Somoclu: An Efficient Parallel Library for Self-Organizing Maps

Somoclu is a massively parallel tool for training self-organizing maps on large data sets written in C++. It builds on OpenMP for multicore execution, and on MPI for distributing the workload across the nodes in a cluster. It is also able to boost training by using CUDA if graphics processing units...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2017-06
Main Authors: Wittek, Peter, Shi Chao Gao, Lim, Ik Soo, Zhao, Li
Format: Article
Language:English
Subjects:
Data mining
Graphics processing units
Self organizing maps
Training
Vector spaces
Workload
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Somoclu is a massively parallel tool for training self-organizing maps on large data sets written in C++. It builds on OpenMP for multicore execution, and on MPI for distributing the workload across the nodes in a cluster. It is also able to boost training by using CUDA if graphics processing units are available. A sparse kernel is included, which is useful for high-dimensional but sparse data, such as the vector spaces common in text mining workflows. Python, R and MATLAB interfaces facilitate interactive use. Apart from fast execution, memory use is highly optimized, enabling training large emergent maps even on a single computer.
ISSN:2331-8422
DOI:10.48550/arxiv.1305.1422