newff newlin

[alon.benari]

Hello,
I am a newbie to octave learning neural network. Using  nnet octave package
I work through the examples in a MATLAB book.
I have the following results from MATLAB:
net=newlin([1 3;1 3],1);

>> net.IW{1,1}=[1 2];
>> net.b{1}=0;
P=[1 2 2 3;2 1 3 1];
>> net.IW{1,1}=[1 2];
>> net.b{1}=0;
A=sim(net,P)

A =

     5     4     8     5
>From octave
If  I am correct we are looking at one layer with with output so
net=newff([1 3;1 3],[1 1])
 net.IW{1,1}=[1 2];
 net.b{1}=0;
The P input  is the same.
but the sim output is not even remotely close to the matlab (does matlab use
different defaults)
If someone can please point to my error?


Thaks 
-- 
View this message in context: 
http://octave.1599824.n4.nabble.com/newff-newlin-tp2286183p2286183.html
Sent from the Octave - General mailing list archive at Nabble.com.