Obtaining mathematical equation from neural network toolbox after training

Question

Julix 2016-7-7

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/294162-obtaining-mathematical-equation-from-neural-network-toolbox-after-training

回答： pathakunta 2024-1-26

My ANN is for 3 inputs, N neurons in a single hidden layer and output. Tansig transfer function was used in the hidden layer and purelin in the output layer. Using the weight and bias values, I obtained my model equation

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

and transformed it into

y = A*((2/(1 + exp(-2*(B*X + b1)))) - 1) + b2

where A = LW values in (1xN) array

B = IW values in (Nx3) array

X = 3 input values in (3x1) array

b1 = layer 1 bias values in (Nx1) array and b2, bias value for layer 2 is a single value (1x1)

My model equation only works in matlab environment because my constants A, B and b1 are in array form.

I need to have A and b1 values as single constant values, and B as a (1x3) array to have B1, B2 and B3 for the 3 inputs. but I don't know how to achieve this..

PLEASE is there anyone that can tell how to make my equation a standalone that works anywhere, like excel & others..??

3 个评论
显示 1更早的评论隐藏 1更早的评论

Julix 2016-7-8

Thanks. But I did not do that because I don't think the input normalization and output de-normalization has effect on the output values. The extracted equation was used to compute values for y, and in matlab environment, the results were same with the simulated output of the network

Greg Heath 2016-7-8

I'm not sure that I understand your argument.

If you are saying that the weights do not depend on the type of normalization, you are incorrect.

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

circuit_designer5172 2016-7-7

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/294162-obtaining-mathematical-equation-from-neural-network-toolbox-after-training#answer_228018

I believe you are mostly correct in your analysis. To transform out of arrays you can add a summation in front of the equation. Then, in excel each row will represent one input and you will have a column for the contribution to "y" from that input. Then, you just sum them together to get the network output. Hope that is clear!

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Julix 2016-7-8

Thanks.. But I wish there was a more simplified method.

请先登录，再进行评论。

Answer 2

Bhupendra Suryawansi 2017-12-29

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/294162-obtaining-mathematical-equation-from-neural-network-toolbox-after-training#answer_298086

My ANN is for 5 inputs and 1 output, N neurons in a single hidden layer and output. Tansig transfer function was used in the hidden layer and purelin in the output layer. i have normalized my input data from 0.1 to 0.9 values using the equation y(norm) = =(0.1+0.8*((Xexp value-Xmin value)/(Xmax value-Xmin value))). Should i change my TANSIG function formula ? and what would be that ? how can i get that which varies the value between 0.1 to 0.9 only.

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Greg Heath 2017-12-30

Why are you bothering to normalize? MATLAB handles normalization automatically.

Just look at the examples used in the help and doc documentation.

Hope this helps.

Greg

请先登录，再进行评论。

Answer 3

Bhupendra Suryawansi 2018-1-2

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/294162-obtaining-mathematical-equation-from-neural-network-toolbox-after-training#answer_298319

Can anybody tell me the output equation for Cascade-forward back-propagation network? Means, how to represent the output equation for the Cascade-forward back-propagation neural network? (for five inputs, one output and single hidden layer)

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

Answer 4

pathakunta 2024-1-26

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/294162-obtaining-mathematical-equation-from-neural-network-toolbox-after-training#answer_1398131

My ANN is for 5 inputs and 1 output, N neurons in a single hidden layer and output. Tansig transfer function was used in the hidden layer and purelin in the output layer. i have normalized my input data from 0.1 to 0.9 values using the equation y(norm) = =(0.1+0.8*((Xexp value-Xmin value)/(Xmax value-Xmin value))). Should i change my TANSIG function formula ? and what would be that ? how can i get that which varies the value between 0.1 to 0.9 only.