Loss function

A loss function is used in machine learning to measure how far away a prediction is from the actual answer. It does this by taking the difference between the prediction and the actual answer and giving it a numerical value. For example, if the prediction was 6 and the actual answer was 7, the loss function would give the difference a score of 1. The goal of a machine learning algorithm is to minimize the loss function score, so it's doing the best job of predicting the correct answer.