SOURCE-LINKED INTELLIGENCE

Biologically Inspired Mechanisms for Facilitating Grokking in Multilayer Perceptrons

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Grokking is a delayed transition from memorization to generalization that is often accompanied by substantial reorganization of internal representations. This paper studies whether biologically inspired mechanisms, many of which are not commonly incorporated into artificial neural networks, can actively promote this transition by regulating hidden-layer computation at the levels of neuronal activity, response, and effective connectivity. We augment a multilayer perceptron with input gating, structural plasticity, gain modulation, threshold modulation, homeostasis, lateral inhibition, and activ

Read original source ↗ Open in workspace

recordType

paper

region

Global