Skip to main content

2021 | OriginalPaper | Buchkapitel

Membership-Mappings for Data Representation Learning: A Bregman Divergence Based Conditionally Deep Autoencoder

verfasst von : Mohit Kumar, Bernhard Moser, Lukas Fischer, Bernhard Freudenthaler

Erschienen in: Database and Expert Systems Applications - DEXA 2021 Workshops

Verlag: Springer International Publishing

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

search-config
loading …

Abstract

This paper suggests to use membership-mapping as the building block of deep models. An alternative idea of deep autoencoder, referred to as Bregman Divergence Based Conditionally Deep Autoencoder (that consists of layers such that each layer learns data representation at certain abstraction level through a membership-mappings based autoencoder), is presented. A multi-class classifier is presented that employs a parallel composition of conditionally deep autoencoders to learn data representation for each class. Experiments are provided to demonstrate the competitive performance of the proposed framework in classifying high-dimensional feature vectors and in rendering robustness to the classification.

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
2.
Zurück zum Zitat Kumar, M., Freudenthaler, B.: Fuzzy membership functional analysis for nonparametric deep models of image features. IEEE Trans. Fuzzy Syst. 28(12), 3345–3359 (2020) Kumar, M., Freudenthaler, B.: Fuzzy membership functional analysis for nonparametric deep models of image features. IEEE Trans. Fuzzy Syst. 28(12), 3345–3359 (2020)
3.
Zurück zum Zitat Kumar, M., Insan, A., Stoll, N., Thurow, K., Stoll, R.: Stochastic fuzzy modeling for ear imaging based child identification. IEEE Trans. Syst. Man Cybern. Syst. 46(9), 1265–1278 (2016)CrossRef Kumar, M., Insan, A., Stoll, N., Thurow, K., Stoll, R.: Stochastic fuzzy modeling for ear imaging based child identification. IEEE Trans. Syst. Man Cybern. Syst. 46(9), 1265–1278 (2016)CrossRef
4.
Zurück zum Zitat Kumar, M., et al.: Stress monitoring based on stochastic fuzzy analysis of heartbeat intervals. IEEE Trans. Fuzzy Syst. 20(4), 746–759 (2012)CrossRef Kumar, M., et al.: Stress monitoring based on stochastic fuzzy analysis of heartbeat intervals. IEEE Trans. Fuzzy Syst. 20(4), 746–759 (2012)CrossRef
5.
Zurück zum Zitat Kumar, M., Stoll, N., Stoll, R.: Variational bayes for a mixed stochastic/deterministic fuzzy filter. IEEE Trans. Fuzzy Syst. 18(4), 787–801 (2010)CrossRef Kumar, M., Stoll, N., Stoll, R.: Variational bayes for a mixed stochastic/deterministic fuzzy filter. IEEE Trans. Fuzzy Syst. 18(4), 787–801 (2010)CrossRef
6.
Zurück zum Zitat Kumar, M., Stoll, N., Stoll, R.: Stationary fuzzy Fokker-Planck learning and stochastic fuzzy filtering. IEEE Trans. Fuzzy Syst. 19(5), 873–889 (2011)CrossRef Kumar, M., Stoll, N., Stoll, R.: Stationary fuzzy Fokker-Planck learning and stochastic fuzzy filtering. IEEE Trans. Fuzzy Syst. 19(5), 873–889 (2011)CrossRef
8.
Zurück zum Zitat Kumar, M., Moser, B., Fischer, L., Freudenthaler, B.: Membership-mappings for data representation learning: measure theoretic conceptualization. In: Database and Expert Systems Applications (DEXA 2021). Springer, Cham (2021, in press) Kumar, M., Moser, B., Fischer, L., Freudenthaler, B.: Membership-mappings for data representation learning: measure theoretic conceptualization. In: Database and Expert Systems Applications (DEXA 2021). Springer, Cham (2021, in press)
9.
Zurück zum Zitat Kumar, M., Rossbory, M., Moser, B.A., Freudenthaler, B.: Differentially private learning of distributed deep models. In: Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2020 Adjunct, pp. 193–200. Association for Computing Machinery, New York (2020) Kumar, M., Rossbory, M., Moser, B.A., Freudenthaler, B.: Differentially private learning of distributed deep models. In: Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization, UMAP 2020 Adjunct, pp. 193–200. Association for Computing Machinery, New York (2020)
10.
Zurück zum Zitat Kumar, M., Rossbory, M., Moser, B.A., Freudenthaler, B.: An optimal \((\epsilon ,\delta )-\)differentially private learning of distributed deep fuzzy models. Inf. Sci. 546, 87–120 (2021) Kumar, M., Rossbory, M., Moser, B.A., Freudenthaler, B.: An optimal \((\epsilon ,\delta )-\)differentially private learning of distributed deep fuzzy models. Inf. Sci. 546, 87–120 (2021)
11.
Zurück zum Zitat Kumar, M., Singh, S., Freudenthaler, B.: Gaussian fuzzy theoretic analysis for variational learning of nested compositions. Int. J. Approximate Reasoning 131, 1–29 (2021)MathSciNetCrossRef Kumar, M., Singh, S., Freudenthaler, B.: Gaussian fuzzy theoretic analysis for variational learning of nested compositions. Int. J. Approximate Reasoning 131, 1–29 (2021)MathSciNetCrossRef
Metadaten
Titel
Membership-Mappings for Data Representation Learning: A Bregman Divergence Based Conditionally Deep Autoencoder
verfasst von
Mohit Kumar
Bernhard Moser
Lukas Fischer
Bernhard Freudenthaler
Copyright-Jahr
2021
DOI
https://doi.org/10.1007/978-3-030-87101-7_14

Premium Partner