Cost Functions

  • Ovidiu CalinEmail author
Part of the Springer Series in the Data Sciences book series (SSDS)


In the learning process, the parameters of a neural network are subject to minimize a certain objective function, which represents a measure of proximity between the prediction of the network and the associated target. This is also known under the equivalent names of cost function, loss function, or error function. In the following we shall describe some of the most familiar cost functions used in neural networks.

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Mathematics & StatisticsEastern Michigan UniversityYpsilantiUSA

Personalised recommendations