diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 14:17:04 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-07-22 14:33:50 -0500 |
| commit | 41048d9d9c399ded6f5c473b578f59e6ac375ae9 (patch) | |
| tree | 9bcfa1e540957500b9bb82e2c4e4537fe802c25f /NOVELTY.md | |
| parent | d761f655301e3535368a87e9d4ffc26ab1ab8510 (diff) | |
protocol: freeze reciprocal KP baseline funnel
Diffstat (limited to 'NOVELTY.md')
| -rw-r--r-- | NOVELTY.md | 7 |
1 files changed, 7 insertions, 0 deletions
@@ -76,6 +76,13 @@ this attribution. Its zero-noise fixed point and any resulting scale belong to local predictive weight estimation; they become relevant to SDIL only as the feedback substrate on which innovation is separately ablated. +The modified Kolen--Pollack reciprocal-plasticity path is likewise inherited +from Akrout et al. Equal local activity products and matched decay in reciprocal +synapses are not SDIL. Even if the audited implementation reaches BP-level +accuracy, it only supplies a stable feedback substrate. The candidate novelty +still requires neutral somato-dendritic subtraction to outperform raw and +norm-matched raw apical activity under the same mixed-traffic intervention. + ## Candidate SDIL contribution The candidate contribution is the combination |
