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

HP-ELM toolbox trains ELMs fast on any hardware, with GPU acceleration for extremely large models.

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.

This paper appears in: Access, IEEE, Issue Date: 2015, Written by: Akusok, A.; Bjork, K.-M.; Miche, Y.; 

Download PDF

Created at: 2016-03-29 22:41:00

Did you know?


The sinking ship’s distress calls were not received by ham radio operators in the United States, as is commonly believed, because the Titanic’s transmitter range did not extend that far. What ham radio operators did pick up was the radio traffic relayed from ship to ship, and from ship-to-shore stations.