| Library: | nn |
| See also: | nnrnet2 nnrpredict2 |
| Quantlet: | ann2 | |
| Description: | is a tool to run a feed-forward neural network |
| Usage: | ann2 (x, y, t {, vn}) | |
| Input: | ||
| x | n x p matrix input variables | |
| y | n x q matrix output variables | |
| t | n x 1 vector of sets (0=training, 1=test, 2=validation) | |
| vn | p x 1 vector of variable names (unused) | |
x = read("kredit1")
t = read("tkredit")
y = x[,1]
x = x[,2:21]
x =(x-min(x))./(max(x)-min(x))
ANN2(x, y, t)
runs a user specified neural network for the kredit data of Fahrmeier and Hammerle.