Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/66787
Title: HSAE : a hessian regularized sparse auto-encoders
Authors: Liu, WF
Ma, TZ
Tao, DP
You, JN 
Keywords: Hessian regularization
Sparse representation
Auto-encoder
Manifold
Issue Date: 2016
Publisher: Elsevier
Source: Neurocomputing, 26 Apr. 2016, v. 187, p. 59-65 How to cite?
Journal: Neurocomputing 
Abstract: Auto-encoders are one kinds of promising non-probabilistic representation learning paradigms that can efficiently learn stable deterministic features. Recently, auto-encoder algorithms are drawing more and more attentions because of its attractive performance in learning insensitive representation with respect to data changes. The most representative auto-encoder algorithms are the regularized auto-encoders including contractive auto-encoder, denoising auto-encoders, and sparse auto-encoders. In this paper, we incorporate both Hessian regularization and sparsity constraints into auto-encoders and then propose a new auto-encoder algorithm called Hessian regularized sparse auto-encoders (HSAE). The advantages of the proposed HSAE lie in two folds: (1) it employs Hessian regularization to well preserve local geometry for data points; (2) it also efficiently extracts the hidden structure in the data by using sparsity constraints. Finally, we stack the single-layer auto-encoders and form a deep architecture of HSAE. To evaluate the effectiveness, we construct extensive experiments on the popular datasets including MNIST and CIFAR-10 dataset and compare the proposed HSAE with the basic auto-encoders, sparse auto encoders, Laplacian auto-encoders and Hessian auto-encoders. The experimental results demonstrate that HSAE outperforms the related baseline algorithms.
URI: http://hdl.handle.net/10397/66787
ISSN: 0925-2312
EISSN: 1872-8286
DOI: 10.1016/j.neucom.2015.07.119
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

6
Last Week
0
Last month
Citations as of Feb 12, 2018

WEB OF SCIENCETM
Citations

6
Last Week
0
Last month
Citations as of Feb 21, 2018

Page view(s)

46
Last Week
1
Last month
Citations as of Feb 25, 2018

Google ScholarTM

Check

Altmetric


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