Добавить в закладки
Наш форум
Правила Litmy.ru
Мы в Вконтакте
Подписка на RSS
Для правообладателей
Поиск книг:
Разделы сайта
Авторизация
Регистрация



Реклама



Название: Learning Deep Architectures for AI
Автор: Yoshua Bengio
Издательство: Now
Год: 2010
Формат: pdf
Страниц: 130
Размер: 1 mb.
Язык: English

Theoretical results suggest that in order to learn the kind of complicated functions that can represent high-level abstractions (e.g., in vision, language, and other AI-level tasks), one may need deep architectures. Deep architectures are composed of multiple levels of non-linear operations, such as in neural nets with many hidden layers or in complicated propositional formulae re-using many sub-formulae. Searching the parameter space of deep architectures is a difficult task, but learning algorithms such as those for Deep Belief Networks have recently been proposed to tackle this problem with notable success, beating the stateof-the-art in certain areas. This monograph discusses the motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer models such as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks.


Автор: Semka 16-01-2019, 21:44 | Напечатать
 
Уважаемый посетитель, Вы зашли на сайт как незарегистрированный пользователь.




 Litmy.ru  ©2020-2023     При использовании материалов библиотеки обязательна обратная активная ссылка    Политика конфиденциальности