What is Backpropagation? | 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 Backpropagation?

Backpropagation is how neural networks learn from mistakes by working backward through the network to figure out which parts caused the error. When the network makes an incorrect prediction, it calculates how much each connection contributed to that mistake, then adjusts those connections to improve the result.

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

Backpropagation mentioned at Stanford HAI

Explore Similar Terms

Optimization Algorithm | Loss Function | Weights

See Full List of Terms & Definitions

From Brain to Machine: The Unexpected Journey of Neural Networks
Katharine Miller
Nov 18
news

How early cognitive research funded by the NSF paved the way for today’s AI breakthroughs—and how AI is now inspiring new understandings of the human mind.

From Brain to Machine: The Unexpected Journey of Neural Networks

Katharine Miller
Nov 18

How early cognitive research funded by the NSF paved the way for today’s AI breakthroughs—and how AI is now inspiring new understandings of the human mind.

Machine Learning
Computer Vision
news
TextGrad: AutoGrad for Text
Federico Bianchi, James Zou
Jun 19
news
Your browser does not support the video tag.

Scholars develop a new framework that optimizes compound AI systems by backpropagating large language model feedback.

TextGrad: AutoGrad for Text

Federico Bianchi, James Zou
Jun 19

Scholars develop a new framework that optimizes compound AI systems by backpropagating large language model feedback.

Machine Learning
Your browser does not support the video tag.
news

Enroll in a Human-Centered AI Course

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