Loss function Cost function
Used when referring to errors in a single training example. Used to refer to the average of the loss function over the training set.
The purpose of the loss function is to capture the difference between actual and predicted values in a single dataset The cost function aggregates the differences across the training data set. The frequently used loss functions are called squared error and hinge loss.
This is a way of evaluating how well the algorithm models the data set. A cost function refers to the functional relationship between cost and performance. Assuming constant technology, we examine the behavior of costs at different levels of production.
BY Best Interview Question ON 30 Dec 2023