Hi All,

I try to test the neural network package AMORE, I normalized my data first,

the input data is X [x1,x2,x3] where x1,x2,x3 each is 100 row 1 column

vector.

the output data Y is 100 row 1 column vector.

my network has neurons=c(3,2,2,1) which 2 hidden layers, 3 node in the

input layer while 1 in the output layer. Once the network is trained. I

use sim (result$net, z) to test the output,

Here z =c(0.01,0.09,-0.001842388), to my surprise, the simulation result

return is:

[,1]

[1,] -0.008967264

[2,] -0.008783412

[3,] -0.008750038

How come? It should return one scalar instead of a vector. Then I tried sim

(result$net, z2) which z2=c(0.01), the result return is:

[,1]

[1,] -0.008967264

As the input should have 3 variables, how come just one input variable can

have output value? And it is same as the first value in the result above.

Am I misunderstand something here? Many thanks

Ying

[[alternative HTML version deleted]]

______________________________________________

[hidden email] mailing list

https://stat.ethz.ch/mailman/listinfo/r-helpPLEASE do read the posting guide

http://www.R-project.org/posting-guide.htmland provide commented, minimal, self-contained, reproducible code.