METAHEURISTIC ALGORITHMS IN EXTREME LEARNING MACHINE FOR SELECTION OF PARAMETERS IN ACTIVATION FUNCTION

This research investigates the integration of Metaheuristic Algorithms (MAs) with the Extreme Learning Machine (ELM) model to optimize parameters of activation function. While MAs have traditionally been employed for weights selection, a methodology that utilizes MA for the selection of activation function parameters was proposed. The performance of 24 distinctive activation functions was evaluated on diverse and widespread benchmark datasets: Ionosphere, Breast Cancer, Australian Credits, Musk and Banana. The results demonstrate a strong dependence on selecting an optimal activation function for each task, with variations in accuracy ranging up to 60 percentage points. The MA-ELM approach shows promising results, providing improved accuracy and reducing the number of required neurons in certain cases. The approach offers an efficient alternative to the typical MA-ELM method, requiring evaluation of only a few parameter values compared to the optimization of hundreds or thousands of weights. This approach enhances the generalization abilities of core ELM method and reduces computational time in comparison to typical MA-ELM. These findings validate the effectiveness of the proposed MA-ELM approach, contributing to the understanding of integrating MA with activation functions in ELM and offering insights for enhancing model performance in various applications.