What is the difference between i and j in the last equation of gradient descent ?
Difference between i and j
Hey @gauthampkrishnan, j refers to j-th feature. On the other hand i refers to the i-th training example. In layman terms, as we are provided with the dataset, columns represent features so ‘j’ refers to the jth column. and There are many rows which are independent, i represents the row number.
Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. 
One more doubt derivative of (e^-z) y^ wrt z there is -ve sign right but duirng the last equation -ve sign wasnt put please check and tell me whether the final equation is with -ve or not
Hey @gauthampkrishnan, actually there are two negative sign in differentiation process,
Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. 