Sign inSign in
ConceptAI & ML

Word embeddings

Dense, real-valued vectors representing words in a high-dimensional vector space where similar contexts map to similar vectors.
as Christopher Manning defines itStanford UniversityThe wording closest to all 6 definitions
Watch it explained

Know first

Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.

Opens up

Concepts that name this one as a prerequisite.

Lecturers

5

Each in their own terms, from the easiest level.

  • Steven Feng

    Stanford University · Undergraduate

    Dense vectors in high-dimensional space that represent words and enable operations like arithmetic and semantic similarity.
    • 10:23Overview of Transformers (Stanford CS25: Transformers United V6)
    • 8:15Overview of Transformers
  • Grant Sanderson

    Undergraduate

    The representation of words or text tokens as vectors in a high-dimensional space to capture semantic relationships.
    • 6:04Generating Functions & Roots of Unity Filter in Combinatorics
  • Bruno Bauwens

    HSE University · Graduate

    A representation of words for text analysis, typically associated with vectors of real numbers.
    • 11:43HSE Kolmogorov Complexity, Lecture 1: Computability and Solomonoff Induction
  • Yasaman Bahri

    Harvard University · Research

    A technique in natural language processing where words are mapped to vectors of real numbers in a continuous vector space.
    • 3:24On the Emergence of Representational Geometry from Natural Language Statistics

Lectures that assume it

3

Connections

18

The lectures that define it or assume it, and the concepts next to it.

5 lecturers. Definitions are written by AI from each lecture’s transcript. A time with a play mark starts the lecture at the moment the lecturer says it.