"The loss function computes the error for a single training example in contrast to a Cost function, which is the average of the loss functions from each example within the training data set2."
"For example in image classification if an image of the colour red is classified as an image of the colour red then the loss function is 0; however, if it is classified as an image of blue then the loss function is greater than zero. Any correctly chosen loss function for this example will give a greater value for blue than orange or pink."
"There are many types of loss functions including mean absolute loss, mean squared error and mean bias error."