explanatory-illustrative, reproductive, partially-search. |
|
12 |
Language |
Russian |
|
13 |
Forms of knowledge monitoring |
Laboratory works, homework assignments, oral surveys, short class tests, test papers. |
|
14 |
The knowledge check |
Credit |