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

2 次查看(过去 30 天)
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)??

采纳的回答

Greg Heath
Greg Heath 2014-4-23

更多回答(0 个)

类别

Help CenterFile Exchange 中查找有关 Deep Learning Toolbox 的更多信息

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by