Deformed Kernel Based Extreme Learning Machine

The extreme learning machine (ELM) is a newly emerging supervised learning method. In order to use the information provided by unlabeled samples and improve the performance of the ELM, we deformed the kernel in the ELM by modeling the marginal distribution with the graph Laplacian, which is built with both labeled and unlabeled samples. We further approximated the deformed kernel by means of random feature mapping. The experimental results showed that the proposed semi-supervised extreme learning machine tends to achieve outstanding generalization performance at a relatively faster learning speed than traditional semi-supervised learning algorithms.