
Learning Deep Architectures for AI
Yoshua Bengio
Learning Deep Architectures for AI
Yoshua Bengio
Detalles del libro:
Año: | 2009 |
Editor: | Now |
Páginas: | 130 páginas |
Idioma: | inglés |
Desde: | 05/03/2015 |
Tamaño: | 1.00 MB |
Licencia: | Pendiente de revisión |
Contenido:
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.
Categorías:
Etiquetas:
Cargando comentarios...
Escaneando listas...
El libro en números
posición en categorías
en catálogo desde
05/03/2015puntuación
Nothing yet...votos
Nothing yet...'LIKES' sociales
Nothing yet...Visitas
Descargas
Interés
Segmentación por países
Páginas de entrada
Segmentación por sitios web
evolución
Cargando...