DEVDAN: Deep evolving denoising autoencoder

The Denoising Autoencoder (DAE) enhances the flexibility of data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves in-depth study because it characterizes a fixed network capacity which cannot adapt to rapidly changing environments....

Full description

Bibliographic Details

Published in:	Neurocomputing (Amsterdam) Vol. 390; pp. 297 - 314
Main Authors:	Ashfahani, Andri, Pratama, Mahardhika, Lughofer, Edwin, Ong, Yew-Soon
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 21.05.2020
Subjects:	Data streams Denoising autoencoder Incremental learning Denoising autoencoder Incremental learning Data streams
ISSN:	0925-2312, 1872-8286
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!