Exhibit 4.1
1986Backpropagation
Rumelhart, Hinton and Williams show how a multi-layer network can correct its errors by propagating the error signal backwards. This helps overcome the limitation highlighted by Minsky and Papert.
Why it is in the museum
Neural networks learn by adjusting large numbers of numerical weights. The idea is old, but the scale of data and computing made it far more powerful.
What supports this exhibit
Primary scientific paper
Training multi-layer networks with back-propagation.
Main source: Rumelhart, Hinton & Williams (1986), Nature 323, 533–536.
What to keep in mind: Primary source.
Ask the exhibit
This small guide uses only the information documented on this exhibit page. If your question goes beyond that evidence, it will say so instead of inventing an answer.
Start with one of the suggested questions above, or type your own.