Universal Approximation and QoS Violation Application of Extreme Learning Machine

Authors:
Lei Chen;Lifeng Zhou;Hung Keng Pung
Affiliations:
Network Systems and Service Lab, Department of Computer Science, National University of Singapore, Singapore, Singapore;Network Systems and Service Lab, Department of Computer Science, National University of Singapore, Singapore, Singapore;Network Systems and Service Lab, Department of Computer Science, National University of Singapore, Singapore, Singapore
Venue:
Neural Processing Letters
Year:
2008

Citing 8
Cited 3

Approximation capabilities of multilayer feedforward networks

Neural Networks
Approximation of functions on a compact set by finite sums of a sigmoid function without scaling

Neural Networks
Original Contribution: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function

Neural Networks
QualProbes: middleware QoS profiling services for configuring adaptive applications

IFIP/ACM International Conference on Distributed systems platforms
Cooperative run-time management of adaptive applications and distributed resources

Proceedings of the tenth ACM international conference on Multimedia
Kernel orthonormalization in radial basis function neural networks

IEEE Transactions on Neural Networks
Real-time learning capability of neural networks

IEEE Transactions on Neural Networks
Universal approximation using incremental constructive feedforward networks with random hidden nodes

IEEE Transactions on Neural Networks

Weighting Efficient Accuracy and Minimum Sensitivity for Evolving Multi-Class Classifiers

Neural Processing Letters
PCA-ELM: A Robust and Pruned Extreme Learning Machine Approach Based on Principal Component Analysis

Neural Processing Letters
Parallel Chaos Search Based Incremental Extreme Learning Machine

Neural Processing Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

Neural networks have been successfully applied to many applications due to their approximation capability. However, complicated network structures and algorithms will lead to computational and time-consuming burdens. In order to satisfy demanding real-time requirements, many fast learning algorithms were explored in the past. Recently, a fast algorithm, Extreme Learning Machine (ELM) (Huang et al. 70:489---501, 2006) was proposed. Unlike conventional algorithms whose neurons need to be tuned, the input-to-hidden neurons of ELM are randomly generated. Though a large number of experimental results have shown that input-to-hidden neurons need not be tuned, there lacks a rigorous proof whether ELM possesses the universal approximation capability. In this paper, based on the universal approximation property of an orthonormal method, we firstly illustrate the equivalent relationship between ELM and the orthonormal method, and further prove that neural networks with ELM are also universal approximations. We also successfully apply ELM to the identification of QoS violation in the multimedia transmission.