Extreme learning machine: algorithm, theory and applications

Extreme learning machine (ELM) is a new learning algorithm for the single hidden layer feedforward neural networks. Compared with the conventional neural network learning algorithm it overcomes the slow training speed and over-fitting problems. ELM is based on empirical risk minimization theory and...

Full description

Saved in:
Bibliographic Details
Published in:The Artificial intelligence review Vol. 44; no. 1; pp. 103 - 115
Main Authors: Ding, Shifei, Zhao, Han, Zhang, Yanan, Xu, Xinzheng, Nie, Ru
Format: Journal Article
Language:English
Published: Dordrecht Springer Netherlands 01.06.2015
Springer
Springer Nature B.V
Subjects:
Algorithms
Application
Artificial Intelligence
Artificial neural networks
Computer Science
Data mining
Information processing
Learning
Machine learning
Minimization
Neural networks
Optimization
Pattern recognition
R&D
Research & development
Robot learning
Robust control
Robustness
Theory
Tracking
Extreme learning machine (ELM)
Local minimum
Over-fitting
Single-hidden layer feedforward neural networks (SLFNs)
Least-squares
ISSN:0269-2821, 1573-7462
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Extreme learning machine (ELM) is a new learning algorithm for the single hidden layer feedforward neural networks. Compared with the conventional neural network learning algorithm it overcomes the slow training speed and over-fitting problems. ELM is based on empirical risk minimization theory and its learning process needs only a single iteration. The algorithm avoids multiple iterations and local minimization. It has been used in various fields and applications because of better generalization ability, robustness, and controllability and fast learning rate. In this paper, we make a review of ELM latest research progress about the algorithms, theory and applications. It first analyzes the theory and the algorithm ideas of ELM, then tracking describes the latest progress of ELM in recent years, including the model and specific applications of ELM, finally points out the research and development prospects of ELM in the future.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0269-2821
1573-7462
DOI:10.1007/s10462-013-9405-z