ConceptBCM Rule / Bienenstock-Cooper-Munro规则

BCM Rule

An improved variant of the Hebbian learning rule that introduces a sliding modification threshold to address the instability of the pure Hebbian rule, making the learning rule more stable and practical in real neural networks.

Timeline (last 90 days)

Oct 13

To improve the stability of the Hebbian rule, researchers proposed the Oja rule (introducing weight decay to achieve normalization) and the BCM rule (introducing a sliding modification threshold).

Unverified50%

All Facts (1)

Unverified

To improve the stability of the Hebbian rule, researchers proposed the Oja rule (introducing weight decay to achieve normalization) and the BCM rule (introducing a sliding modification threshold).

50%

Source Articles

How Neural Networks Build Their Own Learning Mechanisms: Insights from Brain Science for Unsupervised LearningOct 13