Skip to main content

2016 | OriginalPaper | Buchkapitel

An Elitist Genetic Algorithm Based Extreme Learning Machine

verfasst von : Vimala Alexander, Pethalakshmi Annamalai

Erschienen in: Computational Intelligence, Cyber Security and Computational Models

Verlag: Springer Singapore

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Extreme Learning Machine (ELM) has been proved to be exceptionally fast and achieves more generalized performance for learning Single-hidden Layer Feedforward Neural networks (SLFN). In this paper, a Genetic Algorithm (GA) is proposed to choose the appropriate initial weights, biases and the number of hidden neurons which minimizes the classification error. The proposed GA incorporates a novel elitism approach to avoid local optimum and also speed up GA to satisfy the multi-modal function. The experimental results indicate the superior performance of the proposed algorithm with lower classification error.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70(1), 489–501 (2006)CrossRef Huang, G.B., Zhu, Q.Y., Siew, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70(1), 489–501 (2006)CrossRef
2.
Zurück zum Zitat Huang, G., Huang, G.B., Song, S., You, K.: Trends in extreme learning machines: a review. Neural Networks. 61, 32–48 (2015)CrossRef Huang, G., Huang, G.B., Song, S., You, K.: Trends in extreme learning machines: a review. Neural Networks. 61, 32–48 (2015)CrossRef
3.
Zurück zum Zitat Wang, Y., Cao, F., Yuan, Y.: A study on effectiveness of extreme learning machine. Neurocomputing 74(16), 2483–2490 (2011)CrossRef Wang, Y., Cao, F., Yuan, Y.: A study on effectiveness of extreme learning machine. Neurocomputing 74(16), 2483–2490 (2011)CrossRef
4.
Zurück zum Zitat Bartlett, P.L.: The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network. IEEE Trans. Inf. Theory 44(2), 525–536 (1998)CrossRefMathSciNetMATH Bartlett, P.L.: The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network. IEEE Trans. Inf. Theory 44(2), 525–536 (1998)CrossRefMathSciNetMATH
5.
Zurück zum Zitat Levenberg, K.: A method for the solution of certain nonlinear problems in least squares. Quart. Appl. Math. 2, 164–168 (1994)MathSciNet Levenberg, K.: A method for the solution of certain nonlinear problems in least squares. Quart. Appl. Math. 2, 164–168 (1994)MathSciNet
6.
Zurück zum Zitat Hagan, M.T., Menhaj, M.B.: Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neural Networks 5(6), 989–993 (1994)CrossRef Hagan, M.T., Menhaj, M.B.: Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neural Networks 5(6), 989–993 (1994)CrossRef
7.
Zurück zum Zitat Ilonen, J., Kamarainen, J.K., Lampinen, J.: Differential evolution training algorithm for feed-forward neural networks. Neural Process. Lett. 17(1), 93–105 (2003)CrossRef Ilonen, J., Kamarainen, J.K., Lampinen, J.: Differential evolution training algorithm for feed-forward neural networks. Neural Process. Lett. 17(1), 93–105 (2003)CrossRef
8.
Zurück zum Zitat Subudhi, B., Jena, D.: Differential evolution and Levenberg Marquardt trained neural network scheme for nonlinear system identification. Neural Process. Lett. 27(3), 285–296 (2008)CrossRef Subudhi, B., Jena, D.: Differential evolution and Levenberg Marquardt trained neural network scheme for nonlinear system identification. Neural Process. Lett. 27(3), 285–296 (2008)CrossRef
9.
Zurück zum Zitat Zhu, Q.Y., Qin, A.K., Suganthan, P.N., Huang, G.B.: Evolutionary extreme learning machine. Pattern Recogn. 38(10), 1759–1763 (2005)CrossRefMATH Zhu, Q.Y., Qin, A.K., Suganthan, P.N., Huang, G.B.: Evolutionary extreme learning machine. Pattern Recogn. 38(10), 1759–1763 (2005)CrossRefMATH
10.
Zurück zum Zitat Cao, J., Lin, Z., Huang, G.B.: Self-adaptive evolutionary extreme learning machine. Neural Process. Lett. 36(3), 285–305 (2012)CrossRef Cao, J., Lin, Z., Huang, G.B.: Self-adaptive evolutionary extreme learning machine. Neural Process. Lett. 36(3), 285–305 (2012)CrossRef
11.
Zurück zum Zitat Qin, A.K., Huang, V.L., Suganthan, P.N.: Differential evolution algorithm with strategy adaptation for global numerical optimization. IEEE Trans. Evol. Comput. 13(2), 398–417 (2009)CrossRef Qin, A.K., Huang, V.L., Suganthan, P.N.: Differential evolution algorithm with strategy adaptation for global numerical optimization. IEEE Trans. Evol. Comput. 13(2), 398–417 (2009)CrossRef
12.
Zurück zum Zitat Lahoz, D., Lacruz, B., Mateo, P.M.: A multi-objective micro genetic ELM algorithm. Neuro-computing 111, 90–103 (2013) Lahoz, D., Lacruz, B., Mateo, P.M.: A multi-objective micro genetic ELM algorithm. Neuro-computing 111, 90–103 (2013)
13.
Zurück zum Zitat Suresh, S., Babu, R.V., Kim, H.J.: No-reference image quality assessment using modified extreme learning machine classifier. Appl. Soft Comput. 9(2), 541–552 (2009)CrossRef Suresh, S., Babu, R.V., Kim, H.J.: No-reference image quality assessment using modified extreme learning machine classifier. Appl. Soft Comput. 9(2), 541–552 (2009)CrossRef
14.
Zurück zum Zitat Li, J.P., Balazs, M.E., Parks, G.T., Clarkson, P.J.: A species conserving genetic algorithm for multimodal function optimization. Evol. Comput. 11(1), 107–109 (2003)CrossRef Li, J.P., Balazs, M.E., Parks, G.T., Clarkson, P.J.: A species conserving genetic algorithm for multimodal function optimization. Evol. Comput. 11(1), 107–109 (2003)CrossRef
15.
Zurück zum Zitat Liang, Y., Leung, K.S.: Genetic Algorithm with adaptive elitist-population strategies for multimodal function optimization. Appl. Soft Comput. 11(2), 2017–2034 (2011)CrossRef Liang, Y., Leung, K.S.: Genetic Algorithm with adaptive elitist-population strategies for multimodal function optimization. Appl. Soft Comput. 11(2), 2017–2034 (2011)CrossRef
16.
Zurück zum Zitat Huang, G.B., Babri, H.A.: Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions. IEEE Trans. Neural Networks 9(1), 224–229 (1998)CrossRef Huang, G.B., Babri, H.A.: Upper bounds on the number of hidden neurons in feedforward networks with arbitrary bounded nonlinear activation functions. IEEE Trans. Neural Networks 9(1), 224–229 (1998)CrossRef
17.
Zurück zum Zitat Huang, G.B.: Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Trans. Neural Networks 14(2), 274–281 (2003)CrossRef Huang, G.B.: Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Trans. Neural Networks 14(2), 274–281 (2003)CrossRef
18.
Zurück zum Zitat Huang, G.B., Chen, L., Siew, C.K.: Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans. Neural Networks 17(4), 879–892 (2006)CrossRef Huang, G.B., Chen, L., Siew, C.K.: Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans. Neural Networks 17(4), 879–892 (2006)CrossRef
19.
Zurück zum Zitat Hykin, S.: Neural Networks: A Comprehensive Foundation. Printice-Hall. Inc., NJ (1999) Hykin, S.: Neural Networks: A Comprehensive Foundation. Printice-Hall. Inc., NJ (1999)
20.
Zurück zum Zitat Rao, C.R., Mitra, S.K.: Generalized Inverse of Matrices and Its Aplications, vol. 7. Wiley, New York (1971) Rao, C.R., Mitra, S.K.: Generalized Inverse of Matrices and Its Aplications, vol. 7. Wiley, New York (1971)
21.
Zurück zum Zitat Corwin, E.M., Logar, A.M., Oldham, W.J.: An iterative method for training multilayer networks with threshold functions. IEEE Trans. Neural Networks 5(3), 507–508 (1994)CrossRef Corwin, E.M., Logar, A.M., Oldham, W.J.: An iterative method for training multilayer networks with threshold functions. IEEE Trans. Neural Networks 5(3), 507–508 (1994)CrossRef
22.
Zurück zum Zitat Holland, J.H.: Adaptation in Natural and Artificial Systems. MIT Press (1992) Holland, J.H.: Adaptation in Natural and Artificial Systems. MIT Press (1992)
23.
Zurück zum Zitat Mohamed, M.H.: Rules extraction from constructively trained neural networks based on genetic algorithms. Neurocomputing 74(17), 3180–3192 (2011)CrossRef Mohamed, M.H.: Rules extraction from constructively trained neural networks based on genetic algorithms. Neurocomputing 74(17), 3180–3192 (2011)CrossRef
24.
Zurück zum Zitat Bi, C.: Deterministic local alignment methods improved by a simple genetic algorithm. Neurocomputing 73(13), 2394–2406 (2010)CrossRef Bi, C.: Deterministic local alignment methods improved by a simple genetic algorithm. Neurocomputing 73(13), 2394–2406 (2010)CrossRef
25.
Zurück zum Zitat Michalewicz, Z.: Genetic Algorithms + Data Structures = Evolution Programs, pp. 111–112. Springer Science & Business Media (1996) Michalewicz, Z.: Genetic Algorithms + Data Structures = Evolution Programs, pp. 111–112. Springer Science & Business Media (1996)
26.
Zurück zum Zitat Simon, D.: Evolutionary Optimization Algorithms, pp. 188–189. Wiley (2013) Simon, D.: Evolutionary Optimization Algorithms, pp. 188–189. Wiley (2013)
Metadaten
Titel
An Elitist Genetic Algorithm Based Extreme Learning Machine
verfasst von
Vimala Alexander
Pethalakshmi Annamalai
Copyright-Jahr
2016
Verlag
Springer Singapore
DOI
https://doi.org/10.1007/978-981-10-0251-9_29