more than one hidden layer in neural network

[Conoscenza Silente]

Hi
I am trying to use OCTAVE neural network and I want to have more than one hidden layer in neural network.
Is it possible to do that?

This works fine
net = newff( min_max( In_n ), [ 20  2], {"tansig","tansig"} ) 

but if I use the same Input having one more layer
I have problems..do you know why?
Thanks AFG
net = newff( min_max( In_n ), [ 20 20  2], {"tansig","tansig","tansig"} )

error: invalid assignment to cs-list outside multiple assignment.
error: assignment to cell array failed
error: assignment to structure element failed
error: assignment failed, or no method for `struct = null_matrix'
error: called from:
error:   /home/aoi/octave/nnet-0.1.10/newff.m at line 110, column 22