[briga]

As far as I know there is no evidence that the brain has any analogue to the back-propagation used to train pretty much all modern neural networks. Back-propagation is a good way to optimize neural networks, but it doesn't seem to be the way brains optimize neural networks.

[neuronerd]

well, the original paper has a pretty good summary of how the brain may actually do backdrop.

[joycian]

What do you mean by "original paper" here?