High-Performance Extreme Learning Machines: A Complete Toolbox for Big Data Applications

被引：190

作者：

Akusok, Anton ^{[1
,2
]}

Bjork, Kaj-Mikael ^{[3
]}

Miche, Yoan ^{[4
]}

Lendasse, Amaury ^{[1
,2
]}

机构：

[1] Univ Iowa, Dept Mech & Ind Engn, Iowa City, IA 52242 USA

[2] Univ Iowa, Iowa Informat Initiat, Iowa City, IA 52242 USA

[3] Arcada Univ Appl Sci, Dept Business Management & Analyt, Helsinki 00550, Finland

[4] Nokia Solut & Networks Grp, Espoo 02022, Finland

来源：

IEEE ACCESS | 2015年 / 3卷

关键词：

Learning systems; Supervised learning; Machine learning; Prediction methods; Predictive models; Neural networks; Artificial neural networks; Feedforward neural networks; Radial basis function networks; Computer applications; Scientific computing; Performance analysis; High performance computing Software; Open source software; Utility programs; ELM; REGRESSION; CLASSIFICATION; APPROXIMATION; ALGORITHM; NETWORKS; ONLINE;

D O I：

10.1109/ACCESS.2015.2450498

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

080201 [机械制造及其自动化];

摘要：

This paper presents a complete approach to a successful utilization of a high-performance extreme learning machines (ELMs) Toolbox(1) for Big Data. It summarizes recent advantages in algorithmic performance; gives a fresh view on the ELM solution in relation to the traditional linear algebraic performance; and reaps the latest software and hardware performance achievements. The results are applicable to a wide range of machine learning problems and thus provide a solid ground for tackling numerous Big Data challenges. The included toolbox is targeted at enabling the full potential of ELMs to the widest range of users.

引用

页码：1011 / 1025

页数：15

共 43 条

[1]

Arbitrary Category Classification of Websites Based on Image Content [J].