Self-adaptive Differential Evolutionary Extreme Learning Machine and Its Application in Facial Age Estimation

In this paper, Self-adaptive Differential Evolutionary Extreme Learning Machine (SaDE-ELM) was proposed as a new class of learning algorithm for single-hidden layer feed forward neural network (SLFN). In order to achieve good generalization performance, SaDE-ELM calculates the error on a subset of testing data for parameter optimization. Since SaDE-ELM employs extra data for validation to avoid the over fitting problem, more samples are needed for model training. In this paper, the cross-validation strategy is proposed to be embedded into the training phase so as to solve the overtraining problem. Experimental results demonstrate that the proposed algorithms are efficient for Facial Age Estimation.