Loading...
Loading...

Go to the content (press return)

Comparing error minimized extreme learning machines and support vector sequential feed-forward neural networks

Author
Romero, E.; Alquezar, R.
Type of activity
Report
Date
2010-06
Code
LSI-10-14-R
Repository
http://hdl.handle.net/2117/88076 Open in new window
Abstract
Recently, error minimized extreme learning machines (EM-ELMs) have been proposed as a simple and efficient approach to build single-hidden-layer feed-forward networks (SLFNs) sequentially. They add random hidden nodes one by one (or group by group) and update the output weights incrementally to minimize the sum-of-squares error in the training set. Other very similar methods that also construct SLFNs sequentially had been reported earlier with the main difference that their hidden-layer weights ...
Citation
Romero, E., Alquézar, R. "Comparing error minimized extreme learning machines and support vector sequential feed-forward neural networks". 2010.
Keywords
Approximation theory, Feedforward neural nets, Learning (artificial intelligence), Regression analysis, Support vector machines
Group of research
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center
SOCO - Soft Computing
VIS - Artificial Vision and Intelligent Systems

Participants

Attachments