Skip to main content

2016 | OriginalPaper | Buchkapitel

Semi-supervised Learning for Convolutional Neural Networks Using Mild Supervisory Signals

verfasst von : Takashi Shinozaki

Erschienen in: Neural Information Processing

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

We propose a novel semi-supervised learning method for convolutional neural networks (CNNs). CNN is one of the most popular models for deep learning and its successes among various types of applications include image and speech recognition, image captioning, and the game of ‘go’. However, the requirement for a vast amount of labeled data for supervised learning in CNNs is a serious problem. Unsupervised learning, which uses the information of unlabeled data, might be key to addressing the problem, although it has not been investigated sufficiently in CNN regimes. The proposed method involves both supervised and unsupervised learning in identical feedforward networks, and enables seamless switching among them. We validated the method using an image recognition task. The results showed that learning using non-labeled data dramatically improves the efficiency of supervised learning.

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 LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Jackel, L.D.: Backpropagation applied to hand-written zip code recognition. Neural Comput. 1(4), 541–551 (1989)CrossRef LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Jackel, L.D.: Backpropagation applied to hand-written zip code recognition. Neural Comput. 1(4), 541–551 (1989)CrossRef
2.
Zurück zum Zitat Krizhevsky, A., Sutskerver, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1106–1114 (2012) Krizhevsky, A., Sutskerver, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1106–1114 (2012)
3.
Zurück zum Zitat Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30–42 (2012)CrossRef Dahl, G.E., Yu, D., Deng, L., Acero, A.: Context-dependent pre-trained deep neural networks for large vocabulary speech recognition. IEEE Trans. Audio Speech Lang. Process. 20(1), 30–42 (2012)CrossRef
4.
Zurück zum Zitat Fukushima, K.: Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)CrossRefMATH Fukushima, K.: Neocognitron: a self organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)CrossRefMATH
5.
6.
Zurück zum Zitat Le, Q.V., Ranzato, M.A., Monga, R., Devin, M., Chen, K., Corrado, G.S., Dean, J., Ng, A.Y.: Building high-level features using large scale unsupervised learning. In: Proceedings of the 29th International Conference on Machine Learning (2012) Le, Q.V., Ranzato, M.A., Monga, R., Devin, M., Chen, K., Corrado, G.S., Dean, J., Ng, A.Y.: Building high-level features using large scale unsupervised learning. In: Proceedings of the 29th International Conference on Machine Learning (2012)
7.
Zurück zum Zitat Radford, A., Metz, L.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: IPLR 2016 (2016) Radford, A., Metz, L.: Unsupervised representation learning with deep convolutional generative adversarial networks. In: IPLR 2016 (2016)
8.
Zurück zum Zitat Goroshin, R., Bruna, J., Tompson, J., Eigen, D., LeCun, Y.: Unsupervised Learning of Spatiotemporally Coherent Metrics, arXiv:1412.6056 (2015) Goroshin, R., Bruna, J., Tompson, J., Eigen, D., LeCun, Y.: Unsupervised Learning of Spatiotemporally Coherent Metrics, arXiv:​1412.​6056 (2015)
9.
Zurück zum Zitat Bengio, Y., Lambling, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. Adv. Neural Inf. Process. Syst. 19, 153–160 (2007) Bengio, Y., Lambling, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. Adv. Neural Inf. Process. Syst. 19, 153–160 (2007)
10.
Zurück zum Zitat Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: Proceedings of the 4th International Conference on Learning Representations (2015) Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: Proceedings of the 4th International Conference on Learning Representations (2015)
11.
Zurück zum Zitat Bottou, L.: Online algorithms and stochastic approximations. In: Online Learning and Neural Networks. Cambridge University Press (1998) Bottou, L.: Online algorithms and stochastic approximations. In: Online Learning and Neural Networks. Cambridge University Press (1998)
12.
Zurück zum Zitat LeCun, Y., Cortes, C., Barges, C.J.C.: The MNIST database of handwritten digits (1998) LeCun, Y., Cortes, C., Barges, C.J.C.: The MNIST database of handwritten digits (1998)
13.
Zurück zum Zitat Tokui, S., Oono, K., Hido, S., Clayton, J.: Chainer: a next-generation open source framework for deep learning. In: NIPS (2015) Tokui, S., Oono, K., Hido, S., Clayton, J.: Chainer: a next-generation open source framework for deep learning. In: NIPS (2015)
14.
Zurück zum Zitat Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998) Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)
Metadaten
Titel
Semi-supervised Learning for Convolutional Neural Networks Using Mild Supervisory Signals
verfasst von
Takashi Shinozaki
Copyright-Jahr
2016
DOI
https://doi.org/10.1007/978-3-319-46681-1_46