Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Common-Mode Collapse and Recovery in Direct Feedback Alignment
Varun Reddy, Bernardo L. Sabatini, Houman Safaai
Direct feedback alignment (DFA) trains hidden layers through fixed random projections of output error. With tanh hidden units and independent sigmoid outputs, plain stochastic grad…
cs.LG2026
Conditioned Direct Feedback Alignment via Activity and Error Geometry
Houman Safaai, Varun Reddy, Bernardo L. Sabatini
Direct feedback alignment (DFA) trains hidden layers with fixed random projections of the output error. Even when this feedback provides useful credit, unequal scales across activi…