By Topic

Combining adaptive sigmoid packet and trace neural network for fast invariance-learning

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 $33
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

4 Author(s)
Han Chuan Peng ; Dept. of Biomed. Eng., Southeast Univ., Nanjing, China ; Li Feng Sha ; Qiang Gan ; Yu Wei

By replacing the commonly used sigmoid neuron activation function with an adaptive sigmoid packet, the invariance extraction of a trace neural network can be effectively enhanced and speeded up for fast varying sample sequences. The performance is compared with several existing models

Published in:

Electronics Letters  (Volume:34 ,  Issue: 9 )