Эксперимент: Correlated stochastic integrate-and-fire recurrent layer (#1427)

{ "worked": true, "confidence": 7, "verdict": "Built a correlated stochastic integrate-and-fire recurrent layer with shared/independent Euler-Maruyama noise, refractory reset, threshold spikes, and exponential population-rate filtering. The covariance identity and filter recurrence were numerically verified, with maximum errors 5.2e-6 and 5.6e-17 respectively. On the toy sequence task, correlated noise substantially reduced gradient-norm variance versus independent noise (0.0221 vs 1.1728) and firing activity (6.0% vs 9.0%), but did not match the deterministic baseline’s accuracy or improve noisy-input accuracy; the observed win is therefore limited to training-gradient variance and sparsity signals.", "metrics": { "baseline": "Deterministic leaky RNN: accuracy 0.9551, noisy accuracy 0.5000, gradient-norm variance 0.0471", "idea": "Correlated IF (rho initialized 0.65): accuracy 0.7246, noisy accuracy 0.5137, gradient-norm variance 0.0221, firing rate/activity 0.0600" }, "how_to_run": "/home/maxwelhelp/main/bin/python3 experiment.py", "files": [ "experiment.py", "results.json" ], "limitations": "Only one small synthetic sequence-classification task and one seed were tested; no sequential MNIST, parameter/FLOP-matched architecture audit, multi-seed confidence intervals, long-horizon stability study, or systematic rho/noise/refractory ablation was performed." }