Answers are grounded in this paper and cite their sources.
Investigates the role of internal noise in reducing representational collapse in neural systems, suggesting vital thresholds.
Internal noise in neural systems is typically treated as a source of performancedegradation. We investigate whether controlled internal micro-variability can insteadprevent representational collapse in a transformer-based dynamical system.Using a Fitzhugh-Nagumo (FHN)-driven transformer as a testbed, we conduct asystematic sweep of internal Gaussian noise σ across three complementary measurementframeworks: (A-1/A-2) hidden geometry metrics (effective rank, collapseindex), (A-3) upper-bound sweep with MSE acceleration analysis, and (B) phaseenergymetrics (Δθ, R(t), phase-state classification).Across all frameworks, we identify a consistent safe edge band at σ = 0.10–0.20 (peak σ ≈ 0.15) in which effective rank is elevated, collapse index is reduced,edge-state proportion is maximized, and prediction error remains bounded. Belowthis band (σ ≈ 0.00), the system is fully collapse-dominated; above it (σ > 0.30),chaos-state proportion increases rapidly while geometric benefit saturates.These findings provide preliminary evidence that internal noise can function asan anti-collapse resource within a measurable band, consistent with the Layer-9Natural Fuzzy Immunity hypothesis in Safe Attractor Architecture (SAA). We donot claim direct proof of edge-of-chaos dynamics; the results are characterized aspreliminary evidence for a safe-edge-like regime.
No takes yet. Share an insight, caveat, or question.
Jun Sakai (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: