Skip to main content

2018 | OriginalPaper | Buchkapitel

Neural Networks Saturation Reduction

verfasst von : Janusz Kolbusz, Pawel Rozycki, Oleksandr Lysenko, 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

The saturation of particular neuron and a whole neural network is one of the reasons for problems with training effectiveness. The paper shows neural network saturation analysis, proposes a method for detection of saturated neurons and its reduction to achieve better training performance. The proposed approach has been confirmed by several experiments.

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 Rozycki, P., Kolbusz, J., Wilamowski, B.M.: Dedicated deep neural network architectures and methods for their training. In: IEEE 19th International Conference on Intelligent Engineering Systems (INES 2015) Bratislava, 3–5 September 2015, pp. 73–78 (2015) Rozycki, P., Kolbusz, J., Wilamowski, B.M.: Dedicated deep neural network architectures and methods for their training. In: IEEE 19th International Conference on Intelligent Engineering Systems (INES 2015) Bratislava, 3–5 September 2015, pp. 73–78 (2015)
2.
3.
Zurück zum Zitat Mohamed, A., Dahl, G.E., Hinton, G.E.: Acoustic modeling using deep belief networks. IEEE Trans. Audio Speech Lang. Process. 20, 14–22 (2012)CrossRef Mohamed, A., Dahl, G.E., Hinton, G.E.: Acoustic modeling using deep belief networks. IEEE Trans. Audio Speech Lang. Process. 20, 14–22 (2012)CrossRef
4.
Zurück zum Zitat Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012) Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
5.
Zurück zum Zitat Simonyan K., Zisserman A.: Very deep convolutional networks for largescale image recognition. arXiv preprint arXiv:1409.1556 (2014) Simonyan K., Zisserman A.: Very deep convolutional networks for largescale image recognition. arXiv preprint arXiv:​1409.​1556 (2014)
6.
Zurück zum Zitat Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)CrossRef Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)CrossRef
7.
Zurück zum Zitat Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)CrossRef Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)CrossRef
8.
Zurück zum Zitat Wilamowski, B.M., Yu, H.: Neural network learning without backpropagation. IEEE Trans. Neural Netw. 21(11), 1793–1803 (2010)CrossRef Wilamowski, B.M., Yu, H.: Neural network learning without backpropagation. IEEE Trans. Neural Netw. 21(11), 1793–1803 (2010)CrossRef
9.
Zurück zum Zitat Hunter, D., Hao, Y., Pukish, M.S., Kolbusz, J., Wilamowski, B.M.: Selection of proper neural network sizes and architectures—A comparative study. IEEE Trans. Industr. Inf. 8, 228–240 (2012)CrossRef Hunter, D., Hao, Y., Pukish, M.S., Kolbusz, J., Wilamowski, B.M.: Selection of proper neural network sizes and architectures—A comparative study. IEEE Trans. Industr. Inf. 8, 228–240 (2012)CrossRef
10.
Zurück zum Zitat Hochreiter, S.: The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int. J. Uncertain. Fuzz. Knowl. Based Syst. 06, 107 (1998)MATHCrossRef Hochreiter, S.: The vanishing gradient problem during learning recurrent neural nets and problem solutions. Int. J. Uncertain. Fuzz. Knowl. Based Syst. 06, 107 (1998)MATHCrossRef
11.
Zurück zum Zitat Larochelle, H., et al.: Exploring strategies for training deep neural networks. J. Mach. Learn. Res. 10(Jan), 1–40 (2009)MATH Larochelle, H., et al.: Exploring strategies for training deep neural networks. J. Mach. Learn. Res. 10(Jan), 1–40 (2009)MATH
12.
Zurück zum Zitat He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: ICCV (2015) He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: ICCV (2015)
13.
Zurück zum Zitat Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is dificult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)CrossRef Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is dificult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)CrossRef
14.
Zurück zum Zitat Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Articial Intelligence and Statistics, pp. 249–256 (2010) Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Articial Intelligence and Statistics, pp. 249–256 (2010)
15.
16.
Zurück zum Zitat Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: ICML (2015) Ioffe, S., Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: ICML (2015)
18.
Zurück zum Zitat Kolbusz J., Różycki P., Wilamowski B.M.: The study of architecture MLP with linear neurons in order to eliminate the “vanishing gradient” problem. In: Artificial Intelligence and Soft Computing, ICAISC 2017, pp. 97–106 (2017) Kolbusz J., Różycki P., Wilamowski B.M.: The study of architecture MLP with linear neurons in order to eliminate the “vanishing gradient” problem. In: Artificial Intelligence and Soft Computing, ICAISC 2017, pp. 97–106 (2017)
19.
Zurück zum Zitat Rakitianskaia, A., Engelbrecht, A.: Measuring saturation in neural networks. In: 2015 IEEE Symposium Series on Computational Intelligence, Cape Town, pp. 1423–1430 (2015) Rakitianskaia, A., Engelbrecht, A.: Measuring saturation in neural networks. In: 2015 IEEE Symposium Series on Computational Intelligence, Cape Town, pp. 1423–1430 (2015)
21.
Zurück zum Zitat Rakitianskaia, A., Engelbrecht, A.: Training high-dimensional neural networks with cooperative particle swarm optimiser. In: 2014 International Joint Conference on Neural Networks (IJCNN), Beijing, pp. 4011–4018 (2014) Rakitianskaia, A., Engelbrecht, A.: Training high-dimensional neural networks with cooperative particle swarm optimiser. In: 2014 International Joint Conference on Neural Networks (IJCNN), Beijing, pp. 4011–4018 (2014)
22.
Zurück zum Zitat Wilamowski, B.M., Yu, H.: Improved computation for levenberg Marquardt training. IEEE Trans. Neural Netw. 21(6), 930–937 (2010)CrossRef Wilamowski, B.M., Yu, H.: Improved computation for levenberg Marquardt training. IEEE Trans. Neural Netw. 21(6), 930–937 (2010)CrossRef
Metadaten
Titel
Neural Networks Saturation Reduction
verfasst von
Janusz Kolbusz
Pawel Rozycki
Oleksandr Lysenko
Bogdan M. Wilamowski
Copyright-Jahr
2018
DOI
https://doi.org/10.1007/978-3-319-91253-0_11