An improved hybrid regularization approach for extreme learning machine

Abstract

Extreme learning machine (ELM) is a network model that arbitrarily initializes the first hidden layer and can be computed speedily. In order to improve the classification performance of ELM, a ℓ2 and ℓ0.5 regularization ELM model (ℓ2-ℓ0.5-ELM) is proposed in this paper. An iterative optimization algorithm of the fixed point contraction mapping is applied to solve the ℓ2-ℓ0.5-ELM model. The convergence and sparsity of the proposed method are discussed and analyzed under reasonable assumptions. The performance of the proposed ℓ2-ℓ0.5-ELM method is compared with BP, SVM, ELM, ℓ0.5-ELM, ℓ1-ELM, ℓ2-ELM and ℓ2-ℓ1ELM, the results show that the prediction accuracy, sparsity, and stability of the ℓ2-ℓ0.5-ELM are better than the other 7 models.