Error Minimized Extreme Learning Machine With Growth of Hidden Nodes and Incremental Learning

By Guorui Feng, G. Huang, Qingping Lin, Robert Kheng Leng Gay. IEEE Transactions on Neural Networks, 2009

636 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Extreme learning machines: a survey (2011, methodology): “In the enhancement of EM-ELM, the hidden node is added to the network one-byone .”
A review on extreme learning machine (2021, background): “Feng and Huang [34] combined extreme learning machine with random structure of hidden neurons and improved the model performance in their research.”
A structure optimisation algorithm for feedforward neural network construction (2013, methodology): “The ability to approximate functions makes the FNN applicable to the application areas such as modelling and identification in system control [5,6].”
A fast maximum likelihood nonlinear feature transformation method for GMM-HMM speaker adaptation (2014, methodology): “The method in [22] selects the hidden layer size by reducing its regression error to a predefined threshold.”
Trends in extreme learning machines: A review (2015, background): “The EM-ELM algorithm (Feng et al., 2009) Input: The maximum number of hidden neurons N max ; The expected training error ϵ .”