arXiv cs.NE
· Papers
Conditioned Direct Feedback Alignment via Activity and Error Geometry
arXiv:2607.18574v1 Announce Type: cross Abstract: Direct feedback alignment (DFA) trains hidden layers with fixed random projections of the output error, avoiding the transposed-weight backward pass of backpropagation (BP). We study a failure mode of DFA training that is distinct from feedback quality: the local weight