Swarm-Based Extreme Learning Machine Models for Global Optimization

Extreme Learning Machine (ELM) is popular in batch learning, sequential and progressive due to its speed, easy integration, generalization ability. While, Traditional ELM cannot train massive data rapidly efficiently memory residence, high time space complexity. In ELM, the hidden layer typically necessitates a huge number of nodes. Furthermore, there no certainty that arrangement weights biases within optimal. To solve this problem, traditional has been hybridized with swarm intelligence optimization techniques. This paper displays five proposed hybrid Algorithms “Salp Swarm Algorithm (SSA-ELM), Grasshopper (GOA-ELM), Grey Wolf (GWO-ELM), Whale (WOA-ELM) Moth Flame Optimization (MFO-ELM)”. These optimizers are standard methodology for resolving tumor type classification using gene expression data. The models applied predication electricity loading data, describes energy use single residence over four-year period. layer, algorithms used pick smaller nodes speed up execution ELM. best preferences were calculated by these layer. Experimental results demonstrated MFO-ELM achieved 98.13% accuracy highest model While predication, GOA-ELM 0.397which least RMSE compared other models.