From 2ec92906b45018665de97d6de63d6a754a1508d6 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 13:05:04 -0500 Subject: analysis: identify hierarchical spatial credit bottleneck --- ROADMAP.md | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'ROADMAP.md') diff --git a/ROADMAP.md b/ROADMAP.md index 4f6c315..15699e2 100644 --- a/ROADMAP.md +++ b/ROADMAP.md @@ -383,6 +383,15 @@ remains sealed. This closes learning-rate tuning of the same output-error-only channel-gated family; a further branch must make a substantive feedback-context or cross-layer-noise change. +The fixed post-failure hierarchical oracle identifies the substantive next +change. Ordinary downstream activation context moves early alignment only from +`0.031123` to `0.032069`, while held-out local maps from the actual residual-DAG +child error fields reach `0.440525` (1x1), `0.819917` (3x3), and `0.999767` +(3x3 plus the locally available child ReLU gate). This is not task evidence +and uses exact child gradients as oracle inputs. It establishes that future +development should learn spatial hierarchical feedback without weight copying, +with random/fixed hierarchical FA and BurstCCN as mandatory baselines. + Prepare convolutional local-update primitives and ResNet-20/32/56 protocols early. Queue frozen runs opportunistically on authorized idle GPUs. Because BurstCCN already reports CIFAR-10 and ImageNet scaling, dataset scale alone is not novel. The oral-level target is a memorable joint -- cgit v1.2.3