error in number of neruns

hi every body...i using neural network to image recognition... i used newff(input,target)but i have problem in number of neruns..i can not useing more than 10 neruns in each layers but when i apply the same code in other laptop it accept more than 10 neruns...why this happen????? pls help

Answer 1

[Greg Heath]

% >> 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.

I disagree. I recommend

 fitnet                  for regression and curvefitting
 patternnet         for classification and patternrecognition

Try the commands

>> help fitnet

>> help patternnet

Also, to improve training speed, see the appropriate documentation section at mathworks.com

http://www.mathworks.com/help/nnet/function-approximation-and-nonlinear-regression.html

Hope this helps.

Thank you for formally accepting my answer

Greg

[primrose khaleed]

thanks greg...but the both laptops used same version of matlab... but why one of them accept more than 10 nerunons and other not

[Greg Heath]

Spelling: neuron

Which version of MATLAB?

Regression or Classification? (fitnet or patternnet)

Have you looked up the comments in the documentation re the speed/size tradeoff ?

Post code so I know exactly what you are doing.

Greg