Livewired Neural Networks: Making Neurons That Fire Together Wire Together
This is an incremental proposal for improving neural networks to achieve human-like reasoning capabilities.
The paper tackles the problem of fixed network structures in artificial neural networks by proposing livewiring, a dynamic rewiring approach based on coincident neuron activations, with the potential to enable compositional world models and few-shot learning for human-level cognition.
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.