Extreme Learning Machine for Supervised Classification with Self-paced Learning

The extreme learning machine (ELM), a typical machine learning algorithm based on feedforward neural network, has been widely used in classification, clustering, regression and feature learning. However, the traditional ELM learns all samples at once, and sample weights of traditional methods are defined before the learning process and they will not change during the learning process. So, its performance is vulnerable to noisy data and outliers, finding a way to solve this problem is meaningful. In this work, we propose a model of self-paced ELM named SP-ELM for binary classification and multi-classification originated from the self-paced learning paradigm. Concretely, the algorithm takes the importance of samples into account according to the loss of predicted value and real value, and it establishes the model from the simple samples to complex samples. By setting certain restrictions, the influence of complex data on the model is reduced. Four different self-paced regularization terms are adopted in the paper to select the instances. Experimental results demonstrate the effectiveness and of the proposed method by comparing it with other improved ELMs.