Skip to main content

2020 | OriginalPaper | Buchkapitel

Neural Network Data Processing Technology Based on Deep Belief Networks

verfasst von : Viktor V. Krasnoproshin, Vadim V. Matskevich

Erschienen in: Open Semantic Technologies for Intelligent System

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

The paper provides approach for building neural network data processing technology based on deep belief networks. A neural network architecture, focused on parallel data processing and an original training algorithm implementing the annealing method, is proposed. The approach effectiveness is demonstrated by solving the image compression problem as an example.

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
8.
Zurück zum Zitat Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR, vol. 9, pp. 249–256 (2010) Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR, vol. 9, pp. 249–256 (2010)
9.
Zurück zum Zitat Golovko, V., Kroshenko, A.: Using deep belief neural networks to highlight semantically significant attributes. In: Proceedings of the 5-th International Conference - OSTIS 2015, pp. 481–486 (2015) Golovko, V., Kroshenko, A.: Using deep belief neural networks to highlight semantically significant attributes. In: Proceedings of the 5-th International Conference - OSTIS 2015, pp. 481–486 (2015)
11.
Zurück zum Zitat Krasnoproshin, V., Matskevich, V.: Effective data processing on heterogeneous computing devices. Bull. Brest State Tech. Univ. Ser. Phys. Math Comput. Sci. 113(5), 15–18 (2018) Krasnoproshin, V., Matskevich, V.: Effective data processing on heterogeneous computing devices. Bull. Brest State Tech. Univ. Ser. Phys. Math Comput. Sci. 113(5), 15–18 (2018)
12.
Zurück zum Zitat Krasnoproshin, V., Matskevich, V.: Algorithm for fast image compression on heterogeneous computing devices. In: Research Papers Collection Open Semantic Technologies for Intelligent Systems - OSTIS 2019, pp. 265–268 (2019) Krasnoproshin, V., Matskevich, V.: Algorithm for fast image compression on heterogeneous computing devices. In: Research Papers Collection Open Semantic Technologies for Intelligent Systems - OSTIS 2019, pp. 265–268 (2019)
13.
Zurück zum Zitat Krasnoproshin, V., Matskevich, V.: Statistical approach to image compression based on a restricted Boltzmann machine. In: Proceedings of the 12-th International Conference Computer Data Analysis and Modeling- CDAM 2019, pp. 207–213 (2019) Krasnoproshin, V., Matskevich, V.: Statistical approach to image compression based on a restricted Boltzmann machine. In: Proceedings of the 12-th International Conference Computer Data Analysis and Modeling- CDAM 2019, pp. 207–213 (2019)
14.
Zurück zum Zitat Locatelli, M.: Convergence properties of simulated annealing for continuous global optimization. J. Appl. Probab. 33(4), 1127–1140 (1996)MathSciNetCrossRef Locatelli, M.: Convergence properties of simulated annealing for continuous global optimization. J. Appl. Probab. 33(4), 1127–1140 (1996)MathSciNetCrossRef
15.
Zurück zum Zitat Matskevich, V., Krasnoproshin, V.: Annealing method in training restricted Boltzmann machine. In: Proceedings of the 14-th International Conference Pattern Recognition and Information Processing - PRIP 2019, pp. 264–268 (2019) Matskevich, V., Krasnoproshin, V.: Annealing method in training restricted Boltzmann machine. In: Proceedings of the 14-th International Conference Pattern Recognition and Information Processing - PRIP 2019, pp. 264–268 (2019)
17.
Zurück zum Zitat Rere, L.R., Fanany, M.I., Arymurthy, A.M.: Simulated annealing algorithm for deep learning. Procedia Comput. Sci. 72, 137–144 (2015)CrossRef Rere, L.R., Fanany, M.I., Arymurthy, A.M.: Simulated annealing algorithm for deep learning. Procedia Comput. Sci. 72, 137–144 (2015)CrossRef
18.
Zurück zum Zitat Temel, D., AlRegib, G.: Perceptual image quality assessment through spectral analysis of error representations. Sign. Process. Image Commun. 70, 37–46 (2019)CrossRef Temel, D., AlRegib, G.: Perceptual image quality assessment through spectral analysis of error representations. Sign. Process. Image Commun. 70, 37–46 (2019)CrossRef
20.
Zurück zum Zitat Treadgold, N., Gedeon, T.: Simulated annealing and weight decay in adaptive learning: the SARPROP algorithm. IEEE Trans. Neural Netw. 9(4), 662–668 (1998)CrossRef Treadgold, N., Gedeon, T.: Simulated annealing and weight decay in adaptive learning: the SARPROP algorithm. IEEE Trans. Neural Netw. 9(4), 662–668 (1998)CrossRef
21.
Zurück zum Zitat Zhou, X., Xu, L., Liu, S., Lin, Y., Zhang, L., Zhuo, C.: An efficient compressive convolutional network for unified object detection and image compression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 5949–5956 (2019) Zhou, X., Xu, L., Liu, S., Lin, Y., Zhang, L., Zhuo, C.: An efficient compressive convolutional network for unified object detection and image compression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 5949–5956 (2019)
Metadaten
Titel
Neural Network Data Processing Technology Based on Deep Belief Networks
verfasst von
Viktor V. Krasnoproshin
Vadim V. Matskevich
Copyright-Jahr
2020
DOI
https://doi.org/10.1007/978-3-030-60447-9_15

Premium Partner