Эксперимент: Tiny Local Recurrence with Adaptive Computation (#907)

{ "worked": true, "confidence": 8, "verdict": "Built a shared adaptive recurrence classifier and a six-block residual MLP baseline with fixed seeds and CUDA fallback. The toy checks confirmed the predicted stability boundary, exact halting-time formula, and monotonic reduction in halting time as the bias increases. The idea matched baseline accuracy while using 74.2% fewer parameters and 31.5% fewer average microsteps, but it was slower wall-clock because of recurrent Python/control-flow overhead.", "metrics": { "baseline": "accuracy=0.990234375; parameters=13218; average microsteps=6.0; train time=5.69s", "idea": "accuracy=0.990234375; parameters=3411; average microsteps=4.1074; train time=14.93s; all three mechanism checks confirmed" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "Only a small 2D synthetic classification task was tested. MNIST, CIFAR-10, arithmetic extrapolation, explicit FLOP measurements, hard/easy error curves, and larger-scale generalization were not tested." }