Feature (Machine Learning)
A feature is an individual measurable input variable that a machine learning model uses to make a prediction, such as a customer's age or the pixels of an image.
What is Feature (Machine Learning)?
Traditional machine learning relied heavily on feature engineering, where experts chose and transformed inputs. Deep learning models largely learn useful features themselves from raw data. Features that act as proxies for protected characteristics can introduce discrimination.
How it works
Each example is represented as a vector of feature values that the model combines to produce its output.
← All Artificial Intelligence & Superintelligence definitions · ← Back to the A–Z definitions