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

Saved in:
Bibliographic Details
Main Authors: Ashfahani, Andri, Pratama, Mahardhika, Lughofer, Edwin, Ong, Yew Soon
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2022
Subjects:
Online Access:https://hdl.handle.net/10356/160972
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-160972
record_format dspace
spelling sg-ntu-dr.10356-1609722022-08-10T01:59:53Z DEVDAN: Deep evolving denoising autoencoder Ashfahani, Andri Pratama, Mahardhika Lughofer, Edwin Ong, Yew Soon School of Computer Science and Engineering Engineering::Computer science and engineering Denoising Autoencoder Data Streams 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. Deep evolving denoising autoencoder (DEVDAN), is proposed in this paper. It features an open structure in the generative phase and the discriminative phase where the hidden units can be automatically added and discarded on the fly. The generative phase refines the predictive performance of discriminative model exploiting unlabeled data. Furthermore, DEVDAN is free of the problem-specific threshold and works fully in the single-pass learning fashion. We show that DEVDAN can find competitive network architecture compared with state-of-the-art methods on the classification task using ten prominent datasets simulated under the prequential test-then-train protocol. The third author acknowledges the support by the LCM K2 Cen- ter within the framework of the Austrian COMET-K2 program. 2022-08-10T01:59:53Z 2022-08-10T01:59:53Z 2020 Journal Article Ashfahani, A., Pratama, M., Lughofer, E. & Ong, Y. S. (2020). DEVDAN: Deep evolving denoising autoencoder. Neurocomputing, 390, 297-314. https://dx.doi.org/10.1016/j.neucom.2019.07.106 0925-2312 https://hdl.handle.net/10356/160972 10.1016/j.neucom.2019.07.106 2-s2.0-85073050094 390 297 314 en Neurocomputing © 2019 Elsevier B.V. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Denoising Autoencoder
Data Streams
spellingShingle Engineering::Computer science and engineering
Denoising Autoencoder
Data Streams
Ashfahani, Andri
Pratama, Mahardhika
Lughofer, Edwin
Ong, Yew Soon
DEVDAN: Deep evolving denoising autoencoder
description 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. Deep evolving denoising autoencoder (DEVDAN), is proposed in this paper. It features an open structure in the generative phase and the discriminative phase where the hidden units can be automatically added and discarded on the fly. The generative phase refines the predictive performance of discriminative model exploiting unlabeled data. Furthermore, DEVDAN is free of the problem-specific threshold and works fully in the single-pass learning fashion. We show that DEVDAN can find competitive network architecture compared with state-of-the-art methods on the classification task using ten prominent datasets simulated under the prequential test-then-train protocol.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Ashfahani, Andri
Pratama, Mahardhika
Lughofer, Edwin
Ong, Yew Soon
format Article
author Ashfahani, Andri
Pratama, Mahardhika
Lughofer, Edwin
Ong, Yew Soon
author_sort Ashfahani, Andri
title DEVDAN: Deep evolving denoising autoencoder
title_short DEVDAN: Deep evolving denoising autoencoder
title_full DEVDAN: Deep evolving denoising autoencoder
title_fullStr DEVDAN: Deep evolving denoising autoencoder
title_full_unstemmed DEVDAN: Deep evolving denoising autoencoder
title_sort devdan: deep evolving denoising autoencoder
publishDate 2022
url https://hdl.handle.net/10356/160972
_version_ 1743119553714454528