Re:Theories of Error Back-Propagation in the Brain
by raindeer3 on Sunday August 11, 2019 @03:47AM
(#20666941)
Very interesting also is that you can directly send the error to intermediate layers through sparse random projections without the need for any layerwise backpropagation. This relaxation of the structure of the backward pass makes bp even more plausible from a biological perspective.
https://arxiv.org/abs/1609.01596 https://arxiv.org/abs/1903.02083