faeval.git/results/cnn_baseline, branch master

Recompute all CNN diagnostics with fixed BP gradient flow

2026-04-03T22:35:12+00:00

CNN CIFAR-10 (5 seeds, fixed Gamma):
BP: acc=86.8%, Gamma=0.970, rho=0.603
DFA: acc=56.7%, Gamma=0.896, rho=0.061
EP: acc=50.6%, Gamma=0.484, rho=0.450
SB: acc=63.3%, Gamma=1.000 (BP self-cos, feedback nets not saved), rho=0.601
CB: acc=31.8%, Gamma=1.000 (BP self-cos), rho=0.226

DFA Gamma=0.896 is notably high — CNN DFA credit aligns well with BP gradients.

Co-Authored-By: Claude Opus 4.6 (1M context)

Update all EP results with sign-corrected credit

2026-04-03T15:23:25+00:00

EP Synthetic (fixed): Gamma=+0.13~0.20, rho=+0.25
EP CIFAR d=256: Gamma=+0.007, rho=+0.051
EP CIFAR d=512: Gamma=+0.000, rho=-0.002
EP CNN: Gamma=+0.248, rho=+0.492

Co-Authored-By: Claude Opus 4.6 (1M context)

Add CNN SB+CB results (5 seeds each), update summary CSV

2026-04-02T22:50:02+00:00

CNN CIFAR-10 (5 seeds):
BP: 86.8%±0.3%, Gamma=0.238, rho=0.250
DFA: 56.7%±2.0%, Gamma=0.216, rho=0.017
SB: 63.3%±0.5%, Gamma=0.045, rho=0.298
CB: 31.8%±6.2%, Gamma=0.013, rho=0.033

Co-Authored-By: Claude Opus 4.6 (1M context)

Add summary CSVs for EP, GELU ablation, CNN

2026-04-02T19:47:58+00:00

Co-Authored-By: Claude Opus 4.6 (1M context)

Add EP baseline (5 seeds), GELU ablation (20 runs), CNN BP+DFA (10 runs)

2026-04-02T19:42:02+00:00

EP (L=4 d=256): acc≈30%, Gamma≈0, rho≈0 — EP credit signal weak on feedforward MLP
GELU ablation (ReLU variant): 4 methods × 5 seeds complete
CNN BP+DFA: 5 seeds each, BP + DFA on SmallCNN

Co-Authored-By: Claude Opus 4.6 (1M context)