Complete Stacked Denoising Auto-Encoders for Regression

Complete modified stacked denoising auto-encoder (CMSDAE) machines constitute a version of stacked auto-encoders in which a target estimate is included at the input, and are trained layer-by-layer by minimizing a convex combination of the errors corresponding to the input sample and the target. This...

Full description

Saved in:
Bibliographic Details
Published in:Neural processing letters Vol. 53; no. 1; pp. 787 - 797
Main Authors: Fernández-García, María-Elena, Sancho-Gómez, José-Luis, Ros-Ros, Antonio, Figueiras-Vidal, Aníbal R.
Format: Journal Article
Language:English
Published: New York Springer US 01.02.2021
Springer Nature B.V
Subjects:
Algorithms
Artificial Intelligence
Coders
Complex Systems
Computational Intelligence
Computer Science
Concrete
Datasets
Experiments
Noise reduction
Regression
Time series
Variables
Regression
Complete auto-encoders
Neural networks
Denoising
ISSN:1370-4621, 1573-773X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Complete modified stacked denoising auto-encoder (CMSDAE) machines constitute a version of stacked auto-encoders in which a target estimate is included at the input, and are trained layer-by-layer by minimizing a convex combination of the errors corresponding to the input sample and the target. This permits to carry out the transformation of the observation space without forgetting what the target is. It has been shown in recent publications that this method produces a clear performance advantage in classification tasks. The above facts motivate to explore whether CMSDAE machines also offer performance improvements in regression problems, and in particular for time series prediction where conventional discriminative machines find difficulties: The layer-by-layer reconstruction of the target (together with the input) can help to reduce these difficulties. This contribution presents the CMSDAE regression/prediction machines and their design, showing experimental evidence of their frequent superior performance —never lower— with respect to other machine architectures. Some subsequent research directions are indicated together with the conclusions.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1370-4621
1573-773X
DOI:10.1007/s11063-020-10419-0