Extreme Learning Machine: A Review

Feedforward neural networks (FFNN) have been utilised for various research in machine learning and they have gained a significantly wide acceptance. However, it was recently noted that the feedforward neural network has been functioning slower than needed. As a result, it has created critical bottlenecks among its applications. Extreme Learning Machines (ELM) were suggested as alternative learning algorithms instead of FFNN. The former is characterised by single-hidden layer feedforward neural networks (SLFN). It selects hidden nodes randomly and analytically determines their output weight. This review aims to, first, present a short mathematical explanation to explain the basic ELM. Second, because of its notable simplicity, efficiency, and remarkable generalisation performance, ELM has had wide uses in various domains, such as computer vision, biomedical engineering, control and robotics, system identification, etc. Thus, in this review, we will aim to present a complete view of these ELM advances for different applications. Finally, ELM’s strengths and weakness will be presented, along with its future perspectives.