A review on extreme learning machine

Abstract Extreme learning machine (ELM) is a training algorithm for single hidden layer feedforward neural network (SLFN), which converges much faster than traditional methods and yields promising performance. In this paper, we hope to present comprehensive review on ELM. Firstly, will focus the theoretical analysis including universal approximation theory generalization. Then, various improvements are listed, help ELM works better in terms of stability, efficiency, accuracy. Because its outstanding performance, has been successfully applied many real-time tasks classification, clustering, regression. Besides, report applications medical imaging: MRI, CT, mammogram. The controversies were also discussed paper. We aim these advances find some future perspectives.