How can I edit the number of hidden layer nodes?

Dear friends, I create an neural network with network function. net = network(1,2,[1;0],[1; 0],[0 0; 1 0],[0 1]) This network has one input and two hidden layer. Now I want to edit the number of hidden layer nodes (such as: firts layer is 10 nodes and second layer has 8 nodes). Thanks!

Answer 1

[Greg Heath]

Nghia:

 net1 = network(1,2,[1;0],[1; 0],[0 0; 1 0],[0 1]) ;
 view(net1)

% 1. The topology of Nghia's net1 has 1 hidden layer and 2 feedback loops.

------------------------------------------------------

Albert:

 [ P, T] = simplefit_dataset
 net2 = newff(minmax(P),[10,8,T],{'tansig','purelin',...
        'purelin'},'traingdm');

 Warning: NEWFF used in an obsolete way. 
> In nnerr.obs_use (line 17)
  In newff>create_network (line 126)
  In newff (line 101) 
          See help for NEWFF to update calls to the new argument list.

 Error using newff>new_5p0 (line 271)
Layer sizes is not a row vector of positive integers.

 Error in newff>create_network (line 127)
  net = new_5p0(varargin{:});

 Error in newff (line 101)
  out1 = create_network(varargin{:});

-----------------------------------------------------

IN ADDITION, NEWFF is a doubly obsolete function.

>> help newff

 newff Create a feed-forward backpropagation network.

   Obsoleted in R2010b NNET 7.0.  Last used in R2010a NNET 6.0.4.
   The recommended function is feedforwardnet.

 Syntax

     net = newff(P,T,S)
     net = newff(P,T,S,TF,BTF,BLF,PF,IPF,OPF,DDF)

Greg

Answer 2

[Nghia Nguyen Thanh]

Thanks You very much. But when I can't feedback signal beetwen other layer with newff function. Ex: I have neural network architechture like this: net = network(1,2,[1;0],[1; 0],[0 1; 1 1],[0 1]). How can I fix it?

[ALBERT ALEXANDER STONIER]

can you tell which are the your inputs and targets..