An Extreme Learning Approach to Active Learning
Euler Guimarães Horta, Antônio P. Braga · 2014
Abstract. We propose in this paper a new active learning method that makes no considerations about the data distribution and does not need to adjust any free parameter. The proposed algorithm is based on extreme learning machines (ELM) and a perceptron with analytical calculation of weights. We show that the proposed model have good results using a reduced set of patterns. 1