Backpropagation and gradient learning: Technologies
Technologies
The technologies that rely on it, and how each one uses it
Relied on by- DL Deep learning Deep networks are normally trained by passing the output error backwards to adjust the weights of every layer, the method set out in the 1986 paper [1].
- LLM Large language models The models' weights are trained by gradient methods whose gradients are found by backpropagation.
- AIx AI diagnosis from medical images Networks learn from graded images by adjusting every weight to reduce the error on each example.
as of 2026-11-12
Sources
- Learning representations by back-propagating errors Nature (D. E. Rumelhart, G. E. Hinton and R. J. Williams), via the SAO/NASA Astrophysics Data System, 1986, vol. 323, October 1986