Optimizing neural network based on cuckoo search and invasive weed optimization using extreme learning machine approach - 03/05/22
Abstract |
Extreme Learning Machine (ELM) is widely known to train feed forward network with high speed and good generalization performance. The only problem associated with ELM is required higher number of hidden neurons due to random selection. In this paper we proposed a new model Cuckoo Search with Invasive weed optimization based Extreme Learning Machine (CSIWO-ELM) to optimize input weight and hidden neurons. This model provides the optimize input to the feedforward network to improve the ELM. The developed model is experimented on three medical datasets to see the data classification. Also, the developed model is compared with different optimize algorithm. The experimental result proves the excellent working of CSIWO-ELM model for classification problem.
El texto completo de este artículo está disponible en PDF.Highlights |
• | Optimal performance of generalization results in increased classification accuracy. |
• | Faster training speed. |
• | Lesser number of hidden neurons for prediction due to compact structure. |
• | Optimization of input weight and hidden neurons. |
JEL classification : C30, C45, C53, C60, C61, C69
Keywords : Feed forward neural network, Extreme machine learning, Invasive weed optimization, Cuckoo search
Esquema
Vol 2 - N° 3
Artículo 100075- septembre 2022 Regresar al númeroBienvenido a EM-consulte, la referencia de los profesionales de la salud.