SciELO - Scientific Electronic Library Online

 
vol.30 issue4Representation of the Competencies of a Software Development Team based on the Semat Essence KernelThermodynamic Analysis of Steam Turbines for Ultracritical, Supercritical, Subcritical and Geothermal Cycles author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google

Share


Información tecnológica

On-line version ISSN 0718-0764

Abstract

CASTRO, Fausto M.  and  JOJOA, Pablo E.. Compressed Training Based on Extreme Learning Machine. Inf. tecnol. [online]. 2019, vol.30, n.4, pp.227-236. ISSN 0718-0764.  http://dx.doi.org/10.4067/S0718-07642019000400227.

This paper presents the design and testing of a new training model for single hidden layer feedforward network based on the same properties of Extreme Learning Machine (ELM). The model acts by compressing the information coming from the hidden layer by means of a subset of nodes from the same layer. This allows to considerably reduce the computational complexity compared to ELM. Experimental results based on simulation for different classification problems indicate that the proposed model achieves the same ELM performances in terms of generalization, exceeding it in speed

Keywords : ELM; neural networks; machine learning; classification technics; supervised learning.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )