Varun Reddy
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1Neural Computing×1Neurons and Cognition×1
Frequent co-authors
Research Timeline
2026
Conditioned Direct Feedback Alignment via Activity and Error Geometry
This paper studies failure modes of Direct Feedback Alignment (DFA) training and isolates two distinct gain mechanisms: activity conditioning and error conditioning.
Highlighted terms show continued research focus across papers