We developed a new method of intelligent optimum strategy for a local coupled extreme\nlearning machine (LC-ELM). In this method, both the weights and biases between the input layer and\nthe hidden layer, as well as the addresses and radiuses in the local coupled parameters, are determined\nand optimized based on the particle swarm optimization (PSO) algorithm. Compared with extreme\nlearning machine (ELM), LC-ELM and extreme learning machine based on particle optimization\n(PSO-ELM) that have the same network size or compact network configuration, simulation results in\nterms of regression and classification benchmark problems show that the proposed algorithm, which\nis called LC-PSO-ELM, has improved generalization performance and robustness.
Loading....