Growing Artificial Neural Networks for Control: the Role of Neuronal Diversity

TL;DR

This paper introduces a novel method for growing artificial neural networks inspired by biological development, emphasizing neuronal diversity and stability to improve performance in reinforcement learning tasks.

Contribution

It presents an algorithm that maintains neuronal diversity during growth using intrinsic neuron states and lateral inhibition, enhancing the robustness of neural development programs.

Findings

Neuronal diversity is crucial for complex task performance.

Intrinsic neuron states help preserve diversity during growth.

Lateral inhibition stabilizes growth and diversity.

Abstract

In biological evolution complex neural structures grow from a handful of cellular ingredients. As genomes in nature are bounded in size, this complexity is achieved by a growth process where cells communicate locally to decide whether to differentiate, proliferate and connect with other cells. This self-organisation is hypothesized to play an important part in the generalisation, and robustness of biological neural networks. Artificial neural networks (ANNs), on the other hand, are traditionally optimized in the space of weights. Thus, the benefits and challenges of growing artificial neural networks remain understudied. Building on the previously introduced Neural Developmental Programs (NDP), in this work we present an algorithm for growing ANNs that solve reinforcement learning tasks. We identify a key challenge: ensuring phenotypic complexity requires maintaining neuronal diversity, but this diversity comes at the cost of optimization stability. To address this, we introduce two mechanisms: (a) equipping neurons with an intrinsic state inherited upon neurogenesis; (b) lateral inhibition, a mechanism inspired by biological growth, which controlls the pace of growth, helping diversity persist. We show that both mechanisms contribute to neuronal diversity and that, equipped with them, NDPs achieve comparable results to existing direct and developmental encodings in complex locomotion tasks