How to get values on testdata in RSNNS

Question

I have two files, "testi" containing few numbers and "testo" containing their square roots. I have another test named file which contains some numbers for which I want their square roots. I used the command

model <- mlp(testi,testo,size=50,learnFuncParams = c(0.001),maxit = 5000)
xyz <- predict(model,test)

The values which I get from "xyz" are

xyz
#[1,] 0.9971085
#[2,] 0.9992253
#[3,] 0.9992997
#[4,] 0.9993009
#[5,] 0.9993009
#[6,] 0.9993009
#[7,] 0.9993009

Whereas "test" contains

1   4
2  16
3  36
4  64
5 100
6 144
7 196

Please let me know why does this happen?

Answer 1

mlp has logistic output, you need to specify linOut=TRUE. In general, normalizing your data would also help.