How to generate neural network equation with weight and bias??

Hi, I have 3 Input Data (temperature, moisture content, and frequency) set of 168 and my target data (dielectric constant) set of 168.

I used an artificial neural network toolbox. I trained(70%), validated (15%), and tested(15%) it. I got reasonable result.

And I got the IW, LW, and b using commands (cell2mat(net.IW, LW,and b)) to plug into the default equation below.

y = b2 + LW * tansig( b1 + IW * x )

Here is my question I have only b (bias) does this include b1 and b2?? If it is, how can I divide this into b1 and b2?

and how to generate neural network equation with default equation, weight, and bias especially input values are 3 (168*3)??

Answer 1

[Greg Heath]

http://www.mathworks.com/matlabcentral/answers/126180-regression-equation-from-artificial-neural-network