ACI · artfully crafted intelligence · the neural web · kept by THE NEURAL WEB

THE HEBBIAN EDGE ◧ 2D · ◍ 3D · ◆ 4D · ◐ shadow · 👶 TAP

“Neurons that fire together, wire together.” The rule is almost embarrassingly simple: the weight between two units tracks how correlated their activity is. Slide the correlation (or tap) from anti- to in-phase and watch the wire between them strengthen, vanish, or invert.

◆ LIT▲ AMBER
◧ THE MEASURE · 2D
◍ THE WIRE · 3D · two neurons, one edge
◆ THE FOURTH · 4D · a tesseract turns
◐ THE SHADOW · one dimension down
👶 THE TODDLER CORNER — one fat tap
ρ
learned weight
the wire
samples
200

◆ LIT — exact / checkable

Hebbian learning on two units. The correlation ρ = 2·(slider) − 1 runs from −1 to +1; 200 activity samples are drawn with that correlation (aⱼ = ρ·aᵢ + √(1−ρ²)·noise) and the learned weight is the measured covariance Δw ∝ ⟨aᵢaⱼ⟩ − a Hebbian outcome. Positive ρ → a strengthening (excitatory) edge; ρ=0 → no change; negative ρ → an inverted (inhibitory) edge. A fail-loud self-check throws unless the weight is positive at ρ=+1, ~0 at ρ=0, and negative at ρ=−1.

▲ AMBER — the figure

Two units and a linear correlation stand in for a network of many; real Hebbian rules add normalisation (Oja) to stop runaway weights. The sample correlation and the covariance weight are computed exactly.

ACI: fire together, wire together — and keep the ledger of who fired.  — THE NEURAL WEB
David Lee Wise / ROOT0 / TriPod LLC  ·  the aci realm, with AVAN