Restricted Boltzmann machine as an aggregation technique for binary descriptors
| Autor: | Szymon Sobczak, Aleksandra Swietlicka, Noel E. O'Connor, Kevin McGuinness, Dariusz Pazderski, Rafal Kapela |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Restricted Boltzmann machine
Computational complexity theory Artificial neural network Contextual image classification Computer science Feature vector Digital video Computer Graphics and Computer-Aided Design Restricted Boltzmann Machine image local binary descriptors aggregation techniques of feature vectors Image processing Feature (computer vision) Machine learning Memory footprint Computer Vision and Pattern Recognition Projection (set theory) Algorithm Software |
| Zdroj: | Sobczak, Szymon ORCID: 0000-0001-8234-2503 |
| ISSN: | 1432-2315 0178-2789 |
| DOI: | 10.1007/s00371-019-01782-8 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink