• English
  • Deutsch
  • Log In
    Password Login
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. tanh Neurons are Bayesian Decision Makers
 
  • Details
  • Full
Options
2021
Conference Paper
Titel

tanh Neurons are Bayesian Decision Makers

Abstract
The hyperbolic tangent (tanh) is a traditional choice for the activation function of the neurons of an artificial neural network. Here, we go through a simple calculation that shows that this modeling choice is linked to Bayesian decision theory. Our brief, tutorial-like discussion is intended as a reference to an observation rarely mentioned in standard textbooks.
Author(s)
Bauckhage, Christian
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Sifa, Rafet
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Hecker, Dirk
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Hauptwerk
Intelligent Systems and Applications. Proceedings of the 2020 Intelligent Systems Conference, IntelliSys 2020. Vol.3
Project(s)
ML2R
Funder
Bundesministerium für Bildung und Forschung BMBF (Deutschland)
Konferenz
Intelligent Systems Conference (IntelliSys) 2020
Thumbnail Image
DOI
10.1007/978-3-030-55190-2_56
Language
English
google-scholar
Fraunhofer-Institut für Intelligente Analyse- und Informationssysteme IAIS
Tags
  • hyperbolic tangent

  • decision boundaries

  • neural network

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022