Survey of Deep and Extreme Learning Machines for Big data Classification

Abstract

Extracting useful information from a large pool of available data, transforming it to an understandable format is a contemporary data mining challenge. Mining big data is a computational process of discovering patterns in large data sets and it involves intersection of artificial intelligence, machine learning, statistics, and database systems. Extreme learning machines based on deep machine learning architecture are a hot research topic in mining big data and promises great accuracy in training and processing them. Hence main purpose of this survey paper is to provide an in-depth analysis of different deep machine learning techniques and extreme learning machines available for performing big data analytics. This paper surveys different deep and extreme learning machine learning architectures available for big data analytics and assesses the advantages and drawbacks of each of these platforms based on various metrics such as learning speed, scalability, Parameters and model size supported, training accuracy and testing time. Some of the critical characteristics described here can potentially aid the readers in making an informed decision about the right choice of learning architecture for big data depending on their computational needs.