All Topics
All Topics
Technology
Technology
Design
Design
Programming
Programming
Science
Science
News
News
Gaming
Gaming
Entertainment
Entertainment
Business
Business
Finance
Finance
Sports
Sports
Health
Health
Food
Food
Travel
Travel
Art
Art
Music
Music
Books
Books
Education
Education
Politics
Politics
Personal
Personal
No algorithm. No AI slop. No ads. Just RSS. Pro-human. Indie writers. Real journalism. Open web. Chronological. Hand toasted.

The Origins of Backpropagation in Neural Networks

By

nothrowaways

9mo ago· 18 min readenInsight

Summary

The article explores the origins of backpropagation (BP), a foundational technique in neural networks and deep learning. It credits the modern version of BP, also known as the reverse mode of automatic differentiation, to Finnish student Seppo Linnainmaa in 1970, with a precursor by Henry J. Kelley in 1960. The piece highlights BP's significance in the AI field and its 50th anniversary in 2020.

Key quotes

· 3 pulled
Efficient backpropagation (BP) is central to the ongoing Neural Network (NN) ReNNaissance and 'Deep Learning.'
BP's modern version (also called the reverse mode of automatic differentiation) was first published in 1970 by Finnish master student Seppo Linnainmaa.
A precursor of BP was published by Henry J. Kelley in 1960.
Snippet from the RSS feed
Its modern version (the reverse mode of automatic differentiation) was first published in 1970 by Seppo Linnainmaa

You might also wanna read