Machine Learning Fundamentals · Foundations

Cost functions and loss

The single number a model tries to minimize during training, chosen to reflect how wrong its predictions are.

Also known as: loss function, objective function, MSE, cross-entropy.

Start a lesson on Cost functions and loss

Learn first

• Linear regression: Fitting a straight line (or hyperplane) through data to predict a continuous number.

Leads to

• Gradient descent: Repeatedly nudging a model's parameters downhill on the cost function to reduce error.

Related topics

• Gradient descent: Repeatedly nudging a model's parameters downhill on the cost function to reduce error.