An Incremental Deep Learning Network for On-line Unsupervised Feature Extraction

被引：3

作者：

Liang, Yu ^{[1
]}

Yang, Yi ^{[1
]}

Shen, Furao ^{[1
]}

Zhao, Jinxi ^{[1
]}

Zhu, Tao ^{[1
]}

机构：

[1] Nanjing Univ, Collaborat Innovat Ctr Novel Software Technol & I, Dept Comp Sci & Technol, Natl Key Lab Novel Software Technol, Nanjing, Peoples R China

来源：

NEURAL INFORMATION PROCESSING (ICONIP 2017), PT II | 2017年 / 10635卷

基金：

美国国家科学基金会;

关键词：

Deep learning; On-line unsupervised feature extraction;

D O I：

10.1007/978-3-319-70096-0_40

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose an incremental deep learning network for on-line unsupervised feature extraction. This deep learning network is based on 3 data processing components: (1) cascaded incremental orthogonal component analysis network (IOCANet); (2) binary hashing; and (3) blockwise histograms. In this architecture, IOCANet can process online data and get filters to do convolutions. Binary hashing is used to enhance the nonlinearity of IOCANet and reduce the quantity of the data. Eventually, the data is encoded by blockwise histograms. Experiments demonstrate that the proposed architecture has potential results for on-line unsupervised feature extraction.

引用

页码：383 / 392

页数：10

共 50 条

[31] Advancement of three chemometric tools: network architecture, unsupervised learning and nonlinear feature extraction
Yu, RQ
Jiang, JH
[J]. CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 1999, 45 (1-2) : 191 - 198
[32] A Perception Evolution Network for Unsupervised Fast Incremental Learning
Xing, Youlu
Shen, Furao
Zhao, Jinxi
[J]. 2013 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2013,
[33] On-line learning in changing environments with applications in supervised and unsupervised learning
Murata, N
Kawanabe, M
Ziehe, A
Müller, KR
Amari, S
[J]. NEURAL NETWORKS, 2002, 15 (4-6) : 743 - 760
[34] Incremental Similarity for real-time on-line incremental learning systems
Reznakova, Marta
Tencer, Lukas
Cheriet, Mohamed
[J]. PATTERN RECOGNITION LETTERS, 2016, 74 : 61 - 67
[35] Network intrusion detection method based on deep learning feature extraction
Song Y.
Hou B.
Cai Z.
[J]. Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition), 2021, 49 (02): : 115 - 120
[36] On-line Learning of Sequence Data Based on Self-Organizing Incremental Neural Network
Okada, Shogo
Hasegawa, Osamu
[J]. 2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, : 3847 - +
[37] FEATURE-EXTRACTION USING AN UNSUPERVISED NEURAL NETWORK
INTRATOR, N
[J]. NEURAL COMPUTATION, 1992, 4 (01) : 98 - 107
[38] Unsupervised High-Level Feature Extraction of SAR Imagery With Structured Sparsity Priors and Incremental Dictionary Learning
Chen, Jiawei
Jiao, Licheng
Ma, Wenping
Liu, Hongying
[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2016, 13 (10) : 1467 - 1471
[39] Power Line Detection Based on Feature Fusion Deep Learning Network
Zou, Kuansheng
Jiang, Zhenbang
Zhao, Shuaiqiang
[J]. ADVANCES IN COMPUTER GRAPHICS, CGI 2022, 2022, 13443 : 527 - 538
[40] An on-line learning mechanism for unsupervised classification and topology representation
Furao, S
Hasegawa, O
[J]. 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, : 651 - 656

← 1 2 3 4 5 →