Gradient Descent

Gradient Descent  there are three variants of gradient descent,which differ in how much data we use to compute the gradient of objective function Depending on the amount of data , we make a trade-off between the accuracy of the parameter update and the time it takes to perform as update  Batch gradient descent:  Parameters are updated after computing the gradient of error with respect to the entire training set  In code, batch  gradient descent looks like this: for i in range(nd_epochs):         params_grad = eval uate_gra dient ( loss_function , data , params )        params = params - learning_rate * params_grad   Stochastic Gradient Descent:   Parameters are updated after computing the gradient of error with respect to a single training example    Mini-Batch Gradient Descent:   Parameters are updated after computing the gradient of error with respect to a subset of the training set in code this looks like :  for i in range ( nb_epochs ):