Improvements on parsimonious extreme learning machine using recursive orthogonal least squares
| Autor: | Yong-Ping Zhao, Ramon Huerta |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
0209 industrial biotechnology
Generalization business.industry Computer science Cognitive Neuroscience System identification 02 engineering and technology Machine learning computer.software_genre Constructive Regression Computer Science Applications Householder transformation 020901 industrial engineering & automation Artificial Intelligence 0202 electrical engineering electronic engineering information engineering Givens rotation 020201 artificial intelligence & image processing Artificial intelligence business computer Robotic arm Extreme learning machine |
| Zdroj: | Neurocomputing. 191:82-94 |
| ISSN: | 0925-2312 |
| DOI: | 10.1016/j.neucom.2016.01.005 |
| Popis: | Recently novel constructive and destructive parsimonious extreme learning machines (CP-ELM and DP-ELM) arose to cope with regression problems. With these foundations, several improvements on CP-ELM and DP-ELM are suggested. CP-ELM can be improved by replacing the Givens rotation with the Householder transformation, yielding the improved CP-ELM (ICP-ELM) which results in the acceleration of the training speed without hampering the generalization performance. Subsequently, a hybrid constructive–destructive ELM (CDP-ELM) is generated integrating elements from CP-ELM and DP-ELM. The goal is to combine the advantages of training speed and parsimony from CP-ELM and DP-ELM. Finally, experiments on regression data sets and a real-world system identification of robot arm example are done to test the feasibility and efficacy of these variants including ICP-ELM and CDP-ELM. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect