SIG-NmNN (Spike-Intensity Growth Non-Monotonic Neural Networks): a framework where neuronal activation regions dynamically expand based on accumulated spike intensity. This creates neurons that "breathe" with their input—contracting during low activity, expanding during high activity—and naturally produces fractal structures through power-law scaling when neurons are nested hierarchically..
Experiment: The Blue Torus is the activation volume. The Sphere is the input. Watch the torus expand physically as intensity builds. The input glows GREEN when inside the volume and RED when outside.
Experiment: Comparison of integration dynamics with discrete time step Δt=0.1 (Stable) vs Δt=2.1 (Unstable).