Performance of Selected Nature-Inspired Metaheuristic Algorithms Used for Extreme Learning Machine

This work presents a research on Nature Inspired Metaheuristic Algorithms (MA) used as optimizers in training process of Machine Learning method called Extreme Learning Machine (ELM). We tested 19 MA optimizers measuring their performance directly on sample datasets. The impact of input parameters such as number of hidden layer units, optimization stopping conditions and population size on the accuracy results, training and prediction time is evaluated here. Significant differences in performance of applied methods and their parameters’ values are detected. The most meaningful outcome of this paper shows that an increase of the number of MA iterations does not yield significant boost in accuracy with a huge increase in training time. Indeed a cap on number of MA iterations ranging from 1 to 5 is sufficient for analyzed machine learning tasks. In our research the best results are obtained for population size ranging between 50 and 100. Hybridized ELM outperforms classical implementation of ELM as higher accuracy is reached for the same number of neurons.