Leaky magnitude-of-sum activity accumulator

Read the equation

The state retains 99% of its previous energy value and takes 1% of the absolute sum of the current components. Opposite-sign components can cancel before the absolute value, so this is not the Euclidean norm or sum of absolute activities. With nonnegative initialization it stays nonnegative and smooths its scalar target over time.

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

ΔW[i][j] = η × y[i] × x[j]                     // Hebbian learning

state[i] = 0.95 × state[i] + 0.05 × (y[i] + core[i])  // State update

energy = 0.99 × energy + 0.01 × |Σ state|     // Energy accumulation

5.4 Integration Metrics

φ_local = tanh(energy)                          // Per-strand [Eq. 485]

φ_global = tanh(Σ(all states) / 256)           // Global [Eq. 486]

energy = 0.99 × energy + 0.01 × |Σ state|     // Energy accumulation