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

Author

Akusok, Anton ; Bjork, Kaj-Mikael ; Miche, Yoan ; Lendasse, Amaury

Author_Institution

Dept. of Mech. & Ind. Eng., Univ. of Iowa, Iowa City, IA, USA

Volume

3

fYear

2015

fDate

2015

Firstpage

1011

Lastpage

1025

Abstract

This paper presents a complete approach to a successful utilization of a high-performance extreme learning machines (ELMs) Toolbox 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.

Keywords

Big Data; learning (artificial intelligence); linear algebra; Big Data; ELM Toolbox; extreme learning machines; feedforward neural networks; linear algebraic performance; Learning systems; Machine learning; Performance evaluation; Artificial neural networks; Computer applications; Feedforward neural networks; High performance computing Software; Learning systems; Machine learning; Neural networks; Open source software; Performance analysis; Prediction methods; Predictive models; Radial basis function networks; Scientific computing; Supervised learning; Utility programs;

fLanguage

English

Journal_Title

Access, IEEE

Publisher

ieee

ISSN

2169-3536

Type

jour

DOI

10.1109/ACCESS.2015.2450498

Filename

7140733