Livewired Neural Networks: Making Neurons That Fire Together Wire Together

TL;DR

This paper proposes livewired neural networks that dynamically rewire based on neuron activations, aiming to emulate brain-like adaptability, improve few-shot learning, and build compositional models for advanced reasoning.

Contribution

It introduces the concept of livewired neural networks that adapt their structure in real-time, inspired by brain mechanisms, to enhance learning and reasoning capabilities.

Findings

Livewired networks can dynamically rewire based on neuron activity.

Evidence suggests glial cells guide livewiring in the brain.

Livewiring may lead to emergent associative behaviors.

Abstract

Until recently, artificial neural networks were typically designed with a fixed network structure. Here, I argue that network structure is highly relevant to function, and therefore neural networks should be livewired (Eagleman 2020): dynamically rewired to reflect relationships between higher order representations of the external environment identified by coincident activations in individual neurons. I discuss how this approach may enable such networks to build compositional world models that operate on symbols and that achieve few-shot learning, capabilities thought by many to be critical to human-level cognition. Here, I also 1) discuss how such livewired neural networks maximize the information the environment provides to a model, 2) explore evidence indicating that livewiring is implemented in the brain, guided by glial cells, 3) discuss how livewiring may give rise to the associative emergent behaviors of brains, and 4) suggest paths for future research using livewired networks to understand and create human-like reasoning.