newsbillnet - News

 
 

added back_prop

Item posted by Vassilis Virvilis <vasvir> on Sun 06 Apr 2003 09:05:51 AM UTC.

The back propagation family is the base of all gradient learning machines. The current billnet's implementation can be used with:
 -the cross entropy cost function
 -the online and offline type of learning
 -the sigmoid output function
 -the tanh output function (untested)

Back to the top

Powered by Savane 3.13-02a9.
Corresponding source code