feature extraction
Overloaded term having either of the following definitions: - Retrieving intermediate feature representations calculated by an unsupervised or pre-trained model (for example, hidden layer values in a neural network) for use in another model as input.
Plain English Explanation
Overloaded term having either of the following definitions: - Retrieving intermediate feature representations calculated by an unsupervised or pre-trained model (for example, hidden layer values in a neural network) for use in another model as input. - Synonym for feature engineering.
How is it used?
Practitioners refer to feature extraction when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.