A study on effectiveness of extreme learning machine

TL;DR

This paper evaluates the effectiveness of Extreme Learning Machine (ELM) and introduces an improved version, EELM, which enhances learning accuracy and robustness by ensuring the full rank of the hidden layer output matrix.

Contribution

The paper proposes EELM, an improved ELM algorithm that selects input weights and biases to guarantee full rank of the output matrix, enhancing performance.

Findings

EELM improves testing and prediction accuracy.

EELM increases robustness of the neural networks.

Experimental results show EELM's superior performance on benchmarks and real-world tasks.

Abstract

Extreme learning machine (ELM), proposed by Huang et al., has been shown a promising learning algorithm for single-hidden layer feedforward neural networks (SLFNs). Nevertheless, because of the random choice of input weights and biases, the ELM algorithm sometimes makes the hidden layer output matrix H of SLFN not full column rank, which lowers the effectiveness of ELM. This paper discusses the effectiveness of ELM and proposes an improved algorithm called EELM that makes a proper selection of the input weights and bias before calculating the output weights, which ensures the full column rank of H in theory. This improves to some extend the learning rate (testing accuracy, prediction accuracy, learning time) and the robustness property of the networks. The experimental results based on both the benchmark function approximation and real-world problems including classification and regression applications show the good performances of EELM.