From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing
In recent studies [1] [2] [3] Recurrent Neural Networks were used for generative processes and their surprising performance can be explained by their ability to create good predictions. In addition, data compression is also based on prediction. What the problem comes down to is whether a data compre...
Guardado en:
| Autores principales: | Laura, Juan Andrés, Masi, Gabriel Omar, Argerich, Luis |
|---|---|
| Formato: | Objeto de conferencia |
| Lenguaje: | Inglés |
| Publicado: |
2017
|
| Materias: | |
| Acceso en línea: | http://sedici.unlp.edu.ar/handle/10915/65946 http://www.clei2017-46jaiio.sadio.org.ar/sites/default/files/Mem/ASAI/asai-10.pdf |
| Aporte de: |
Ejemplares similares
-
Prediction of wavelet transform coefficients using neural networks applied to lossless compression of multispectral images
por: Acevedo, D.G., et al. -
Prediction of wavelet transform coefficients using neural networks applied to lossless compression of multispectral images
por: Acevedo, Daniel G., et al.
Publicado: (2007) -
Extended evaluation of the Volterra-Neural Network for model compression
por: Rubiolo, Mariano
Publicado: (2012) -
Implementation of boolean neural networks on parallel computers
por: Carvalho, Andre Carlos Ponce de Leon Ferreira de, et al.
Publicado: (1996) -
ALENA : Adaptive-Length Evolving Neural Arrays
por: Corbalán, Leonardo César, et al.
Publicado: (2004)