diff options
Diffstat (limited to 'RESULTS.md')
| -rw-r--r-- | RESULTS.md | 19 |
1 files changed, 19 insertions, 0 deletions
@@ -446,6 +446,25 @@ neutral residualization raises the teaching squared cosine from `0.7492` to `0.9 task-period fitting lowers it to `0.5395` by removing soma-correlated teaching. **The frozen C5 theory package and numerical checks pass.** +### Normalized-regression development screen (task seed 0 only) + +The final bounded C2 recovery divided each context-vectorizer regression update by the complete +feature power of `[c, c outer tanh(h_top)]`. It fixed the feedback-first prefix at 100 layerwise-K4 +steps, retained simultaneous K1/e4 joint calibration, and compared only `eta_A in {0.01, 0.05}`. + +| NLMS eta_A | depth | validation acc (%) | depth gain | d4 lesion drop | d4 work / ordinary | +|-----------:|------:|-------------------:|-----------:|----------------:|-------------------:| +| 0.01 | 1 | 70.717 ± 2.759 | — | — | — | +| 0.01 | 4 | 75.150 ± 23.011 | +4.433 | +26.000 | 2.5x | +| 0.05 | 1 | 73.000 ± 2.783 | — | — | — | +| 0.05 | 4 | 73.350 ± 23.008 | +0.350 | +19.533 | 2.5x | + +Both settings have only 2/3 positive depth gains and lesions, and neither approaches the frozen +90% d4 threshold. Small per-example feature norms amplify perturbation noise despite finite final +losses. **No NLMS candidate is eligible; further tent-map tuning is closed and task seeds 6--8 +remain untouched.** Direct NP still establishes that causal local updates can solve the task, but +the current low-query amortized vectorizer cannot reliably track them. + ## Paper-faithful non-backprop baselines `PETITE` in the initial request is treated as **PEPITA**. Implementations and hyperparameters were |