Smoothing L0 Regularization for Extreme Learning Machine

Extreme learning machine (ELM) has been put forward for single hidden layer feedforward networks. Because of its powerful modeling ability and it needs less human intervention, the ELM algorithm has been used widely in both regression and classification experiments. However, in order to achieve requ...

Full description

Saved in:
Bibliographic Details
Published in:Mathematical problems in engineering 2020, Vol.2020 (2020), p.1-10
Main Authors: Fan, Qinwei, Liu, Ting
Format: Article
Language:English
Subjects:
Accuracy
Algorithms
Artificial intelligence
Artificial neural networks
Classification
Datasets
Error reduction
Machine learning
Mathematical problems
Neural networks
Neurons
Nodes
Optimization
Regularization
Regularization methods
Smoothing
Sparsity
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Extreme learning machine (ELM) has been put forward for single hidden layer feedforward networks. Because of its powerful modeling ability and it needs less human intervention, the ELM algorithm has been used widely in both regression and classification experiments. However, in order to achieve required accuracy, it needs many more hidden nodes than is typically needed by the conventional neural networks. This paper considers a new efficient learning algorithm for ELM with smoothing L0 regularization. A novel algorithm updates weights in the direction along which the overall square error is reduced the most and then this new algorithm can sparse network structure very efficiently. The numerical experiments show that the ELM algorithm with smoothing L0 regularization has less hidden nodes but better generalization performance than original ELM and ELM with L1 regularization algorithms.
ISSN:1024-123X
1563-5147
DOI:10.1155/2020/9175106