Эксперимент: Doubled-angle orientation order pooling (#462)

{ "worked": true, "confidence": 9, "verdict": "Built differentiable doubled-angle pooling returning normalized Cartesian order channels and confidence, plus confidence-gated orientation recovery. Three predicted mechanisms were confirmed: exact π-reversal invariance (maximum error 0), equal-pair confidence q=|cos(delta)| (maximum discretization error 0.00619), and weighted resultant confidence (maximum error 0.00405); cancellation at 90° gives q≈5.6e-17. On the toy reversal-prototype task, pooling achieved 1.0 accuracy versus 0.03125 for directed-bin and scalar-average baselines, but no trained CNN or image benchmark was run.", "metrics": { "baseline": "Directed-bin reversal accuracy 0.03125; scalar-average reversal accuracy 0.03125", "idea": "Doubled-angle pooling reversal accuracy 1.0; reversal max error 0.0; q=|cos(delta)| max error 0.00619; weighted-q max error 0.00405; exact cancellation q=5.55e-17; non-canceling orientation error <=0.223 degrees" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 run_experiment.py", "files": [ "orientation_pooling.py", "run_experiment.py", "results.json" ], "limitations": "The experiment uses idealized orientation impulses and nearest-bin discretization, not natural images, learned steerable filters, or a trained CNN. FLOPs, optimization behavior, calibration, rotation equivariance under image transforms, and accuracy on CIFAR-10/MNIST-C were not tested." }