Intermediate · Fundamentals

Embeddings

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

TL;DR. Dense vector representations of discrete items, capturing their semantic relationships and meanings.

Technical Definition

Dense vector representations of discrete items, capturing their semantic relationships and meanings.

How it works

Embeddings convert high-dimensional sparse data like words or categories into lower-dimensional continuous vectors. These vectors are designed so that items with similar meanings or properties are located closer to each other in the vector space. They are crucial for tasks in NLP and recommender systems.

Related Concepts

• Feature Engineering — The process of creating, selecting, and transforming input variables to improve a machine learning model's performance.
• Natural language processing (NLP) — A field of AI enabling computers to understand, interpret, and generate human language.