loss function

American  

noun

1. (in decision theory) a function that expresses the loss incurred when a decision is made in terms of various factors.

---

Example Sentences

"This gives us a kind of 'periodic table' of AI methods. Different methods fall into different cells, based on which information a method's loss function retains or discards."

From Science Daily

A loss function is the mathematical formula that measures how far an AI model's predictions deviate from the correct answer.

From Science Daily

Gains in machine-learning algorithms can come from fundamental changes in their architecture, loss function, or optimization strategy—how they use feedback to improve.

From Science Magazine

The loss function controlling the learning was considering only the error of the next step, not the validity of the solution over many steps, which is what we really want.

From Nature

Machine-learning algorithms require researchers to specify a ‘loss function’, which determines the severity of various errors — such as whether it is better to make two errors of 1% each, or a single error of 2%.

From Nature