Optimizing parameters is the ultimate goal of every machine learning algorithm. You want to get the optimum value of the slope and the intercept to get the line of best fit in linear regression problems. You also want to get the optimum value for the parameters of a sigmoidal curve in logistic regression problems. So what if I told you that Gradient Descent does it all? Before learning how it works, let’s first make clear the meaning of the words Gradient and Descent along with some other key terms.