Back to Search
Start Over
Improved Meta-ELM with error feedback incremental ELM as hidden nodes.
- Source :
- Neural Computing & Applications; Dec2018, Vol. 30 Issue 11, p3363-3370, 8p
- Publication Year :
- 2018
-
Abstract
- Liao et al. (Neurocomputing 128:81-87, 2014) proposed a meta-learning approach to extreme learning machine (Meta-ELM), which can obtain good generalization performance by training multiple ELMs. However, one of its open problems is overfitting when minimizing training error. In this paper, we propose an improved meta-learning model of ELM (improved Meta-ELM) to handle the problem. The improved Meta-ELM architecture is composed of some base ELMs which are error feedback incremental extreme learning machine (EFI-ELM) and the top ELM. The improved Meta-ELM includes two stages. First, each base ELM with EFI-ELM is trained on a subset of training data. Then, the top ELM learns with the base ELMs as hidden nodes. Simulation results on some artificial and benchmark datasets show that the proposed improved Meta-ELM model is more feasible and effective than Meta-ELM. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09410643
- Volume :
- 30
- Issue :
- 11
- Database :
- Complementary Index
- Journal :
- Neural Computing & Applications
- Publication Type :
- Academic Journal
- Accession number :
- 133105837
- Full Text :
- https://doi.org/10.1007/s00521-017-2922-y