A study on the randomness reduction effect of extreme learning machine with ridge regression

Authors:
Meng Joo Er;Zhifei Shao;Ning Wang
Affiliations:
Dalian Maritime University, Dalian, China,Nanyang Technological University, Singapore;Nanyang Technological University, Singapore;Dalian Maritime University, Dalian, China
Venue:
ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part I
Year:
2013

Citing 10
Cited 0

Neural Network Ensembles

IEEE Transactions on Pattern Analysis and Machine Intelligence
Deterministic neural classification

Neural Computation
Sales forecasting using extreme learning machine with applications in fashion retailing

Decision Support Systems
Letters: Ensemble of online sequential extreme learning machine

Neurocomputing
Error minimized extreme learning machine with growth of hidden nodes and incremental learning

IEEE Transactions on Neural Networks
Rapid and brief communication: Evolutionary extreme learning machine

Pattern Recognition
OP-ELM: optimally pruned extreme learning machine

IEEE Transactions on Neural Networks
Performance enhancement of extreme learning machine for multi-category sparse data classification problems

Engineering Applications of Artificial Intelligence
Two-stage extreme learning machine for regression

Neurocomputing
Constructive hidden nodes selection of extreme learning machine for regression

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In recent years, Extreme Learning Machine (ELM) has attracted comprehensive attentions as a universal function approximator. Comparing to other single layer feedforward neural networks, its input parameters of hidden neurons can be randomly generated rather than tuned, and thereby saving a huge amount of computational power. However, it has been pointed out that the randomness of ELM parameters would result in fluctuating performances. In this paper, we intensively investigate the randomness reduction effect by using a regularized version of ELM, named Ridge ELM (RELM). Previously, RELM has been shown to achieve generally better generalization than the original ELM. Furthermore, we try to demonstrate that RELM can also greatly reduce the fluctuating performance with 12 real world regression tasks. An insight into this randomness reduction effect is also given.