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

Alexandros Iosifidis; Anastasios Tefas; Ioannis Pitas

doi:10.1007/978-3-319-26393-9_21

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

Alexandros Iosifidis
, Anastasios Tefas
, Ioannis Pitas

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

402 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 language	English
Title of host publication	Computational Intelligence
Subtitle of host publication	International 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
Publisher	Springer
Pages	351-364
Number of pages	4
Volume	III
ISBN (Electronic)	9783319263939
ISBN (Print)	9783319263915
DOIs	https://doi.org/10.1007/978-3-319-26393-9_21
Publication status	Published - 25 Nov 2015
Event	International Joint Conference on Computational Intelligence (IJCCI 2014) - Rome, Italy Duration: 22 Oct 2014 → 24 Oct 2014

Publication series

Name	Studies in Computational Intelligence
Publisher	Springer
Volume	620
ISSN (Print)	1860-949X

Conference

Conference	International Joint Conference on Computational Intelligence (IJCCI 2014)
Country/Territory	Italy
City	Rome
Period	22/10/14 → 24/10/14

Access to Document

10.1007/978-3-319-26393-9_21

Ioannis Pitas - Single-hidden Layer Feedforward Neual network training using class geometric information - 2015Accepted author manuscript, 374 KB

Handle.net

Persistent link

Cite this

Iosifidis, A., Tefas, A., & Pitas, I. (2015). Single-Hidden Layer Feedforward Neual Network Training Using Class Geometric Information. In J. J. Merelo, A. Rosa, J. M. Cadenas, A. Dourado, K. Madani, & J. Filipe (Eds.), Computational Intelligence: International Joint Conference, IJCCI 2014 Rome, Italy, October 22-24, 2014 Revised Selected Papers (Vol. III, pp. 351-364). (Studies in Computational Intelligence; Vol. 620). Springer. https://doi.org/10.1007/978-3-319-26393-9_21

Iosifidis, Alexandros ; Tefas, Anastasios ; Pitas, Ioannis. / Single-Hidden Layer Feedforward Neual Network Training Using Class Geometric Information. Computational Intelligence: International Joint Conference, IJCCI 2014 Rome, Italy, October 22-24, 2014 Revised Selected Papers. editor / Juan Julian Merelo ; Agostinho Rosa ; José M Cadenas ; António Dourado ; Kurosh Madani ; Joaquim Filipe. Vol. III Springer, 2015. pp. 351-364 (Studies in Computational Intelligence).

@inproceedings{7698460619a74711aa24dffaa9a91c44,

title = "Single-Hidden Layer Feedforward Neual Network Training Using Class Geometric Information",

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.",

author = "Alexandros Iosifidis and Anastasios Tefas and Ioannis Pitas",

year = "2015",

month = nov,

day = "25",

doi = "10.1007/978-3-319-26393-9\_21",

language = "English",

isbn = "9783319263915",

volume = "III",

series = "Studies in Computational Intelligence",

publisher = "Springer",

pages = "351--364",

editor = "Merelo, \{ Juan Julian\} and Agostinho Rosa and Cadenas, \{Jos{\'e} M\} and Ant{\'o}nio Dourado and Kurosh Madani and Joaquim Filipe",

booktitle = "Computational Intelligence",

address = "United States",

note = "International Joint Conference on Computational Intelligence (IJCCI 2014) ; Conference date: 22-10-2014 Through 24-10-2014",

}

Iosifidis, A, Tefas, A & Pitas, I 2015, Single-Hidden Layer Feedforward Neual Network Training Using Class Geometric Information. in JJ Merelo, A Rosa, JM Cadenas, A Dourado, K Madani & J Filipe (eds), Computational Intelligence: International Joint Conference, IJCCI 2014 Rome, Italy, October 22-24, 2014 Revised Selected Papers. vol. III, Studies in Computational Intelligence, vol. 620, Springer, pp. 351-364, International Joint Conference on Computational Intelligence (IJCCI 2014), Rome, Italy, 22/10/14. https://doi.org/10.1007/978-3-319-26393-9_21

Single-Hidden Layer Feedforward Neual Network Training Using Class Geometric Information. / Iosifidis, Alexandros; Tefas, Anastasios; Pitas, Ioannis.
Computational Intelligence: International Joint Conference, IJCCI 2014 Rome, Italy, October 22-24, 2014 Revised Selected Papers. ed. / Juan Julian Merelo; Agostinho Rosa; José M Cadenas; António Dourado; Kurosh Madani; Joaquim Filipe. Vol. III Springer, 2015. p. 351-364 (Studies in Computational Intelligence; Vol. 620).

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

TY - GEN

T1 - Single-Hidden Layer Feedforward Neual Network Training Using Class Geometric Information

AU - Iosifidis, Alexandros

AU - Tefas, Anastasios

AU - Pitas, Ioannis

PY - 2015/11/25

Y1 - 2015/11/25

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-319-26393-9_21

DO - 10.1007/978-3-319-26393-9_21

M3 - Conference Contribution (Conference Proceeding)

SN - 9783319263915

VL - III

T3 - Studies in Computational Intelligence

SP - 351

EP - 364

BT - Computational Intelligence

A2 - Merelo, Juan Julian

A2 - Rosa, Agostinho

A2 - Cadenas, José M

A2 - Dourado, António

A2 - Madani, Kurosh

A2 - Filipe, Joaquim

PB - Springer

T2 - International Joint Conference on Computational Intelligence (IJCCI 2014)

Y2 - 22 October 2014 through 24 October 2014

ER -

Iosifidis A, Tefas A, Pitas I. Single-Hidden Layer Feedforward Neual Network Training Using Class Geometric Information. In Merelo JJ, Rosa A, Cadenas JM, Dourado A, Madani K, Filipe J, editors, Computational Intelligence: International Joint Conference, IJCCI 2014 Rome, Italy, October 22-24, 2014 Revised Selected Papers. Vol. III. Springer. 2015. p. 351-364. (Studies in Computational Intelligence). doi: 10.1007/978-3-319-26393-9_21

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

Abstract

Publication series

Conference

Access to Document

Handle.net

Fingerprint

Cite this