what is wrong with y=|x| function to find the error
Why do we need differentiable function to find error
hey @Par1hsharma ,
you don’t need to make the result as to be 0 , or error to be 0.
But you want your model or function to be as such that reaches as close as possible to 0.
hence you need to have a function that is differentiable , with which you can understand the learning nature and hence update your coefficients accordingly.
above function on differentiation , will be either 1 or -1 based on value of x , hence meaning , your model or algorithm doesn’t learn, at first step only it reaches the final zone , which is wrong based on learning theory.
I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.
On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.