Quick Hidden Layer Size Tuning in ELM for Classification Problems

The extreme learning machine is a fast neural network with outstanding performance. However, the selection of an appropriate number of hidden nodes is time-consuming, because training must be run for several values, and this is unde- sirable for a real-time response. We propose to use moving average, exponential moving average, and divide-and-conquer strategies to reduce the number of training’s required to select this size. Compared with the original, constrained, mixed, sum, and random sum extreme learning machines, the proposed methods achieve a percentage of time reduction up to 98% with equal or better generalization ability.

keywords: Extreme Learning Machine, Number of hidden nodes, Moving average, Exponential moving average, Divide and conquer