Hi,  I am forest biometrician in forest faculty,  I have studied for predicting various tree and forest attributes by using ANNs,

I can apply different ANN training networks such as feed-forward backprop, cascade, elman, etc. by using NNTOOLS in Matlab software to various data obtained from forest areas,

NNTOOLs in Matlab produces output values for the normalized data that were trained with Matlab, also Nntool give weights to layer 1, 2 and bias values, you can view and edit weights in Matlab nntool . Then, I want manually to calculate these simulation values, also called networkoutput in Matlab, by using weight values and biases obtained from Matlab nntool, because these manual predictions and formulae are very important to present for reader for my article and projects,

But, I can not obtain these output from Matlab nntool, my manual prediction from formulae including ANN procedure is not same with output values from Matlab nntool, I want to point out these two prediction procedure use the same input values,

In my ANN procedure, I used the feed forward backprop training procedure,  including training procedure is TRAINLM, number of layers are 2, number of neurons are 3, transfer function is LOGSIG, thus, NNTOOL in Matlab procedure output values calculating weight values,

Weight to layer 1:

[1.5141 1.3953 -1.3436;

 5.4251 0.13201 -0.4586;

 -1.0807 -0.6872 3.7094]

Weight to layer:

[2.8651 3.6052 1.5207]

Bias to layer 1:

[-1.0225;

 5.821;

 -5.0482]

Bias to layer 2:

[-4.2332]

Then I used the these formule:  

1.       Step:

Nöron 1 (N1) = 1.5141*G1+1.3953*G2-1.3436*G3-1.0225

Nöron 2 (N2)=5.4251*G1+0.13201*G2-0.4586*G3+5,821

Nöron 3 (N3)=-1.0807*G1-0.6872*G2+3.7094*G3-5.0482

2.       Step:

E1=1/(1+EXP(-N1))

E2=1/(1+EXP(-N2))

E3=1/(1+EXP(-N3))

3.       Step:

Sum=2.8651*E1+3.6052*E2+1.5207*E3-4.2332

4.       Step:

output=1/(1+EXP(-Sum))

But, I can not obtain the output values from Matlab by using these formulea, What is wrong is in these formulea.

Best regards.

Dr. İlker ERCANLI