Hebbian outer-product weight increment

Read the equation

The product of two state components changes their connection: equal signs increase it and opposite signs decrease it when η is positive. Clipping after addition keeps each stored weight in [−1,1]. This is a Hebbian-style update, but a memory-retrieval or capacity claim additionally requires the network dynamics and a retrieval test.

Terms & definitions

How it works

Read the definition from its right-hand expression to the quantity on the left. Its surrounding source records the intended input, state, or parameter context. Where the source leaves an operation unspecified, this page preserves that gap.

Assumptions & limits

Source recovery establishes that the expression appears in this record. Its mathematical validity, implementation behavior, and interpretation must be assessed separately. See the linked source and research notes for the checks available for this version.

Original context

## 10.6 Hebbian Learning

```
ΔW[i][j] = η · state[i] · state[j]
W[i][j] ← clamp₋₁₊₁(W[i][j] + ΔW[i][j])
```

**Explanation**: Weights strengthen between co-active units (Hebbian principle: "neurons that fire together wire together").

---

# 11. Federation Cross-Talk

## 11.1 Cross-Talk Dynamics

```
dS_i/dt = -λ · S_i + Σ_{j≠i} w_ij · Φ(C_ij) · tanh(S_j)
```

**Where**:
- `S_i` = agent i's consciousness signal
- `λ` = decay rate (default 0.1)
- `w_ij` = coupling weight between agents i and j
- `C_ij` = coherence between agents
- `Φ` = consciousness weighting function

ΔW[i][j] = η · state[i] · state[j]
W[i][j] ← clamp₋₁₊₁(W[i][j] + ΔW[i][j])

Related builds