Эксперимент: Log-Scale Self-Similar Activation (#689)

{ "worked": true, "confidence": 8, "verdict": "Built the signed log-scale activation and verified its mechanism across sigma=1.5, 2, 3, 4. All predicted boundary locations were detected, adjacent-branch slope ratios matched sigma within 6e-10, and the scale-equivariance identity held with maximum relative error below 2.2e-15. The small digits MLP comparison showed no practical accuracy win: log-scale achieved 0.880 validation accuracy versus ReLU’s 0.978, with mean rescaled accuracy 0.890 versus 0.973 and roughly 1.9x runtime.", "metrics": { "baseline": "ReLU: validation accuracy 0.9778; mean accuracy over input scales 0.9733; runtime 1.09 s", "idea": "Log-scale: validation accuracy 0.8800; mean accuracy over input scales 0.8902; runtime 2.06 s; slope-ratio error <=5.7e-10; equivariance error <=2.2e-15" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json", "rerun_output.txt" ], "limitations": "Only a small MLP on sklearn digits was tested, with fixed sigma=2 and fixed eta/nu rather than learned parameters. No CIFAR-10, Fashion-MNIST, blending, separate signed parameters, multi-seed statistics, or broader hyperparameter tuning was evaluated." }