Справка
ЭБС "КОНСУЛЬТАНТ СТУДЕНТА"
Электронная библиотека технического вуза
Все издания
Вход / регистрация
Во весь экран / Свернуть
en
Версия для слабовидящих
Каталог
Все издания
Меню
Искать в книге
К результату поиска
Расширенный поиск
Закладки
На главную
Вход / регистрация
Во весь экран / Свернуть
en
Управление
Мои отчеты
Каталог
Издательства
УГС
Мои списки
Скачать приложение
Neural networks fundamentals in mobile robot control systems
Оборот титула
Оглавление
1. LECTURE: INTRODUCTION TO NEURAL NETWORKS
+
2. LECTURE: BASES OF LEARNING OF NEURAL NETWORKS
+
3. LECTURE: MULTILAYERED FEEDFORWARD STATIC NEURAL NETWORKS
+
4. LECTURE: ADVANCED METHODS FOR LEARNING NEURAL NETWORKS
-
4.1. Different Criteria for Error Measure
4.2. Complexities in Regularization
4.3. Weight Decay Approach
4.4. Weight Elimination Approach
4.5. Chauvin's Penalty Approach
4.6. Network Pruning Through Sensitivity Calculation
4.7. Karnin's Pruning Method
4.8. Optimal Brain Damage
4.9. Calculation of the Hessian Matrix
4.10. Second-order Optimization Learning Algorithms
4.11. Recursive Estimation Learning Algorithms
4.12. Tapped Delay Line Neural Networks
4.13. Applications of TDLNN for Adaptive Control Systems
4.14. Problems
Practical training 7
4.15. Task for practical training 7
4.16. Example of the practical training 7 performing
4.17. Variants
4.18. Requirements to the results representation
BIBLIOGRAPHY
Close Menu
Раздел
4
/
5
Страница
21
/
37
4. LECTURE: ADVANCED METHODS FOR LEARNING NEURAL NETWORKS
/
/
Внимание! Для озвучивания и цитирования книги перейдите в режим постраничного просмотра.
Для продолжения работы требуется
Регистрация
Каталог
Издательства
УГС
Мои списки
Скачать приложение
Neural networks fundamentals in mobile robot control systems
Оглавление
1. LECTURE: INTRODUCTION TO NEURAL NETWORKS
+
2. LECTURE: BASES OF LEARNING OF NEURAL NETWORKS
+
3. LECTURE: MULTILAYERED FEEDFORWARD STATIC NEURAL NETWORKS
+
4. LECTURE: ADVANCED METHODS FOR LEARNING NEURAL NETWORKS
-
4.1. Different Criteria for Error Measure
4.2. Complexities in Regularization
4.3. Weight Decay Approach
4.4. Weight Elimination Approach
4.5. Chauvin's Penalty Approach
4.6. Network Pruning Through Sensitivity Calculation
4.7. Karnin's Pruning Method
4.8. Optimal Brain Damage
4.9. Calculation of the Hessian Matrix
4.10. Second-order Optimization Learning Algorithms
4.11. Recursive Estimation Learning Algorithms
4.12. Tapped Delay Line Neural Networks
4.13. Applications of TDLNN for Adaptive Control Systems
4.14. Problems
Practical training 7
4.15. Task for practical training 7
4.16. Example of the practical training 7 performing
4.17. Variants
4.18. Requirements to the results representation
BIBLIOGRAPHY
