A derived least square extreme learning machine

Extreme learning machine (ELM) is a single hidden layer feedforward neural network and is proved to be a good machine learning tool. However, the singularity of the ELM activation function results in the poor generalization ability of the systems. This study proposes a least squares ELM with derivative characteristics (DLSELM). The activation function of the network consists of the original and derivative functions due to the introduction of derivative characteristics in the network. All weights and biases of the network are determined by a twice least squares method. Derivative characteristics increase the diversity of activation functions in the network. The regression accuracy of the network and the generalization ability of the system were greatly improved due to the weighs and biases of the DLSELM calculated by twice least methods. DLSELM is applied to different datasets for verifying their performance. Moreover, DLSELM possesses the best regression accuracy, stability, and generalization performance compared with the other networks.

Automated summary

This study proposes a least squares ELM with derivative characteristics (DLSELM) which increases the diversity of activation functions in the network and determines the weights and biases of the network through a twice least squares method. DLSELM possesses the best regression accuracy, stability, and generalization performance compared with the other networks.