Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
A Novel Approach for Mobile Robot Localization in Topological Maps Using Classification with Reject Option from Structural Co-occurrence Matrix Read chapter Read first chapter

2017 | OriginalPaper | Chapter

Deep Boltzmann Machines Using Adaptive Temperatures

Authors : Leandro A. Passos Júnior, Kelton A. P. Costa, João P. Papa

Published in: Computer Analysis of Images and Patterns

Publisher: Springer International Publishing

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Deep learning has been considered a hallmark in a number of applications recently. Among those techniques, the ones based on Restricted Boltzmann Machines have attracted a considerable attention, since they are energy-driven models composed of latent variables that aim at learning the probability distribution of the input data. In a nutshell, the training procedure of such models concerns the minimization of the energy of each training sample in order to increase its probability. Therefore, such optimization process needs to be regularized in order to reach the best trade-off between exploitation and exploration. In this work, we propose an adaptive regularization approach based on temperatures, and we show its advantages considering Deep Belief Networks (DBNs) and Deep Boltzmann Machines (DBMs). The proposed approach is evaluated in the context of binary image reconstruction, thus outperforming temperature-fixed DBNs and DBMs.

Dont have a licence yet? Then find out more about our products and how to get one now:

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!

inform now

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!

inform now

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!

inform now
previous chapter On the Essence of Unsupervised Detection of Anomalous Motion in Surveillance Videos
next chapter Twin Deep Convolutional Neural Network for Example-Based Image Colorization
Footnotes
2
The images are originally available in grayscale with resolution of \(28\times 28\), but they were reduced to \(14\times 14\) images.
 
3
The original training set was reduced to \(2\%\) of its former size, which corresponds to 1, 200 images.
 
5
Since this architecture has been commonly employed in several works in the literature, we opted to employ it in our work either.
 
6
One sampling iteration was used for all learning algorithms.
 
Literature
1.
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRef
2.
3.
Salakhutdinov, R., Hinton, G.E.: An efficient learning procedure for deep Boltzmann machines. Neural Comput. 24(8), 1967–2006 (2012)MathSciNetCrossRefMATH
4.
Wan, L., Zeiler, M., Zhang, S., LeCun, Y., Fergus, R.: Regularization of neural networks using dropconnect. In: Dasgupta, S., Mcallester, D. (eds.) Proceedings of the 30th International Conference on Machine Learning. JMLR Workshop and Conference Proceedings, ICML 2013, vol. 28, no. 3, pp. 1058–1066 (2013)
5.
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetMATH
6.
Papa, J.P., Rosa, G.H., Costa, K.A.P., Marana, A.N., Scheirer, W., Cox, D.D.: On the model selection of Bernoulli restricted Boltzmann machines through harmony search. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2015, pp. 1449–1450. ACM, New York (2015)
7.
Papa, J.P., Rosa, G.H., Yang, X.-S.: Quaternion-driven deep belief networks fine-tuning. Applied Soft Computing (2016) (submitted)
8.
Papa, J.P., Rosa, G.H., Marana, A.N., Scheirer, W., Cox, D.D.: Model selection for discriminative restricted Boltzmann machines through meta-heuristic techniques. J. Comput. Sci. 9, 14–18 (2015)CrossRef
9.
Rosa, G.H., Papa, J.P., Marana, A.N., Scheirer, W., Cox, D.D.: Fine-tuning convolutional neural networks using harmony search. In: Pardo, A., Kittler, J. (eds.) IARP 2015. LNCS, vol. 9423, pp. 683–690. Springer, Cham (2015)
10.
Papa, J.P., Scheirer, W., Cox, D.D.: Fine-tuning deep belief networks using harmony search. Appl. Soft Comput. 46, 875–885 (2016)CrossRef
11.
Li, G., Deng, L., Xu, Y., Wen, C., Wang, W., Pei, J., Shi, L.: Temperature based restricted Boltzmann machines. Sci. Rep. 6, 1–12 (2016)CrossRef
12.
13.
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771–1800 (2002)CrossRefMATH
14.
Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics Bull. 1(6), 80–83 (1945)CrossRef
15.
Tieleman, T.: Training restricted Boltzmann machines using approximations to the likelihood gradient. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1064–1071. ACM, New York (2008)
Metadata
Title
Deep Boltzmann Machines Using Adaptive Temperatures
Authors
Leandro A. Passos Júnior
Kelton A. P. Costa
João P. Papa
Copyright Year
2017
Book
Computer Analysis of Images and Patterns

Print ISBN: 978-3-319-64688-6

Electronic ISBN: 978-3-319-64689-3

Copyright Year: 2017

DOI
https://doi.org/10.1007/978-3-319-64689-3_14

Premium Partner

    Image Credits