Experiments

V16: Hebbian Plasticity

Negative result. Mean robustness dropped to 0.892 — lowest of all substrates. Zero cycles exceeded 1.0.

Addition: Local Hebbian learning rules allowing each spatial location to modify its coupling structure in response to experience.

Lesson: Simple learning rules are too blunt. The extra degrees of freedom overwhelm the selection signal. Plasticity added noise faster than selection could filter it.

V13-V16 substrate comparison: robustness trajectories and aggregate comparison — **V13–V16 substrate evolution comparison.** Top-left: per-cycle robustness trajectories across all seeds (V13 green, V15 black, V16 red). V16 (Hebbian plasticity) consistently tracks lowest. Top-right: V16 learning rate evolution — highly variable, not converging. Bottom-left: V16 coupling spatial variance collapses to zero (homogenization, not differentiation). Bottom-right: aggregate comparison confirms V13 content coupling (0.923) > V15 temporal memory (0.907) > V16 plasticity (0.892).

Source code

v16_substrate.py — Hebbian plasticity implementation
v16_evolution.py — Evolution loop
v16_gpu_run.py — GPU runner