Intermediate · Data

Feature Extraction

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. Deriving informative numerical signals from raw data for use as model inputs.

Technical Definition

Deriving informative numerical signals from raw data for use as model inputs.

How it works

Classical ML required hand-crafted features (SIFT for vision, TF-IDF for text). Deep learning largely automates this with learned representations, but feature extraction still matters for tabular data, signal processing, and combining model outputs with structured inputs.

Related Concepts

• Embedding — A dense vector representation that captures semantic meaning, mapping discrete items like words into continuous mathematical space.
• Feature Engineering — The process of creating, selecting, and transforming input variables to improve a machine learning model's performance.
• Feature Selection — Choosing the most useful subset of features to improve performance and interpretability.