Детальная информация

Название: Connectionist symbol processing. — 1st MIT Press ed.
Другие авторы: Hinton Geoffrey
Организация: IEEE Xplore (Online Service); MIT Press
Выходные сведения: Cambridge, Massachusetts London, England: MIT Press: A Bradford book, 1991
Коллекция: Электронные книги зарубежных издательств; Общая коллекция
Тематика: Нейронные сети; MIT Press eBooks Library
УДК: 004.032.26
Тип документа: Другой
Тип файла: Другой
Язык: Английский
Права доступа: Доступ по паролю из сети Интернет (чтение, печать)
Ключ записи: 6267281

Разрешенные действия: Посмотреть

Аннотация

The six contributions in Connectionist Symbol Processing address the current tension within the artificial intelligence community between advocates of powerful symbolic representations that lack efficient learning procedures and advocates of relatively simple learning procedures that lack the ability to represent complex structures effectively. The authors seek to extend the representational power of connectionist networks without abandoning the automatic learning that makes these networks interesting.Aware of the huge gap that needs to be bridged, the authors intend their contributions to be viewed as exploratory steps in the direction of greater representational power for neural networks. If successful, this research could make it possible to combine robust general purpose learning procedures and inherent representations of artificial intelligence -- a synthesis that could lead to new insights into both representation and learning.

Статистика использования

stat Количество обращений: 25
За последние 30 дней: 2
Подробная статистика