Back to Search
Start Over
DEVDAN: Deep evolving denoising autoencoder
- Source :
- Neurocomputing. 390:297-314
- Publication Year :
- 2020
- Publisher :
- Elsevier BV, 2020.
-
Abstract
- The Denoising Autoencoder (DAE) enhances the flexibility of the data stream method in exploiting unlabeled samples. Nonetheless, the feasibility of DAE for data stream analytic deserves an in-depth study because it characterizes a fixed network capacity that 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 the 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.<br />This paper has been accepted for publication in Neurocomputing 2019. arXiv admin note: substantial text overlap with arXiv:1809.09081
- Subjects :
- FOS: Computer and information sciences
Data stream
Computer Science - Machine Learning
0209 industrial biotechnology
Computer science
Cognitive Neuroscience
data streams
Machine Learning (stat.ML)
02 engineering and technology
Machine Learning (cs.LG)
020901 industrial engineering & automation
Discriminative model
Statistics - Machine Learning
Artificial Intelligence
denoising autoencoder
0202 electrical engineering, electronic engineering, information engineering
Protocol (object-oriented programming)
incremental learning
Flexibility (engineering)
Denoising autoencoder
business.industry
Pattern recognition
Computer Science Applications
Computer science and engineering [Engineering]
020201 artificial intelligence & image processing
Artificial intelligence
business
Subjects
Details
- ISSN :
- 09252312
- Volume :
- 390
- Database :
- OpenAIRE
- Journal :
- Neurocomputing
- Accession number :
- edsair.doi.dedup.....1facc15a65d227441e9b65b6a8414e96