Source code for fast training of multilayer perceptron classifier. Example training and validation data files included. Source code for applying the trained network. Resulting networks can be pruned by NuClass7.06. The training algorithm can be modified to be substantially better than BP. A readme file is provided.
The approximation/regression version of this software, called MLP-Map, is also available. MLP-Class was developed by the Image Processing and Neural Networks Lab of Univ. of Texas at Arlington, and by Neural Decision Lab LLC. For winzip password, go to: http://www-ee.uta.edu/eeweb/ip/Software/Software.htm