I used the equation of the neural network ("y = b2 + LW * tansig (b1 + IW * x)") to an Excel, so you can calculate the output values of two input values and one target of a network of two neurons and one layer, values generated by the equation "y = b2 + LW * tansig (IW + b1 * x)" (all done in excel) are normalize, give me exactly equal to the coefficient of determination delivered by Matlab but it gives me different values between output Excel and output Matlab because one is normalize (excel).
Someone can write the equation for me to denormalize my output values, I have sought "mapminmax" command but I can not understand how denormalize (the variables of the equation). Is there a website where explain the command mapminmax , but can not understand how denormalize (to do it in excel).
I know the equation of normalize:
y = (ymax-ymin)*(x-xmin)/(xmax-xmin) + ymin; where :
ymax= max. value of specified range in this case = 1 ( which is default for mapminmax command)
ymin= min. value of specified range in this case=-1 ( also default value)
x= value to be scaled.
xmax= max. value of numbers to be scaled
xmin= min. value of numbers to be scaled
but i need to know the equation of denormalization to use in Excel. How dat use for max and min value in denormalization.
please help me
Best Answer