A Hybrid Model of Extreme Learning Machine Based on Bat and Cuckoo Search Algorithm for Regression and Multiclass Classification

• Published in: Journal of Mathematics Vol. 2021; pp. 1 - 11
• Main Authors: Fan, Qinwei, Fan, Tongke
• Format: Journal Article
• Language: English
• Published: Cairo Hindawi 08.11.2021; John Wiley & Sons, Inc; Wiley
• Subjects: Algorithms; Approximation; Artificial intelligence; Artificial neural networks; Classification; Computational linguistics; Data mining; Fault diagnosis; Genetic algorithms; Language processing; Machine learning; Mathematics; Natural language interfaces; Neural networks; Optimization algorithms; Search algorithms
• ISSN: 2314-4629; 2314-4785; 2314-4785
• DOI: 10.1155/2021/4404088

Extreme learning machine (ELM), as a new simple feedforward neural network learning algorithm, has been extensively used in practical applications because of its good generalization performance and fast learning speed. However, the standard ELM requires more hidden nodes in the application due to the random assignment of hidden layer parameters, which in turn has disadvantages such as poorly hidden layer sparsity, low adjustment ability, and complex network structure. In this paper, we propose a hybrid ELM algorithm based on the bat and cuckoo search algorithm to optimize the input weight and threshold of the ELM algorithm. We test the numerical experimental performance of function approximation and classification problems under a few benchmark datasets; simulation results show that the proposed algorithm can obtain significantly better prediction accuracy compared to similar algorithms.