## Survey of Neural Transfer Functions (1999)

### Cached

### Download Links

Venue: | Neural Computing Surveys |

Citations: | 35 - 19 self |

### BibTeX

@ARTICLE{Duch99surveyof,

author = {Wlodzislaw Duch and Norbert Jankowski},

title = {Survey of Neural Transfer Functions},

journal = {Neural Computing Surveys},

year = {1999},

volume = {2},

pages = {163--213}

}

### Years of Citing Articles

### OpenURL

### Abstract

The choice of transfer functions may strongly influence complexity and performance of neural networks. Although sigmoidal transfer functions are the most common there is no apriorireason why models based on such functions should always provide optimal decision borders. A large number of alternative transfer functions has been described in the literature. A taxonomy of activation and output functions is proposed, and advantages of various non-local and local neural transfer functions are discussed. Several less-known types of transfer functions and new combinations of activation/output functions are described. Universal transfer functions, parametrized to change from localized to delocalized type, are of greatest interest. Other types of neural transfer functions discussed here include functions with activations based on nonEuclidean distance measures, bicentral functions, formed from products or linear combinations of pairs of sigmoids, and extensions of such functions making rotations...