Skip to main content

2016 | OriginalPaper | Buchkapitel

Parallel Learning of Feedforward Neural Networks Without Error Backpropagation

verfasst von : Jarosław Bilski, Bogdan M. Wilamowski

Erschienen in: Artificial Intelligence and Soft Computing

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

A parallel architecture of the steepest descent algorithm for training fully connected feedforward neural networks is presented. This solution is based on a new idea of learning neural networks without error backpropagation. The proposed solution is based on completely new parallel structures to effectively reduce high computational load of this algorithm. Detailed parallel 2D and 3D neural network learning structures are explicitely discussed.

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 Bilski, J.: The UD RLS algorithm for training the feedforward neural networks. Int. J. Appl. Math. Comput. Sci. 15(1), 101–109 (2005)MATH Bilski, J.: The UD RLS algorithm for training the feedforward neural networks. Int. J. Appl. Math. Comput. Sci. 15(1), 101–109 (2005)MATH
2.
Zurück zum Zitat Bilski, J., Litwiński, S., Smola̧g, J.: Parallel realisation of QR algorithm for neural networks learning. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol. 3070, pp. 158–165. Springer, Heidelberg (2004)CrossRef Bilski, J., Litwiński, S., Smola̧g, J.: Parallel realisation of QR algorithm for neural networks learning. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol. 3070, pp. 158–165. Springer, Heidelberg (2004)CrossRef
3.
Zurück zum Zitat Bilski, J., Smola̧g, J.: Parallel realisation of the recurrent RTRN neural network learning. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2008. LNCS (LNAI), vol. 5097, pp. 11–16. Springer, Heidelberg (2008)CrossRef Bilski, J., Smola̧g, J.: Parallel realisation of the recurrent RTRN neural network learning. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2008. LNCS (LNAI), vol. 5097, pp. 11–16. Springer, Heidelberg (2008)CrossRef
4.
Zurück zum Zitat Bilski, J., Smola̧g, J.: Parallel realisation of the recurrent Elman neural network learning. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010, Part II. LNCS, vol. 6114, pp. 19–25. Springer, Heidelberg (2010)CrossRef Bilski, J., Smola̧g, J.: Parallel realisation of the recurrent Elman neural network learning. In: Rutkowski, L., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2010, Part II. LNCS, vol. 6114, pp. 19–25. Springer, Heidelberg (2010)CrossRef
5.
Zurück zum Zitat Bilski, J., Smola̧g, J.: Parallel realisation of the recurrent multi layer perceptron learning. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2012, Part I. LNCS, vol. 7267, pp. 12–20. Springer, Heidelberg (2012)CrossRef Bilski, J., Smola̧g, J.: Parallel realisation of the recurrent multi layer perceptron learning. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2012, Part I. LNCS, vol. 7267, pp. 12–20. Springer, Heidelberg (2012)CrossRef
6.
Zurück zum Zitat Bilski, J., Smola̧g, J.: Parallel approach to learning of the recurrent Jordan neural network. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013, Part I. LNCS, vol. 7894, pp. 32–40. Springer, Heidelberg (2013)CrossRef Bilski, J., Smola̧g, J.: Parallel approach to learning of the recurrent Jordan neural network. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2013, Part I. LNCS, vol. 7894, pp. 32–40. Springer, Heidelberg (2013)CrossRef
7.
Zurück zum Zitat Bilski, J.: Parallel Structures for Feedforward and Dynamical Neural Networks (in Polish). AOW EXIT (2013) Bilski, J.: Parallel Structures for Feedforward and Dynamical Neural Networks (in Polish). AOW EXIT (2013)
8.
Zurück zum Zitat Bilski, J., Smola̧, J., Galushkin, A.I.: The parallel approach to the conjugate gradient learning algorithm for the feedforward neural networks. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2014, Part I. LNCS, vol. 8467, pp. 12–21. Springer, Heidelberg (2014)CrossRef Bilski, J., Smola̧, J., Galushkin, A.I.: The parallel approach to the conjugate gradient learning algorithm for the feedforward neural networks. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2014, Part I. LNCS, vol. 8467, pp. 12–21. Springer, Heidelberg (2014)CrossRef
9.
Zurück zum Zitat Bilski, J., Smola̧g, J.: Parallel architectures for learning the rtrn and elman dynamic neural networks. IEEE Trans. Parallel Distrib. Syst. 26(9), 2561–2570 (2015)CrossRef Bilski, J., Smola̧g, J.: Parallel architectures for learning the rtrn and elman dynamic neural networks. IEEE Trans. Parallel Distrib. Syst. 26(9), 2561–2570 (2015)CrossRef
10.
Zurück zum Zitat Bilski, J., Smola̧, J., Żurada, J.M.: Parallel approach to the levenberg-marquardt learning algorithm for feedforward neural networks. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) Artificial Intelligence and Soft Computing. LNCS(LNAI), vol. 9119, pp. 3–14. Springer, Heidelberg (2015)CrossRef Bilski, J., Smola̧, J., Żurada, J.M.: Parallel approach to the levenberg-marquardt learning algorithm for feedforward neural networks. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) Artificial Intelligence and Soft Computing. LNCS(LNAI), vol. 9119, pp. 3–14. Springer, Heidelberg (2015)CrossRef
11.
Zurück zum Zitat Cpałka, K., Łapa, K., Przybył, A., Zalasiński, M.: A new method for designing neuro-fuzzy systems for nonlinear modelling with interpretability aspects. Neurocomputing 135, 203–217 (2014)CrossRef Cpałka, K., Łapa, K., Przybył, A., Zalasiński, M.: A new method for designing neuro-fuzzy systems for nonlinear modelling with interpretability aspects. Neurocomputing 135, 203–217 (2014)CrossRef
12.
Zurück zum Zitat Fahlman, S.: Faster learning variations on backpropagation: an empirical study. In: Proceedings of Connectionist Models Summer School, Los Atos (1988) Fahlman, S.: Faster learning variations on backpropagation: an empirical study. In: Proceedings of Connectionist Models Summer School, Los Atos (1988)
13.
Zurück zum Zitat Hagan, M.T., Menhaj, M.B.: Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neuralnetworks 5(6), 989–993 (1994) Hagan, M.T., Menhaj, M.B.: Training feedforward networks with the Marquardt algorithm. IEEE Trans. Neuralnetworks 5(6), 989–993 (1994)
14.
Zurück zum Zitat Knop, M., Kapuściński, T., Mleczko, W.: Video key frame detection based on the restricted Boltzmann machine. J. Appl. Math. Comput. Mech. 14(3), 49–58 (2016)CrossRef Knop, M., Kapuściński, T., Mleczko, W.: Video key frame detection based on the restricted Boltzmann machine. J. Appl. Math. Comput. Mech. 14(3), 49–58 (2016)CrossRef
15.
Zurück zum Zitat Korytkowski, M., Rutkowski, L., Scherer, R.: Fast image classification by boosting fuzzy classifiers. Inf. Sci. 327, 175–182 (2016)MathSciNetCrossRef Korytkowski, M., Rutkowski, L., Scherer, R.: Fast image classification by boosting fuzzy classifiers. Inf. Sci. 327, 175–182 (2016)MathSciNetCrossRef
16.
Zurück zum Zitat Korytkowski, M., Scherer, R., Rutkowski, L.: On Combining backpropagation with boosting. computational collective intelligence. In: 2006 International Joint Conference on Neural Networks, IEEE World Congress on Computational Intelligence, pp. 1274–127. Vancouver, BC, Canada (2006) Korytkowski, M., Scherer, R., Rutkowski, L.: On Combining backpropagation with boosting. computational collective intelligence. In: 2006 International Joint Conference on Neural Networks, IEEE World Congress on Computational Intelligence, pp. 1274–127. Vancouver, BC, Canada (2006)
17.
Zurück zum Zitat Nowak, B., Nowicki, R., Starczewski, J.: The learning of neuro-fuzzy classifier with fuzzy rough sets for imprecise datasets. Artifi. Intell. Soft Comput. 8467, 256–266 (2014) Nowak, B., Nowicki, R., Starczewski, J.: The learning of neuro-fuzzy classifier with fuzzy rough sets for imprecise datasets. Artifi. Intell. Soft Comput. 8467, 256–266 (2014)
18.
Zurück zum Zitat Riedmiller, M., Braun, H.: A direct method for faster backpropagation learning: the RPROP algorithm. In: IEEE International Conference on Neural Networks. IEEE, San Francisco (1993) Riedmiller, M., Braun, H.: A direct method for faster backpropagation learning: the RPROP algorithm. In: IEEE International Conference on Neural Networks. IEEE, San Francisco (1993)
19.
Zurück zum Zitat Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McCelland, J. (red.) Parallel Distributed Processing, vol. 1, chap. 8. The MIT Press, Cambridge, Massachusetts (1986) Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Rumelhart, D.E., McCelland, J. (red.) Parallel Distributed Processing, vol. 1, chap. 8. The MIT Press, Cambridge, Massachusetts (1986)
20.
Zurück zum Zitat Rutkowski, L., Jaworski, M., Pietruczuk, L., Duda, P.: Decision trees for mining data streams based on the gaussian approximation. IEEE Trans. Knowl. Data Eng. 26(1), 108–119 (2014)CrossRef Rutkowski, L., Jaworski, M., Pietruczuk, L., Duda, P.: Decision trees for mining data streams based on the gaussian approximation. IEEE Trans. Knowl. Data Eng. 26(1), 108–119 (2014)CrossRef
21.
Zurück zum Zitat Rutkowski, L., Jaworski, M., Pietruczuk, L., Duda, P.: A new method for data stream mining based on the misclassification error. IEEE Trans. Neural Netw. Learn. Syst. 26(5), 1048–1059 (2015)MathSciNetCrossRef Rutkowski, L., Jaworski, M., Pietruczuk, L., Duda, P.: A new method for data stream mining based on the misclassification error. IEEE Trans. Neural Netw. Learn. Syst. 26(5), 1048–1059 (2015)MathSciNetCrossRef
22.
Zurück zum Zitat Rutkowski, L., Pietruczuk, L., Duda, P., Jaworski, M.: Decision trees for mining data streams based on the McDiarmid’s bound. IEEE Trans. Knowl. Data Eng. 25(6), 1272–1279 (2013)CrossRef Rutkowski, L., Pietruczuk, L., Duda, P., Jaworski, M.: Decision trees for mining data streams based on the McDiarmid’s bound. IEEE Trans. Knowl. Data Eng. 25(6), 1272–1279 (2013)CrossRef
23.
Zurück zum Zitat Rutkowski, L., Jaworski, M., Pietruczuk, L., Duda, P.: The CART Decision Trees for Mining Data Streams. Inf. Sci. 266, 1–15 (2014)CrossRef Rutkowski, L., Jaworski, M., Pietruczuk, L., Duda, P.: The CART Decision Trees for Mining Data Streams. Inf. Sci. 266, 1–15 (2014)CrossRef
24.
Zurück zum Zitat Smola̧g, J., Bilski, J.: A systolic array for fast learning of neural networks. In: Proceedings of Fifth Conference on Neural Networks and Soft Computing, pp. 754–758. Zakopane (2000) Smola̧g, J., Bilski, J.: A systolic array for fast learning of neural networks. In: Proceedings of Fifth Conference on Neural Networks and Soft Computing, pp. 754–758. Zakopane (2000)
25.
Zurück zum Zitat Smola̧g, J., Rutkowski, L., Bilski, J.: Systolic array for neural networks. In: Proceedings of the fourth Conference on Neural Networks and their Applications, pp. 487–497. Zakopane (1999) Smola̧g, J., Rutkowski, L., Bilski, J.: Systolic array for neural networks. In: Proceedings of the fourth Conference on Neural Networks and their Applications, pp. 487–497. Zakopane (1999)
27.
Zurück zum Zitat Tadeusiewicz, R.: Neural Networks (in Polish). AOW RM (1993) Tadeusiewicz, R.: Neural Networks (in Polish). AOW RM (1993)
28.
Zurück zum Zitat Werbos, J.: Backpropagation through time: what it does and how to do it. Proc. IEEE 78(10), 1550–1560 (1990)CrossRef Werbos, J.: Backpropagation through time: what it does and how to do it. Proc. IEEE 78(10), 1550–1560 (1990)CrossRef
29.
Zurück zum Zitat Wilamowski, B.M., Yo, H.: Neural network learning without backpropagation. IEEE Trans Neural Netw. 21(11), 1793–1803 (2010)CrossRef Wilamowski, B.M., Yo, H.: Neural network learning without backpropagation. IEEE Trans Neural Netw. 21(11), 1793–1803 (2010)CrossRef
30.
Zurück zum Zitat Wilamowski, B.M., Yo, H.: Improved Computation For Levenberg–Marquardt Training. IEEE Trans. Neural Netw. 21(6), 930–937 (2010)CrossRef Wilamowski, B.M., Yo, H.: Improved Computation For Levenberg–Marquardt Training. IEEE Trans. Neural Netw. 21(6), 930–937 (2010)CrossRef
31.
Zurück zum Zitat Yo, H., Reiner, P.D., Xie, T., Bartczak, T., Wilamowski, B.M.: An incremental design of radial basis function networks. IEEE Trans. Neural Netw. Learn. Syst. 25(10), 1793–1803 (2014)CrossRef Yo, H., Reiner, P.D., Xie, T., Bartczak, T., Wilamowski, B.M.: An incremental design of radial basis function networks. IEEE Trans. Neural Netw. Learn. Syst. 25(10), 1793–1803 (2014)CrossRef
Metadaten
Titel
Parallel Learning of Feedforward Neural Networks Without Error Backpropagation
verfasst von
Jarosław Bilski
Bogdan M. Wilamowski
Copyright-Jahr
2016
DOI
https://doi.org/10.1007/978-3-319-39378-0_6

Premium Partner