Справка
STUDENT'S CONSULTANT
Электронная библиотека технического вуза
Все издания
Login/Registration
Во весь экран / Свернуть
ru
Accessibility
General Catalogue
Все издания
Menu
Искать в книге
К результату поиска
Advanced search
Bookmarks
Homepage
Login/Registration
Во весь экран / Свернуть
ru
Управление
My reports
General Catalogue
Издательства
УГС
Мои списки
Download app
Neural networks fundamentals in mobile robot control systems
Оборот титула
Table of contents
1. LECTURE: INTRODUCTION TO NEURAL NETWORKS
+
2. LECTURE: BASES OF LEARNING OF NEURAL NETWORKS
+
3. LECTURE: MULTILAYERED FEEDFORWARD STATIC NEURAL NETWORKS
-
3.1. Two layered neural network mathematical description
3.2. Generalized delta rule
3.3. Network with linear output neurons
3.4. Structure of a multi-layered feedforward neural network
3.5. Description of a multi-layered feedforward neural network
3.6. Generalized Delta Rule for MFNN
3.7. Recursive computation of delta
3.8. Momentum BP algorithm
3.9. A Summary of BP learning algorithm
3.10. Some issues in BP learning algorithm
3.11. Local minimum problem
3.12. Problems
Practical training 5
3.13. Task for practical training 5
3.14. Example of the practical training 5 performing
3.15. Variants
3.16. Requirements to the results representation
Practical training 6
3.17 Task for practical training 6
3.18. Example of the practical training 6 performing
3.19. Variants
3.20. Requirements to the results representation
4. LECTURE: ADVANCED METHODS FOR LEARNING NEURAL NETWORKS
+
BIBLIOGRAPHY
Close Menu
Раздел
3
/
5
Страница
1
/
48
3. LECTURE: MULTILAYERED FEEDFORWARD STATIC NEURAL NETWORKS
/
/
Внимание! Для озвучивания и цитирования книги перейдите в режим постраничного просмотра.
Для продолжения работы требуется
Registration
General Catalogue
Издательства
УГС
Мои списки
Скачать приложение
Neural networks fundamentals in mobile robot control systems
Table of contents
1. LECTURE: INTRODUCTION TO NEURAL NETWORKS
+
2. LECTURE: BASES OF LEARNING OF NEURAL NETWORKS
+
3. LECTURE: MULTILAYERED FEEDFORWARD STATIC NEURAL NETWORKS
-
3.1. Two layered neural network mathematical description
3.2. Generalized delta rule
3.3. Network with linear output neurons
3.4. Structure of a multi-layered feedforward neural network
3.5. Description of a multi-layered feedforward neural network
3.6. Generalized Delta Rule for MFNN
3.7. Recursive computation of delta
3.8. Momentum BP algorithm
3.9. A Summary of BP learning algorithm
3.10. Some issues in BP learning algorithm
3.11. Local minimum problem
3.12. Problems
Practical training 5
3.13. Task for practical training 5
3.14. Example of the practical training 5 performing
3.15. Variants
3.16. Requirements to the results representation
Practical training 6
3.17 Task for practical training 6
3.18. Example of the practical training 6 performing
3.19. Variants
3.20. Requirements to the results representation
4. LECTURE: ADVANCED METHODS FOR LEARNING NEURAL NETWORKS
+
BIBLIOGRAPHY
