Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Restricted Boltzmann machine as an aggregation technique for binary descriptors

Sobczak, Szymon orcid logoORCID: 0000-0001-8234-2503, Kapela, Rafal orcid logoORCID: 0000-0002-0624-7608, McGuinness, Kevin orcid logoORCID: 0000-0003-1336-6477, Swietlicka, Aleksandra, Pazderski, Daniel orcid logoORCID: 0000-0002-8732-7350 and O'Connor, Noel E. orcid logoORCID: 0000-0002-4033-9135 (2019) Restricted Boltzmann machine as an aggregation technique for binary descriptors. The Visual Computer, 37 . pp. 423-432. ISSN 0178-2789

Abstract
The article presents a novel approach to the challenge of real-time image classification with deep neural networks. The proposed architecture of the neural network exploits computationally efficient local binary descriptors and uses a Restricted Boltzmann Machine (RBM) as a feature space projection step so that the resulting depth of the deep neural network can be reduced. A Contrastive Divergence procedure is used both for RBM training and for feature projection. The resulting neural networks exhibit performance close to the current state of the art but are characterized by a small model memory footprint (i.e., number of parameters) and extremely efficient computational complexity (i.e, response time). The low number of parameters makes these architectures applicable in embedded systems with limited memory or reduced computational capabilities.
Metadata
Item Type:Article (Published)
Refereed:Yes
Uncontrolled Keywords:Restricted Boltzmann Machine; image local binary descriptors; aggregation techniques of feature vectors
Subjects:Computer Science > Image processing
Computer Science > Machine learning
Computer Science > Digital video
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Research Initiatives and Centres > INSIGHT Centre for Data Analytics
Publisher:Springer Verlag
Official URL:http://dx.doi.org/10.1007/s00371-019-01782-8
Copyright Information:© 2019 Springer
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
Funders:Science Foundation Ireland
ID Code:23983
Deposited On:17 Dec 2019 14:16 by Noel Edward O'connor . Last Modified 13 May 2021 11:43
Documents

Full text available as:

[thumbnail of VISUAL_COMPUTER (1).pdf]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
528kB
Downloads

Downloads

Downloads per month over past year

Archive Staff Only: edit this record