A study on effectiveness of extreme learning machine

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.

Cited by in corpus (10)

• Real-Time COVID-19 Diagnosis from X-Ray Images Using Deep CNN and Extreme Learning Machines Stabilized by Chimp Optimization Algorithm
• Sparse Representation Based Augmented Multinomial Logistic Extreme Learning Machine with Weighted Composite Features for Spectral Spatial Hyperspectral Image Classification
• A novel online multi-label classifier for high-speed streaming data applications
• A General Framework for Hypercomplex-valued Extreme Learning Machines
• Linear vs Nonlinear Extreme Learning Machine for Spectral-Spatial Classification of Hyperspectral Image
• Numerical Solution and Bifurcation Analysis of Nonlinear Partial Differential Equations with Extreme Learning Machines
• ZORB: A Derivative-Free Backpropagation Algorithm for Neural Networks
• A Gegenbauer Neural Network with Regularized Weights Direct Determination for Classification
• Effective Non-Random Extreme Learning Machine
• On improving learning capability of ELM and an application to brain-computer interface