High-Performance Extreme Learning Machines.pdf

Received June 5, 2015, accepted June 18, 2015, date of publication June 30, 2015, date of current version July 17, 2015. Digital Object Identifier 10.1109/ACCESS.2015.2450498 High-Performance Extreme Learning Machines: A Complete Toolbox for Big Data Applications ANTON AKUSOK1, KAJ-MIKAEL BJ?RK2, YOAN MICHE3, AND AMAURY LENDASSE1 1Department of Mechanical and Industrial Engineering and the Iowa Informatics Initiative, The University of Iowa, Iowa, IA 52242-1527, USA 2Department of Business Management and Analytics, Arcada University of Applied Sciences, Helsinki 00550, Finland 3Nokia Solutions and Networks Group, Espoo 02022, Finland Corresponding author: A. Lendasse (amaury-lendasse@) ABSTRACT This paper presents a complete approach to a successful utilization of a high-performance extreme learning machines (ELMs) Toolbox1 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. INDEX TERMS 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. I. INTRODUCTION Extreme Learning Machines [1]–[4] (ELM) as important emergent machine learning techniques, are proposed for both ‘‘generalized’’ Single-Layer Feed-forward Networks (SLFNs) [1], [3], [5]–[7] and multi layered feedforward networks [6]. Unlike traditional learning theories and learning algorithms, EL