Эксперимент: Event-triggered phase desynchronisation for recurrent hidden states (#918)

{ "worked": true, "confidence": 8, "verdict": "Built a reproducible phase-controller verification and small recurrent classification experiment. The continuous Lyapunov law matched finite differences across gains k=0.25–2.0 with ratios 1.000002–1.000015, and event rates decreased approximately inversely with delta while dwell times tracked the empirical delta/M bound. The mechanism manifested, but it did not improve this classifier: baseline accuracy was 0.875 versus 0.852 event-triggered and 0.813 continuous.", "metrics": { "baseline": "Toy initial Vdot at k=1: observed -0.004780887, predicted -0.004780850; RNN accuracy 0.875; zero events per sequence.", "idea": "Event counts for delta [0.005, 0.02, 0.08, 0.2]: [128, 32, 6, 1]. Event RNN accuracy 0.8516 with 22.53 events per sequence; rotation norm error 2.61e-8." }, "how_to_run": "CUDA_VISIBLE_DEVICES='' /home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "Only one seed and one tiny synthetic sequence-classification task were tested. Sequential MNIST, multi-seed statistics, tuning, FLOP or communication benchmarks, and larger recurrent/state-space models were not tested; the largest-delta run had only one event, so its minimum dwell time was unavailable." }