◄ UD0   noise (Ising)   spin (oscillators)   Kuramoto laser
Perceptron theory · the 15th body · computing in phase

The perceptron in sync

Every other body stored a number — a voltage, a current, an amplitude, a probability. This one stores a phase: the moment in its cycle at which an oscillator peaks. Couple a crowd of them and they start to listen to each other; turn the coupling up and they fall into step. Two oscillators beating together mean "agree"; a half-cycle apart, "disagree". The computation isn't a sum that lands on a value — it's a whole population finding the pattern of agreement that fits the wiring. The answer is the synchronization.
state = phase (not charge)  ·  weights = couplings  ·  multiply+sum = Kuramoto coupling Σ wᵢⱼ·sin(θⱼ−θᵢ)  ·  nonlinearity = phase-locking  ·  ±1 = in/anti-phase
✓ STRONG

Kuramoto & oscillator Ising machines. Coupled-oscillator synchronization is textbook nonlinear dynamics; oscillator Ising machines (Wang & Roychowdhury) solve optimisation by phase. Solid and demonstrated.

◐ MIDDLING

Oscillatory neural nets. Real hardware — four spin-torque nano-oscillators recognised spoken vowels (Romera & Grollier, Nature 2018); VO₂ & CMOS ONNs exist — but small and finicky to scale.

◔ FRONTIER

Large phase-computing nets. Scaling oscillator networks into general learning machines, with stable precision, is open.

I · Coupling, and the moment they fall into step

A swarm of oscillators, each with its own natural rhythm, scattered around the phase circle. With no coupling they drift independently and the crowd is a smear. Turn the coupling K up and each one feels a pull toward the others — dθᵢ/dt = ωᵢ + (K/N) Σⱼ sin(θⱼ − θᵢ) — until, past a threshold, the smear snaps into a single moving cluster. The length of the order vector is how synchronized they are: 0 for chaos, 1 for one mind.

each dot = an oscillator's phase on the circle · the order vector (centroid) grows as they synchronize
0.05
order parameter r (synchrony)
incoherent
regime
This phase transition — drift to lockstep at a critical coupling — is the Kuramoto model, and it's the engine here: not a clock forcing steps, but a population settling into agreement on its own.

II · In-phase is +1, anti-phase is −1

Encode a bit as a phase: lock to the reference (in-phase, +1) or sit a half-cycle off it (anti-phase, −1). Feed two such inputs to an output oscillator through weighted couplings; it feels the net pull and locks in-phase when the weighted vote is positive, anti-phase when negative. Read its phase against the reference and you've read a thresholded weighted sum — a perceptron whose output is whether it ended up beating with you or against you.

x₁ x₂
three oscillators (x₁, x₂, output) · the output locks in/anti-phase to the reference by the weighted drive
+0.00
net drive b + Σwᵢxᵢ
anti-phase — dark
fires when it locks in-phase

III · The Ising machine, learning, and the gift

Wire oscillators with signed couplings and let them settle — they relax to the phase pattern that satisfies the most couplings, which is exactly minimising an Ising energy. A triangle that all wants to disagree can't win everywhere: it lands two-against-one, the best a frustrated graph allows. The neuron learns AND/OR; XOR is one cut, so it needs more oscillators (depth). The gift is that relaxation is the computation — no clocked steps, just a network humming its way to the answer.

the gift= relaxation = computationthe variable= phase, not chargereal hardware= spin-torque oscillators (vowels, 2018)the role= optimiser / associative recall

Honest place in the family: oscillator networks shine at optimisation and pattern completion — letting a system relax rather than step. They overlap the noise body (both minimise an energy) but the variable is different: deterministic phase, not thermal chance. It's the audit's last distinct avenue, and now it's filled.

…N-cubi · noise · reverse · sync  —  the atlas is whole