Back Propagation Neural Network (BPNN) is a type of algorithm in Neural Network that can be use for Javanese alphabets character recognition. Matlab 7.1 has been used as a software to support the program. The main purpose of this research is order to find out BPNN’s training characteristic from each samples. On the other hand, this research also gives BPNN’s accurancy value in Javanese alphabets character recognition. The result of research shows that each part of the samples having different BPNN’s characteristic based on the best training.  Keywords : NN, BPNN
Copyrights © 2010