HEBBIAN LEARNING · Hebbian update: ΔW

Read the equation

This relation defines Hebbian update: ΔW in the source section “HEBBIAN LEARNING · Hebbian update: ΔW”. It specifies the displayed relationship between the named quantities or parameters. Its interpretation depends on the source’s stated variables and conditions; this record does not assign an unprovided physical or cognitive meaning to them.

Terms & definitions

The recovered passage does not supply a separate symbol table. Read the source context for the notation used in this version; familiar letters may carry different meanings in other builds.

How it works

1. Read Hebbian update: ΔW as the quantity being defined or updated by this relation.

2. Substitute the source-defined variables or recorded values and follow the displayed arithmetic and indexing exactly.

3. Use this version’s variable definitions and update order. The same symbol may be assigned a different meaning in another build.

Assumptions & limits

• This source expression was recovered from the pinned code revision. Its presence does not establish that the associated program was built, run, or scientifically validated.

Original context

            }
        }
        lr = static_cast<float>(ALPHA);
        decay = 0.01f;
        threshold = 0.1f;
    }

    // Hebbian update: ΔW = η·x·y
    void update(const float* pre, const float* post) {
        for (size_t i = 0; i < DIM; ++i) {
            for (size_t j = 0; j < DIM; ++j) {
                // Only update if both pre and post are above threshold
                if (std::abs(pre[j]) > threshold && std::abs(post[i]) > threshold) {
                    W[i][j] += lr * pre[j] * post[i];
                }
                // Weight decay
                W[i][j] *= (1.0f - decay);
                // Clamp

Hebbian update: ΔW = η·x·y

Related builds