Improvement flower pollination extreme learning machine based on meta-learning
Sarunyoo Boriratrit, Sirapat Chiewchanwattana, Khamron Sunat, Pakarat Musikawan, Punyaphol Horata · 2016
Extreme Learning Machine (ELM) model which learn very faster than other neural networks model but the solution was not suitable as expected since the randomness of the input weights and biases may cause to the nonfulfillment of solution. Flower Pollination Extreme Learning Machine (FP-ELM) model that it was merged by ELM and Flower Pollination Algorithm (FPA) to adjust the input weight and biases for improve performance of output weight when the input weight and biases were calculated. Nonetheless, FP-ELM may cause overfitting and more number of hidden nodes were used. In this paper, Meta Learning of Flower Pollination Extreme Learning Machine (Meta-FPELM) was proposed that compart the input weight, calculate to hidden nodes as FP-ELM and combine to the last output weight. In addition, the result of real word regression problems experiment of Meta-FPELM compared with state-of-the-art show that Meta-FPELM can overcome five-eighth in testing phase for all datasets.