Learning Threads

 
EasyNN-plus neural networks can be trained using more than one learning thread.  Some networks will learn much faster with multiple threads but there is no simple relationship between the learning speed and the number of threads.  The optimum number of threads can only be found by experiment. 
 
Networks using multiple threads can learn more than ten times faster than when using a single thread. The disadvantage with using multiple threads is that the final results may vary slightly.
 
Up to eight learning threads can be started using the threading control in the Controls dialog. 
 
All EasyNN-plus threads run at a low priority so that other applications and the operating system do not slow down while the learning threads are running. 
 
 
 

Created with help of DrExplain