Efficient probabilistic inference in generic neural networks trained with non-probabilistic feedback

Behavioural tasks often require probability distributions to be inferred about task specific variables. Here, the authors demonstrate that generic neural networks can be trained using a simple error-based learning rule to perform such probabilistic computations efficiently without any need for task...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: A. Emin Orhan, Wei Ji Ma
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2017
Materias:
Q
Acceso en línea:https://doaj.org/article/9eb0080d125246cb88d6ac22181477e7
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares