trends.barnas.net

method · first seen 27 Oct 2026

direct feedback alignment

Backpropagation-free training method that sends the global output error directly to each hidden layer through fixed random feedback matrices.

Mentions per week

0219 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

backpropagation-free trainingtime series classificationbackpropagation-free learning