Training extreme learning machine with accelerator algorithm
Main Article Content
Abstract
This paper presents a new algorithm for training neural networks fed back not one hidden layer which combines the properties of the end machine learning algorithm with AR? occurs. The proposed algorithm has low computational complexity and tests show a high performance in terms of generalization.
Article Details
Section
Research Papers

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
All the texts published in this magazine are distributed under a Creative Commons License «Attribution-Non-Commercial-Share the same»
How to Cite
Jojoa Gómez, P. E., & Castro Caicedo, F. M. (2015). Training extreme learning machine with accelerator algorithm. I+ T+ C- Investigación, Tecnología Y Ciencia, 1(9), 37-42. https://revistas.unicomfacauca.edu.co/ojs/index.php/itc/article/view/itc2015_pag_37_42