diff options
Diffstat (limited to 'BASELINES.md')
| -rw-r--r-- | BASELINES.md | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/BASELINES.md b/BASELINES.md index 7cc6c10..52fd12c 100644 --- a/BASELINES.md +++ b/BASELINES.md @@ -27,6 +27,11 @@ The audited implementations and completed results are in `RESULTS.md`: forward synapses, and a separate update consumes only parent/child activities to estimate each feedback kernel. It is deliberately treated as a strong learned-FA baseline, not as SDIL novelty; +- residual response mirroring (`rrm`) replaces WM's noisy estimate-then-average + step with local normalized LMS on the child-response prediction error. Its + stochastic update vanishes sample-by-sample at Q=W; the extra feedback + prediction convolution is included in MAC accounting. It is also an + inherited learned-alignment control; - direct node perturbation uses a causal target on every hidden update and no learned vectorizer; - the no-traffic, `P=0` SDIL backbone is learned direct feedback by node |