Efficient Parallel Implementation for Single Block Orthogonal Dictionary Learning
Department of Automatic Control and Computers, University Politehnica of Bucharest, 313 Spl. Independentei, 060042 Bucharest, Romania
J. Computational and Applied Mathematics, vol.292, pp.513-525, 2016
@article{irofti2016efficient,
title={Efficient Parallel Implementation for Single Block Orthogonal Dictionary Learning},
author={Irofti, Paul},
year={2016}
}
Dictionary training for sparse representations involves dealing with large chunks of data and complex algorithms that determine time consuming tasks. In this paper we propose an improved parallel version for the single block orthogonal dictionary learning algorithm that reduces the representation error and improves the execution time. Our solution targets OpenCL capable graphical device units and focuses on full resource utilization and efficient memory partitioning.
April 12, 2016 by hgpu
