Abstract
AbstractAlthough the extreme learning machine(ELM)algorithm is applied in training single hidden layer feedforward neural networks without manual intervention and its fast training speed has been recognized nowadays, there are still several problems need to be solved in this algorithm. In this paper, we propose a new improved ELM algorithm–Error Minimized and Ridge Regression ELM(ER-ELM) derived from how to select the number of hidden nodes and the way to handle with the multicollinearity. We compare the ER-ELM algorithm with other relative algorithms such as ELM et al. Simulation results show that the ER-ELM algorithm has better stability and generalization performance than the other algorithms.KeywordsExtreme Learning MachineRidge RegressionSingle hidden layer neural network
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
