diff options
Diffstat (limited to 'RESULTS.md')
| -rw-r--r-- | RESULTS.md | 22 |
1 files changed, 22 insertions, 0 deletions
@@ -868,6 +868,28 @@ so the single RRM-3 full validation run opens. The 9.86-point gap despite nearly perfect instantaneous alignment is retained as a negative diagnostic rather than treating cosine as a proxy for optimization equivalence. +### Modified Kolen--Pollack reciprocal baseline + +The independently implemented Akrout et al. reciprocal-plasticity baseline +uses the same local parent activity and child teaching field at corresponding +forward and feedback synapses, but each path recomputes its own correlation. +It never reads or copies a weight or weight-update tensor. Mechanics checks +give exactly zero direction, post-observation independence, and symmetric- +limit update errors. + +Its sole frozen 20-epoch full-development record passes every KP-1 gate: + +| method | validation accuracy | early alignment | train-period feedback cosine | estimated MACs | +|:--|--:|--:|--:|--:| +| KP | **82.66%** | 0.885583 | 0.854594 (epochs 11--20) | 1.4519e14 | +| BP at epoch 20 | 81.02% | n/a | exact by construction | 1.0949e14 | + +KP's final feedback/forward cosine is 0.901034. It uses zero task-loss queries, +costs `1.3261x` matched BP after explicitly charging the second reciprocal +correlation, and remains finite throughout the constant-LR screen. The result +opens the frozen KP-2 full baseline. It is entirely prior-art baseline evidence +and does not change the SDIL reviewer score. + ## 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 <ds> "<depths>" <res> <act> "<seeds>" <ep> <pfx>`. |