Parallel Implementation of a Machine Learning Algorithm on GPU

被引：0
作者：
Salvatore Cuomo
Pasquale De Michele
Emanuel Di Nardo
Livia Marcellino
机构：
[1] University of Naples Federico II,Department of Mathematics and Application, Complesso Universitario di Monte Sant’Angelo
[2] University of Naples Parthenope,Department of Science and Technology, Centro Direzionale Isola C4
来源：
International Journal of Parallel Programming | 2018年 / 46卷
关键词：
Machine learning; Fast data analysis and retrieval; Self-organization map; GP-GPU;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
The capability for understanding data passes through the ability of producing an effective and fast classification of the information in a time frame that allows to keep and preserve the value of the information itself and its potential. Machine learning explores the study and construction of algorithms that can learn from and make predictions on data. A powerful tool is provided by self-organizing maps (SOM). The goal of learning in the self-organizing map is to cause different parts of the network to respond similarly to certain input patterns. Because of its time complexity, often using this method is a critical challenge. In this paper we propose a parallel implementation for the SOM algorithm, using parallel processor architecture, as modern graphics processing units by CUDA. Experimental results show improvements in terms of execution time, with a promising speed up, compared to the CPU version and the widely used package SOM_PAK.
引用
收藏
页码：923 / 942
页数：19
相关论文
共 86 条
  • [11] Schuffels C(1990)Variants of self-organizing maps Trans. Neural Netw. 1 93-1480
  • [12] Orwig R(1982)Self-organized formation of topologically correct feature maps Biol. Cybern. 43 5969-6
  • [13] Cuomo Salvatore(1990)The self-organizing map Proc. IEEE 78 1464-952
  • [14] Galletti Ardelio(1998)The self-organizing map Neurocomputing 21 1-1384
  • [15] Giunta Giulio(2002)How to make large self-organizing maps for nonvectorial data Neural Netw. 15 945-585
  • [16] Marcellino Livia(1996)Engineering applications of the self-organizing map Proc. IEEE 84 1358-113
  • [17] Cuomo S(2000)Self organization of a massive document collection Trans. Neural Netw. 11 574-7
  • [18] Galletti A(2007)A survey of general-purpose computation on graphics hardware Comput. Graph. Forum 26 80-1159
  • [19] Giunta G(2015)Extending parallelization of the self-organizing map by combining data and network partitioned methods Adv. Eng. Softw. 88 1-1242
  • [20] Marcellino L(2016)High performance GPU based optimized feature matching for computer vision applications Optik Int. J. Light Electron Opt. 127 1153-786
123456789