Regularized Extreme Learning Machine

Extreme learning machine proposed by Huang G-B has attracted many attentions for its extremely fast training speed and good generalization performance. But it still can be considered as empirical risk minimization theme and tends to generate over-fitting model. Additionally, since ELM doesn´t considering heteroskedasticity in real applications, its performance will be affected seriously when outliers exist in the dataset. In order to address these drawbacks, we propose a novel algorithm called regularized extreme learning machine based on structural risk minimization principle and weighted least square. The generalization performance of the proposed algorithm was improved significantly in most cases without increasing training time.