CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 深度强化学习
A Semi-Supervised Predictive Sparse Decomposition Based on Task-Driven Dictionary Learning
Lv Le1; Zhao Dongbin1,2; Deng QingQiong3
Source PublicationCOGNITIVE COMPUTATION
2017-02
Volume9Issue:1Pages:115-124
AbstractIn feature learning field, many methods are inspired by advances in neuroscience. Among them, neural network and sparse coding have been broadly studied. Predictive sparse decomposition (PSD) is a practical variant of these two methods. It trains a neural network to estimate the sparse codes. After training, the neural network is fine-tuned to achieve higher performance on object recognition tasks. It is widely believed that introducing discriminative information can make the features more useful for classification task. Hence, in this work, we propose applying the task-driven dictionary learning framework to the PSD and demonstrate that this new model can be optimized by the stochastic gradient descent (SGD) algorithm. Before our work, the semi-supervised auto-encoder framework has already been proposed to guide neural network to extract discriminative representations. But it does not improve the classification performance of neural network. In the experiments, we compare the proposed method with the semi-supervised auto-encoder method. The performance of PSD is used as the baseline for these two methods. On the MNIST and USPS datasets, our method can generate more discriminative and predictable sparse codes than other methods. Furthermore, the recognition accuracy of neural network can be improved.
KeywordSemi-supervised Learning Predictive Sparse Decomposition Neural Networks Dictionary Learning
DOI10.1007/s12559-016-9438-0
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/14470
Collection复杂系统管理与控制国家重点实验室_深度强化学习
Affiliation1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
3.Beijing Normal Univ, Coll Informat Sci & Technol, Beijing 100875, Peoples R China
Recommended Citation
GB/T 7714
Lv Le,Zhao Dongbin,Deng QingQiong. A Semi-Supervised Predictive Sparse Decomposition Based on Task-Driven Dictionary Learning[J]. COGNITIVE COMPUTATION,2017,9(1):115-124.
APA Lv Le,Zhao Dongbin,&Deng QingQiong.(2017).A Semi-Supervised Predictive Sparse Decomposition Based on Task-Driven Dictionary Learning.COGNITIVE COMPUTATION,9(1),115-124.
MLA Lv Le,et al."A Semi-Supervised Predictive Sparse Decomposition Based on Task-Driven Dictionary Learning".COGNITIVE COMPUTATION 9.1(2017):115-124.
Files in This Item: Download All
File Name/Size DocType Version Access License
A Semi-Supervised Pr(998KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Lv Le]'s Articles
[Zhao Dongbin]'s Articles
[Deng QingQiong]'s Articles
Baidu academic
Similar articles in Baidu academic
[Lv Le]'s Articles
[Zhao Dongbin]'s Articles
[Deng QingQiong]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Lv Le]'s Articles
[Zhao Dongbin]'s Articles
[Deng QingQiong]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: A Semi-Supervised Predictive Sparse Decomposition Based on Task-Driven Dictionary Learning.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

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