Single-Hidden Layer Feedforward Neual Network Training Using Class Geometric Information

Alexandros Iosifidis, Anastasios Tefas, Ioannis Pitas

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

224 Downloads (Pure)

Abstract

Single-hidden Layer Feedforward (SLFN) networks have been proven to be effective in many pattern classification problems. In this chapter, we provide an overview of a relatively new approach for SLFN network training that is based on Extreme Learning. Subsequently, extended versions of the Extreme Learning Machine algorithm that exploit local class data geometric information in the optimization process followed for the calculation of the network output weights are
discussed. An experimental study comparing the two approaches on facial image
classification problems concludes this chapter.
Original languageEnglish
Title of host publicationComputational Intelligence
Subtitle of host publicationInternational Joint Conference, IJCCI 2014 Rome, Italy, October 22-24, 2014 Revised Selected Papers
Editors Juan Julian Merelo, Agostinho Rosa, José M Cadenas, António Dourado, Kurosh Madani, Joaquim Filipe
PublisherSpringer
Pages351-364
Number of pages4
VolumeIII
ISBN (Electronic)9783319263939
ISBN (Print)9783319263915
DOIs
Publication statusPublished - 25 Nov 2015
EventInternational Joint Conference on Computational Intelligence (IJCCI 2014) - Rome, Italy
Duration: 22 Oct 201424 Oct 2014

Publication series

NameStudies in Computational Intelligence
PublisherSpringer
Volume620
ISSN (Print)1860-949X

Conference

ConferenceInternational Joint Conference on Computational Intelligence (IJCCI 2014)
CountryItaly
CityRome
Period22/10/1424/10/14

Fingerprint Dive into the research topics of 'Single-Hidden Layer Feedforward Neual Network Training Using Class Geometric Information'. Together they form a unique fingerprint.

Cite this