Skip to main content

2016 | OriginalPaper | Buchkapitel

Collective Interpretation and Potential Joint Information Maximization

verfasst von : Ryotaro Kamimura

Erschienen in: Intelligent Information Processing VIII

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

The present paper aims to propose a new type of information-theoretic method called “potential joint information maximization”. The joint information maximization has an effect to reduce the number of jointly fired neurons and then to stabilize the production of final representations. Then, the final connection weights are collectively interpreted by averaging weights produced by different data sets. The method was applied to the data set of rebel participation among youths. The result show that final weights could be collectively interpreted and only one feature could be extracted. In addition, generalization performance could be improved.

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 Linsker, R.: Self-organization in a perceptual network. Computer 21(3), 105–117 (1988)CrossRef Linsker, R.: Self-organization in a perceptual network. Computer 21(3), 105–117 (1988)CrossRef
3.
Zurück zum Zitat Deco, G., Finnoff, W., Zimmermann, H.: Unsupervised mutual information criterion for elimination of overtraining in supervised multilayer networks. Neural Comput. 7(1), 86–107 (1995)CrossRef Deco, G., Finnoff, W., Zimmermann, H.: Unsupervised mutual information criterion for elimination of overtraining in supervised multilayer networks. Neural Comput. 7(1), 86–107 (1995)CrossRef
4.
Zurück zum Zitat Bell, A.J., Sejnowski, T.J.: An information-maximization approach to blind separation and blind deconvolution. Neural Comput. 7(6), 1129–1159 (1995)CrossRef Bell, A.J., Sejnowski, T.J.: An information-maximization approach to blind separation and blind deconvolution. Neural Comput. 7(6), 1129–1159 (1995)CrossRef
5.
Zurück zum Zitat Linsker, R.: Improved local learning rule for information maximization and related applications. Neural Netw. 18(3), 261–265 (2005)CrossRefMATH Linsker, R.: Improved local learning rule for information maximization and related applications. Neural Netw. 18(3), 261–265 (2005)CrossRefMATH
6.
Zurück zum Zitat Principe, J.C., Xu, D., Fisher, J.: Information theoretic learning. Unsupervised Adapt. Filtering 1, 265–319 (2000)MATH Principe, J.C., Xu, D., Fisher, J.: Information theoretic learning. Unsupervised Adapt. Filtering 1, 265–319 (2000)MATH
7.
Zurück zum Zitat Principe, J.C.: Information Theoretic Learning: Renyi’s Entropy and Kernel Perspectives. Information Science and Statistics. Springer, Heidelberg (2010)CrossRefMATH Principe, J.C.: Information Theoretic Learning: Renyi’s Entropy and Kernel Perspectives. Information Science and Statistics. Springer, Heidelberg (2010)CrossRefMATH
8.
Zurück zum Zitat Comon, P.: Independent component analysis: a new concept. Signal Process. 36, 287–314 (1994)CrossRefMATH Comon, P.: Independent component analysis: a new concept. Signal Process. 36, 287–314 (1994)CrossRefMATH
9.
Zurück zum Zitat Bell, A., Sejnowski, T.J.: An information-maximization approach to blind separation and blind deconvolution. Neural Comput. 7(6), 1129–1159 (1995)CrossRef Bell, A., Sejnowski, T.J.: An information-maximization approach to blind separation and blind deconvolution. Neural Comput. 7(6), 1129–1159 (1995)CrossRef
10.
Zurück zum Zitat Kamimura, R.: Self-organizing selective potentiality learning to detect important input neurons. In: 2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 1619–1626. IEEE (2015) Kamimura, R.: Self-organizing selective potentiality learning to detect important input neurons. In: 2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 1619–1626. IEEE (2015)
11.
Zurück zum Zitat Kamimura, R., Kitajima, R.: Selective potentiality maximization for input neuron selection in self-organizing maps. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2015) Kamimura, R., Kitajima, R.: Selective potentiality maximization for input neuron selection in self-organizing maps. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2015)
12.
Zurück zum Zitat Kamimura, R.: Supervised potentiality actualization learning for improving generalization performance. In: Proceedings on the International Conference on Artificial Intelligence (ICAI), p. 616, The Steering Committee of the World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp) (2015) Kamimura, R.: Supervised potentiality actualization learning for improving generalization performance. In: Proceedings on the International Conference on Artificial Intelligence (ICAI), p. 616, The Steering Committee of the World Congress in Computer Science, Computer Engineering and Applied Computing (WorldComp) (2015)
13.
Zurück zum Zitat Kitajima, R., Kamimura, R.: Simplifying potential learning by supposing maximum and minimum information for improved generalization and interpretation. In: 2015 International Conference on Modelling, Identification and Control (IASTED 2015) (2015) Kitajima, R., Kamimura, R.: Simplifying potential learning by supposing maximum and minimum information for improved generalization and interpretation. In: 2015 International Conference on Modelling, Identification and Control (IASTED 2015) (2015)
14.
Zurück zum Zitat Oyefusi, A.: Oil and the probability of rebel participation among youths in the niger delta of Nigeria. J. Peace Res. 45(4), 539–555 (2008)CrossRef Oyefusi, A.: Oil and the probability of rebel participation among youths in the niger delta of Nigeria. J. Peace Res. 45(4), 539–555 (2008)CrossRef
Metadaten
Titel
Collective Interpretation and Potential Joint Information Maximization
verfasst von
Ryotaro Kamimura
Copyright-Jahr
2016
DOI
https://doi.org/10.1007/978-3-319-48390-0_2

Premium Partner