Please use this identifier to cite or link to this item:
Appears in Collections:Computing Science and Mathematics Journal Articles
Peer Review Status: Refereed
Title: Improve deep learning with unsupervised objective
Author(s): Zhang, Shufei
Huang, Kaizhu
Zhang, Rui
Hussain, Amir
Contact Email:
Keywords: Deep learning
Multi-layer perceptron
Unsupervised learning
Issue Date: 2017
Citation: Zhang S, Huang K, Zhang R & Hussain A (2017) Improve deep learning with unsupervised objective. In: Liu D, Xie S, Li Y, Zhao D & El-Alfy E (eds.) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science, 10634. 24th International Conference On Neural Information Processing: ICONIP 2017, Guangzhou, China, 14.11.2017-18.11.2017. Cham, Switzerland: Springer, pp. 720-728.;
Series/Report no.: Lecture Notes in Computer Science, 10634
Abstract: We propose a novel approach capable of embedding the unsupervised objective into hidden layers of the deep neural network (DNN) for preserving important unsupervised information. To this end, we exploit a very simple yet effective unsupervised method, i.e. principal component analysis (PCA), to generate the unsupervised “label" for the latent layers of DNN. Each latent layer of DNN can then be supervised not just by the class label, but also by the unsupervised “label" so that the intrinsic structure information of data can be learned and embedded. Compared with traditional methods which combine supervised and unsupervised learning, our proposed model avoids the needs for layer-wise pre-training and complicated model learning e.g. in deep autoencoder. We show that the resulting model achieves state-of-the-art performance in both face and handwriting data simply with learning of unsupervised “labels".
DOI Link: 10.1007/978-3-319-70087-8_74
Rights: Published in Liu D, Xie S, Li Y, Zhao D, El-Alfy E-SM (ed.) Neural Information Processing. ICONIP 2017, Cham, Switzerland: Springer. Part of the Lecture Notes in Computer Science book series (LNCS, volume 10634). The final publication is available at Springer via

Files in This Item:
File Description SizeFormat 
ShufeiZhang17.pdfFulltext - Accepted Version797.52 kBAdobe PDFView/Open

This item is protected by original copyright

Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

If you believe that any material held in STORRE infringes copyright, please contact providing details and we will remove the Work from public display in STORRE and investigate your claim.