S. Zhang
Improve deep learning with unsupervised objective
Zhang, S.; Huang, K.; Zhang, R.; Hussain, A.
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".
Presentation Conference Type | Edited Proceedings |
---|---|
Conference Name | International Conference on Neural Information Processing |
Start Date | Nov 14, 2017 |
End Date | Nov 18, 2017 |
Online Publication Date | Oct 24, 2017 |
Publication Date | 2017 |
Deposit Date | Sep 20, 2019 |
Publisher | Springer |
Pages | 720-728 |
Series Title | Lecture Notes in Computer Science |
Series Number | 10634 |
Series ISSN | 0302-9743 |
ISBN | 978-3-319-70086-1 |
DOI | https://doi.org/10.1007/978-3-319-70087-8_74 |
Public URL | http://researchrepository.napier.ac.uk/Output/1792525 |
You might also like
Applications of Deep Learning and Reinforcement Learning to Biological Data
(2018)
Journal Article
Guided Policy Search for Sequential Multitask Learning
(2018)
Journal Article
Learning Latent Features With Infinite Nonnegative Binary Matrix Trifactorization
(2018)
Journal Article
Cross-modality interactive attention network for multispectral pedestrian detection
(2018)
Journal Article
Downloadable Citations
About Edinburgh Napier Research Repository
Administrator e-mail: repository@napier.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search