Bauckhage, ChristianChristianBauckhageSifa, RafetRafetSifaHecker, DirkDirkHecker2022-03-142022-03-142021https://publica.fraunhofer.de/handle/publica/40884210.1007/978-3-030-55190-2_56The 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.enhyperbolic tangentdecision boundariesneural network005006629conference paper