baseline: add convolutional hierarchical feedback alignment

1 files changed, 6 insertions, 0 deletions

diff --git a/README.md b/README.md
index c06e9b1..64abf25 100644
--- a/README.md
+++ b/README.md
@@ -115,6 +115,12 @@ path: it perturbs the channel-gated basis directly and reproduces the expected
 full-field delta rule with far less irrelevant spatial variance.  It does not
 retroactively reopen or relabel the failed frozen Oral-A protocol.
 
+The same smoke suite also audits a convolutional hierarchical-FA baseline. Its
+random feedback tensors follow the real residual DAG and use local activation
+Jacobians, but remain independent of forward weights. An audit-only symmetric
+copy reproduces exact hidden gradients to `5.3e-16` relative error and the BP
+parameter update to `2.98e-8`; actual HFA never performs that copy.
+
 The subsequent V3 mechanism estimates the required A/G matrix statistics
 directly by perturbing the vectorizer parameter subspace. It remains
 forward-only and uses two causal loss queries per direction. Its exact and