8 February 2017 Optimization of deep learning algorithms for object classification
Author Affiliations +
Proceedings Volume 10225, Eighth International Conference on Graphic and Image Processing (ICGIP 2016); 102252K (2017) https://doi.org/10.1117/12.2266403
Event: Eighth International Conference on Graphic and Image Processing, 2016, Tokyo, Japan
Abstract
Deep learning is currently the state of the art algorithm for image classification. The complexity of these feedforward neural networks have overcome a critical point, resulting algorithmic breakthroughs in various fields. On the other hand their complexity makes them executable in tasks, where High-throughput computing powers are available. The optimization of these networks -considering computational complexity and applicability on embedded systems- has not yet been studied and investigated in details. In this paper I show some examples how this algorithms can be optimized and accelerated on embedded systems.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
András Horváth, "Optimization of deep learning algorithms for object classification", Proc. SPIE 10225, Eighth International Conference on Graphic and Image Processing (ICGIP 2016), 102252K (8 February 2017); doi: 10.1117/12.2266403; https://doi.org/10.1117/12.2266403
PROCEEDINGS
5 PAGES


SHARE
Back to Top