Drawing Inspiration from Biological Dendrites to Empower Artificial Neural Networks

TL;DR

This paper explores how features of biological dendrites can be incorporated into artificial neural networks to enhance their computational power and efficiency, potentially leading to more capable and energy-efficient machine learning models.

Contribution

It proposes specific biological dendritic features for integration into artificial neurons and discusses their potential benefits for machine learning.

Findings

Dendritic nonlinearities can improve neural network processing.

Compartmentalized plasticity rules may enhance learning efficiency.

Biological features could lead to more powerful and energy-efficient AI models.

Abstract

This article highlights specific features of biological neurons and their dendritic trees, whose adoption may help advance artificial neural networks used in various machine learning applications. Advancements could take the form of increased computational capabilities and/or reduced power consumption. Proposed features include dendritic anatomy, dendritic nonlinearities, and compartmentalized plasticity rules, all of which shape learning and information processing in biological networks. We discuss the computational benefits provided by these features in biological neurons and suggest ways to adopt them in artificial neurons in order to exploit the respective benefits in machine learning.