ClassroomThe classroom
Back to the lesson libraryPERSPECTIVE · 14 MIN
M01.6 CONNECT THE MECHANISM

Why deeper networks became practical

Neural networks were written off, twice. Then in 2012 one won an image contest by a landslide. Meet the four ingredients that had to arrive together.

LESSON OVERVIEW14 min lesson

Lesson overview

Neural networks were written off, twice. Then in 2012 one won an image contest by a landslide. Meet the four ingredients that had to arrive together.

What you’ll explore

  • Explain the distinct roles of learned layers, backpropagation, data, and computing resources in the deep-learning revival.
GO TO THE SOURCE

Original explanations, connected to the research.

Rumelhart, Hinton, and Williams — back-propagating errors (1986)Krizhevsky, Sutskever, and Hinton — ImageNet classification (2012)Hinton, Osindero, and Teh — A Fast Learning Algorithm for Deep Belief Nets (2006)LeCun, Bottou, Bengio, and Haffner — Gradient-based learning applied to document recognition (1998)Hochreiter and Schmidhuber — Long Short-Term Memory (1997)
Suggest a correction

A precise note can make an explanation better.

Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.

The file includes this note, the scene title, and lesson metadata. Your saved progress and quiz responses are excluded. Download before leaving or reloading to keep your note.