What is Zero-Shot Learning? | Stanford HAI
Stanford
University
  • Stanford Home
  • Maps & Directions
  • Search Stanford
  • Emergency Info
  • Terms of Use
  • Privacy
  • Copyright
  • Trademarks
  • Non-Discrimination
  • Accessibility
© Stanford University.  Stanford, California 94305.
Skip to content
  • About

    • About
    • People
    • Get Involved with HAI
    • Support HAI
    • Subscribe to Email
  • Research

    • Research
    • Fellowship Programs
    • Grants
    • Student Affinity Groups
    • Centers & Labs
    • Research Publications
    • Research Partners
  • Education

    • Education
    • Executive and Professional Education
    • Government and Policymakers
    • K-12
    • Stanford Students
  • Policy

    • Policy
    • Policy Publications
    • Policymaker Education
    • Student Opportunities
  • AI Index

    • AI Index
    • AI Index Report
    • Global Vibrancy Tool
    • People
  • News
  • Events
  • Industry
  • Centers & Labs

What is Zero-Shot Learning?

Zero-Shot Learning is the ability of an AI model to perform tasks or recognize categories it has never been explicitly trained on, using only its general knowledge and understanding. For example, a language model might translate between languages it hasn't seen paired together during training, or classify images of objects it has never encountered by understanding descriptions of them. This capability emerges in large-scale models that learn broad patterns and relationships, allowing them to generalize to new situations without requiring specific examples for every possible task.

Navigate
  • About
  • Events
  • Careers
  • Search
Participate
  • Get Involved
  • Support HAI
  • Contact Us

Stay Up To Date

Get the latest news, advances in research, policy work, and education program updates from HAI in your inbox weekly.

Sign Up For Latest News


Zero-Shot Learning mentioned at Stanford HAI

Explore Similar Terms:

Few-Shot Learning | Transfer Learning | Unsupervised Learning

See Full List of Terms & Definitions

Rooting Out Anti-Muslim Bias in Popular Language Model GPT-3
Andrew Myers
Jul 22
news

This “severe” bias must be addressed before these language models become ingrained in real-world tasks. 

Rooting Out Anti-Muslim Bias in Popular Language Model GPT-3

Andrew Myers
Jul 22

This “severe” bias must be addressed before these language models become ingrained in real-world tasks. 

Natural Language Processing
Machine Learning
news

Enroll in a Human-Centered AI Course

This AI program covers technical fundamentals, business implications, and societal considerations.