DensePILAE: a feature reuse pseudoinverse learning algorithm for deep stacked autoencoder

Autoencoder has been widely used as a feature learning technique. In many works of autoencoder, the features of the original input are usually extracted layer by layer using multi-layer nonlinear mapping, and only the features of the last layer are used for classification or regression. Therefore, t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Complex & intelligent systems Jg. 8; H. 3; S. 2039 - 2049
Hauptverfasser: Wang, Jue, Guo, Ping, Li, Yanjun
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Cham Springer International Publishing 01.06.2022
Springer Nature B.V
Schlagworte:
Algorithms
Complexity
Computational Intelligence
Cost analysis
Data Structures and Information Theory
Deep learning
Engineering
Exact solutions
Feature extraction
Intelligent systems
Internet of Things
Machine learning
Multilayers
Neural networks
Original Article
Teaching methods
Pseudoinverse learning
Dense connection
Feature reuse
Pseudoinverse learning autoencoder
ISSN:2199-4536, 2198-6053
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Autoencoder has been widely used as a feature learning technique. In many works of autoencoder, the features of the original input are usually extracted layer by layer using multi-layer nonlinear mapping, and only the features of the last layer are used for classification or regression. Therefore, the features of the previous layer aren’t used explicitly. The loss of information and waste of computation is obvious. In addition, faster training and reasoning speed is generally required in the Internet of Things applications. But the stacked autoencoders model is usually trained by the BP algorithm, which has the problem of slow convergence. To solve the above two problems, the paper proposes a dense connection pseudoinverse learning autoencoder (DensePILAE) from reuse perspective. Pseudoinverse learning autoencoder (PILAE) can extract features in the form of analytic solution, without multiple iterations. Therefore, the time cost can be greatly reduced. At the same time, the features of all the previous layers in stacked PILAE are combined as the input of next layer. In this way, the information of all the previous layers not only has no loss, but also can be strengthened and refined, so that better features could be learned. The experimental results in 8 data sets of different domains show that the proposed DensePILAE is effective.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2199-4536
2198-6053
DOI:10.1007/s40747-021-00516-5