By Topic

Why tanh: choosing a sigmoidal function

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
B. L. Kalman ; Dept. of Comput. Sci., Washington Univ., St. Louis, MO, USA ; S. C. Kwasny

As hardware implementations of backpropagation and related training algorithms are anticipated, the choice of a sigmoidal function should be carefully justified. Attention should focus on choosing an activation function in a neural unit that exhibits the best properties for training. The author argues for the use of the hyperbolic tangent. While the exact shape of the sigmoidal makes little difference once the network is trained, it is shown that it possesses particular properties that make it appealing for use while training. By paying attention to scaling it is illustrated that tanh (1.5×) has the additional advantage of equalizing training over layers. This result can easily generalize to several standard sigmoidal functions commonly in use

Published in:

Neural Networks, 1992. IJCNN., International Joint Conference on  (Volume:4 )

Date of Conference:

7-11 Jun 1992