From 0008f2cd96c06bea98f43560867d93967c597711 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 19:45:46 -0500 Subject: docs: promote full dynamic ResNet result --- RESULTS.md | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) (limited to 'RESULTS.md') diff --git a/RESULTS.md b/RESULTS.md index 0a68133..d36edad 100644 --- a/RESULTS.md +++ b/RESULTS.md @@ -995,6 +995,26 @@ innovation result on the standard ResNet substrate, but it is still a one-seed short validation record. Per the frozen scoring rule it leaves the reviewer score at 5/10 and opens only the predeclared D3 full validation run. +The predeclared D3 full validation record then passes all 19 frozen gates: + +| method | validation accuracy | early alignment | epoch-151--200 feedback cosine | MAC ratio to BP | +|:--|--:|--:|--:|--:| +| dynamic neutral-projection innovation | **91.18%** | 0.999353 | 0.999663 | 1.3261x | +| clean KP | 91.26% | 0.9994 | 0.9997 | 1.326x | +| matched BP | 91.62% | exact | exact | 1.000x | + +D3 remains finite for 200 epochs and ends with validation loss `0.425251`. +The maximum unprojected neutral/traffic ratio is `0.008474`, whereas the +projected remainder and absolute soma slope stay below `3.04e-8` and +`2.13e-8`; used-signal/instruction RMS differs by at most `6.73e-10`. It uses +zero task-loss queries, 1.452e15 MACs, 4.070e13 separately reported elementwise +operations, one neutral observation per ordinary example, 2.165 GB peak +allocated memory, one final validation evaluation, and zero test evaluations. +The source revision is `d945c42`, and the gate was frozen before the endpoint. +This is the first full near-BP standard-ResNet SDIL validation result and raises +the strict reviewer score from 5 to 6. Independent five-seed paired test +confirmation remains open rather than assumed. + ## How to run `experiments/run.py --mode {bp,fa,dfa,sdil} --dataset {mnist,fmnist,cifar10} --depth D --residual {0,1} --act {tanh,gelu,silu,relu}` Batteries: `experiments/run_v2.sh "" "" `. -- cgit v1.2.3