Skip to main content

2019 | OriginalPaper | Buchkapitel

Modeling of Hidden Layer Architecture in Multilayer Artificial Neural Networks

verfasst von : Mihirini Wagarachchi, Asoka Karunananda

Erschienen in: Artificial Intelligence

Verlag: Springer Singapore

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

search-config
loading …

Abstract

A generated solution for an artificial neural network (ANN) may result in complex computations of neural networks, deployment, and usage of trained networks due to its inappropriate architecture. Therefore, modeling the hidden layer architecture of artificial neural networks remains as a research challenge. This paper presents a solution to achieve the hidden layer architecture of artificial neural networks which is inspired by some facts of neuroplasticity. The proposed method has two phases. First, it determines the number of hidden layers for the best architecture and then removes unnecessary hidden neurons from the network to enhance the performance. Experimental results in several benchmark problems show that the modified network shows better generalization than the original network.

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 Liu, Y., Starzyk, J.A., Zhu, Z.: Optimizing number of hidden neurons in neural networks. EeC 1(1), 6 (2007) Liu, Y., Starzyk, J.A., Zhu, Z.: Optimizing number of hidden neurons in neural networks. EeC 1(1), 6 (2007)
2.
Zurück zum Zitat Amini, J.: Optimum learning rate in back-propagation neural network for classification of satellite images (IRS-1D). Sci. Iran. 15(6), 558–567 (2008) Amini, J.: Optimum learning rate in back-propagation neural network for classification of satellite images (IRS-1D). Sci. Iran. 15(6), 558–567 (2008)
3.
Zurück zum Zitat Castellano, G., Fanelli, A.M., Pelillo, M.: An iterative pruning algorithm for feedforward neural networks. IEEE Trans. Neural Netw. 8(3), 519–531 (1997)CrossRef Castellano, G., Fanelli, A.M., Pelillo, M.: An iterative pruning algorithm for feedforward neural networks. IEEE Trans. Neural Netw. 8(3), 519–531 (1997)CrossRef
4.
Zurück zum Zitat Lippmann, R.: An introduction to computing with neural nets. IEEE ASSP Mag. 4(2), 4–22 (1987)CrossRef Lippmann, R.: An introduction to computing with neural nets. IEEE ASSP Mag. 4(2), 4–22 (1987)CrossRef
5.
Zurück zum Zitat LeCun, Y.: Generalization and network design strategies. In: Connectionism in Perspective, vol. 19, pp. 143–155. Elsevier, Amsterdam (1989) LeCun, Y.: Generalization and network design strategies. In: Connectionism in Perspective, vol. 19, pp. 143–155. Elsevier, Amsterdam (1989)
6.
Zurück zum Zitat Herculano-Houzel, S.: The remarkable, yet not extraordinary, human brain as a scaled-up primate brain and its associated cost. Proc. Natl. Acad. Sci. 109(Suppl. 1), 10661–10668 (2012)CrossRef Herculano-Houzel, S.: The remarkable, yet not extraordinary, human brain as a scaled-up primate brain and its associated cost. Proc. Natl. Acad. Sci. 109(Suppl. 1), 10661–10668 (2012)CrossRef
7.
Zurück zum Zitat Sousa, A.M., Meyer, K.A., Santpere, G., Gulden, F.O., Sestan, N.: Evolution of the human nervous system function, structure, and development. Cell 170(2), 226–247 (2017)CrossRef Sousa, A.M., Meyer, K.A., Santpere, G., Gulden, F.O., Sestan, N.: Evolution of the human nervous system function, structure, and development. Cell 170(2), 226–247 (2017)CrossRef
8.
Zurück zum Zitat Wagarachchi, N.M., Karunananda, A.S.: Optimization of multi-layer artificial neural networks using delta values of hidden layers. In: IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, pp. 80–86 (2013) Wagarachchi, N.M., Karunananda, A.S.: Optimization of multi-layer artificial neural networks using delta values of hidden layers. In: IEEE Symposium on Computational Intelligence, Cognitive Algorithms, Mind, and Brain, pp. 80–86 (2013)
10.
Zurück zum Zitat Pascual-Leone, A., Amedi, A., Fregni, F., Merabet, L.B.: The plastic human brain cortex. Annu. Rev. Neurosci. 28, 377–401 (2005)CrossRef Pascual-Leone, A., Amedi, A., Fregni, F., Merabet, L.B.: The plastic human brain cortex. Annu. Rev. Neurosci. 28, 377–401 (2005)CrossRef
11.
Zurück zum Zitat Eggermont, J.J.: The Correlative Brain: Theory and Experiment in Neural Interaction. Springer, New York (1990)CrossRef Eggermont, J.J.: The Correlative Brain: Theory and Experiment in Neural Interaction. Springer, New York (1990)CrossRef
12.
Zurück zum Zitat Chrol-Cannon, J., Jin, Y.: Computational modeling of neural plasticity for self-organization of neural networks. BioSystems 125, 43–54 (2014)CrossRef Chrol-Cannon, J., Jin, Y.: Computational modeling of neural plasticity for self-organization of neural networks. BioSystems 125, 43–54 (2014)CrossRef
13.
Zurück zum Zitat Wells, R.B.: Cortical neurons and circuits: a tutorial introduction. Unpublished Paper (2005) www Mrc Uidaho Edu Wells, R.B.: Cortical neurons and circuits: a tutorial introduction. Unpublished Paper (2005) www Mrc Uidaho Edu
14.
Zurück zum Zitat Mountcastle, V.B.: The columnar organization of the neocortex. Brain 120(4), 701–722 (1997)CrossRef Mountcastle, V.B.: The columnar organization of the neocortex. Brain 120(4), 701–722 (1997)CrossRef
15.
Zurück zum Zitat Thomson, A.M.: Neocortical layer 6, a review. Front. Neuroanat. 4, 13 (2010) Thomson, A.M.: Neocortical layer 6, a review. Front. Neuroanat. 4, 13 (2010)
16.
Zurück zum Zitat Shaffer, J.: Neuroplasticity and positive psychology in clinical practice: a review for combined benefits. Psychology 3(12), 1110 (2012)CrossRef Shaffer, J.: Neuroplasticity and positive psychology in clinical practice: a review for combined benefits. Psychology 3(12), 1110 (2012)CrossRef
18.
Zurück zum Zitat LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRef LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)CrossRef
19.
Zurück zum Zitat Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)MathSciNetCrossRef Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)MathSciNetCrossRef
20.
Zurück zum Zitat Wagarachchi, M., Karunananda, A.: Optimization of artificial neural network architecture using neuroplasticity. Int. J. Artif. Intell. 15(1), 112–125 (2017) Wagarachchi, M., Karunananda, A.: Optimization of artificial neural network architecture using neuroplasticity. Int. J. Artif. Intell. 15(1), 112–125 (2017)
21.
Zurück zum Zitat Wagarachchi, N.M., Karunananda, A.S.: Novel technique for optimizing the hidden layer architecture in artificial neural networks. Am. Int. J. Res. Sci. Technol. Eng. Math. 4(1), 1–6 (2013) Wagarachchi, N.M., Karunananda, A.S.: Novel technique for optimizing the hidden layer architecture in artificial neural networks. Am. Int. J. Res. Sci. Technol. Eng. Math. 4(1), 1–6 (2013)
22.
Zurück zum Zitat Wagarachchi, N.M., Karunananda, A.S.: Towards a theoretical basis for modelling of hidden layer architecture in artificial neural networks. In: 2nd International Conference on Advances in Computing, Electronics and Communication, pp. 47–52 (2014) Wagarachchi, N.M., Karunananda, A.S.: Towards a theoretical basis for modelling of hidden layer architecture in artificial neural networks. In: 2nd International Conference on Advances in Computing, Electronics and Communication, pp. 47–52 (2014)
23.
Zurück zum Zitat Prechelt, L.: PROBEN 1: a set of benchmarks and benchmarking rules for neural network training algorithms. Univ., Fak. für Informatik (1994) Prechelt, L.: PROBEN 1: a set of benchmarks and benchmarking rules for neural network training algorithms. Univ., Fak. für Informatik (1994)
Metadaten
Titel
Modeling of Hidden Layer Architecture in Multilayer Artificial Neural Networks
verfasst von
Mihirini Wagarachchi
Asoka Karunananda
Copyright-Jahr
2019
Verlag
Springer Singapore
DOI
https://doi.org/10.1007/978-981-13-9129-3_5