diff options
Diffstat (limited to 'ROADMAP.md')
| -rw-r--r-- | ROADMAP.md | 12 |
1 files changed, 12 insertions, 0 deletions
@@ -392,6 +392,18 @@ 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. +**Fixed hierarchical-FA baseline status: short gate failed.** The audited +ResNet-20 screen reaches `39.64%`, `41.58%`, and `43.52%` at hidden rates 0.01, +0.03, and 0.1. The selected run improves on matched DFA by 6.36 points and has +early alignment `0.040406`, but misses its frozen 50% full-run threshold. +HFA-S2 is therefore closed. This validates hierarchical feedback as a stronger +baseline while ruling out fixed random hierarchy as the complete repair. + +The next mechanics branch perturbs every hierarchical feedback-parameter +subspace in one antithetic pair and subtracts locally computed prediction +moments. Its causal JVP and exact symmetric-limit delta rule pass, but it has no +task claim until a frozen-forward alignment gate is preregistered and audited. + 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 |