A Reweighted Scheme to Improve the Representation of the Neural Autoregressive Distribution Estimator.
Comput Intell Neurosci
; 2018: 6401645, 2018.
Article
en En
| MEDLINE
| ID: mdl-30675150
ABSTRACT
The neural autoregressive distribution estimator(NADE) is a competitive model for the task of density estimation in the field of machine learning. While NADE mainly focuses on the problem of estimating density, the ability for dealing with other tasks remains to be improved. In this paper, we introduce a simple and efficient reweighted scheme to modify the parameters of the learned NADE. We make use of the structure of NADE, and the weights are derived from the activations in the corresponding hidden layers. The experiments show that the features from unsupervised learning with our reweighted scheme would be more meaningful, and the performance of the initialization for neural networks has a significant improvement as well.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Algoritmos
/
Procesamiento Automatizado de Datos
/
Redes Neurales de la Computación
/
Aprendizaje Automático
Límite:
Humans
Idioma:
En
Revista:
Comput Intell Neurosci
Asunto de la revista:
INFORMATICA MEDICA
/
NEUROLOGIA
Año:
2018
Tipo del documento:
Article
País de afiliación:
China