Do we randomly generate bias and weight matrix in the begining and if so what are its dimensions and if not how do we calculate those matrices
W and b matrix generation
Hey @shreyanarula3, since we have already appended the column having all 1 in th x matrix, there is no need for bias term. Also we can initial all weights and bias with zeros. Just like this,
thetas = np.zeros((x.shape[1],1))
Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section. 