diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 15:08:36 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 15:08:36 -0500 |
| commit | 82d49f4b8b741669ab39100f4719719801064f20 (patch) | |
| tree | 7c7e7a1f58338508e89dab47b3bdf43eb7bf10d0 /BASELINES.md | |
| parent | 6fb38aabad3ce33a263414ecaf4eef0474c66045 (diff) | |
results: record residual mirror full failure
Diffstat (limited to 'BASELINES.md')
| -rw-r--r-- | BASELINES.md | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/BASELINES.md b/BASELINES.md index 767ca93..5c66e2a 100644 --- a/BASELINES.md +++ b/BASELINES.md @@ -31,7 +31,9 @@ The audited implementations and completed results are in `RESULTS.md`: 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; + inherited learned-alignment control. Its short gate passes, but its sole + full run ends at 10% with NaN validation loss despite 0.999998 endpoint Q/W + cosine, closing intermittent RRM as a scalable baseline; - modified Kolen--Pollack (`kp`) is the reciprocal local-plasticity baseline of Akrout et al. Forward and feedback synapses independently recompute the same correlation from their own local activity pair and use matched optimizer and |
