Efficient dictionary learning implementation on the GPU using OpenCL
Department of Automatic Control and Computers University Politehnica of Bucharest
University Politechnica of Bucharest Scientific Bulletin, Series C, Vol. 78, Iss. 3, 2016
@article{irofti2015efficient,
title={Efficient dictionary learning implementation on the GPU using OpenCL},
author={Irofti, Paul},
journal={UPB Scientific Bulletin, Series C},
volume={77},
number={3},
pages={1–12},
year={2015}
}
The dictionary learning field offers a wide range of algorithms that are able to provide good sparse approximations and well trained dictionaries. These algorithms are very complex and this is reflected in the slow execution of their computationally intensive implementations. This article proposes efficient parallel implementations for the main algorithms in the field that significantly reduce the execution time.
September 22, 2016 by hgpu
