AI Glossary Term

What is Feature Extraction?

Definition

Converting raw data into informative features that a model can use.

Related terms

Embedding Model
A model specialized for converting data into vectors used for semantic search, clustering, and retrieval.
Feature Store
A managed system for storing and serving validated ML features consistently for training and inference.
Data Drift
A shift in real-world input data over time that can degrade model performance.
Data Labeling
The process of assigning tags or target outputs to raw data for supervised learning.
Multimodal Model
A model that can process or generate multiple data types such as text, image, and audio.
Bi-Encoder
A model that encodes queries and documents into separate vectors so they can be compared quickly at scale.

Learn more in our free guides

Linear Probing and Frozen Feature EvaluationFeature Engineering Pipelines and Data VersioningOnline and Offline Feature Serving SkewFeature Pyramid Networks
Browse the full AI GlossaryExplore all free AI guides