Should I scale the output of the equation?

With this link I implemented a neural network to calculate y=x*x (x is the input and y is the output) .. I took 1 unit in the input layer, 4 units in the hidden layer and 1 unit in the output layer. But when I enter, for example, 2 as input (the desired result is 4) I got an output value of 0.99999999 .... this also happens for all other input numbers greater than 1 (its output is correct with a value from 0 to 1). I also used the this link and modified it to solve my equation, but the result was the same!

+4
source share
1 answer

Like Pete Said. I have to normalize my output (and input) in order to get the correct answer.

0
source

All Articles