AI Blog

AI Blog

by Michele Laurelli

Back to Glossary

Loss Function

/lɒs ˈfʌŋkʃən/
Concept
Definition

A function that measures the difference between predicted and actual values, guiding model optimization.

Loss functions quantify model error. Common types include Mean Squared Error (MSE) for regression, Cross-Entropy for classification. Optimization minimizes loss through gradient descent.

Examples

1

MSE for regression tasks

2

Cross-entropy for classification

3

Huber loss for robust regression

Related Terms

Gradient Descent

An optimization algorithm that iteratively adjusts parameters to minimize a loss function by following the gradient.

Backpropagation

An algorithm for training neural networks by calculating gradients of the loss function with respect to weights.

Michele Laurelli - AI Research & Engineering