Loss function

How it is used

People choose, define or switch a loss function, then watch 'the loss' go down on training curves. Common examples are cross-entropy for classification and mean squared error for regression.

Example sentences

1. We switched to a weighted loss function because the model was ignoring the rare class.

2. Which loss function did you use for the ranking model?

Common collocations

• choose a loss function
• minimize the loss
• training loss
• cross-entropy loss

Related terms

• gradient descentThe basic optimization method behind training: it repeatedly changes each parameter a little in the direction that reduces the loss the most.
• trainTo teach a model by showing it many examples and repeatedly adjusting its parameters so that its outputs get closer to the correct answers.
• backpropagationThe method that calculates how much each weight in a neural network contributed to the error, by passing the error backward from the output layer toward the input.
• overfittingA problem in which a model learns its training data too closely, including noise and accidents, so it scores well on that data but poorly on new data.

This word in other fields

The same English word can have a different meaning in another field:

• loss function · Software Engineering

More terms: Model Training

• epoch
• learning rate
• hyperparameter
• batch size
• underfitting
• regularization
• checkpoint
• converge