BraiNCA: brain-inspired neural cellular automata and applications to morphogenesis and motor control

TL;DR

BraiNCA introduces a brain-inspired neural cellular automaton with long-range connections and attention mechanisms, improving robustness and learning speed for complex tasks compared to traditional grid-based NCAs.

Contribution

It presents a novel NCA model incorporating brain-like topology and attention, enhancing sample efficiency and damage tolerance in self-organization tasks.

Findings

BraiNCA outperforms vanilla NCAs in robustness and learning speed.

Incorporating long-range connections improves task performance.

Attention-based message routing enhances sample efficiency.

Abstract

Most of the Neural Cellular Automata (NCAs) defined in the literature have a common theme: they are based on regular grids with a Moore neighborhood (one-hop neighbour). They do not take into account long-range connections and more complex topologies as we can find in the brain. In this paper, we introduce BraiNCA, a brain-inspired NCA with an attention layer, long-range connections and complex topology. BraiNCAs shows better results in terms of robustness and speed of learning on the two tasks compared to Vanilla NCAs establishing that incorporating attention-based message selection together with explicit long-range edges can yield more sample-efficient and damage-tolerant self-organization than purely local, grid-based update rules. These results support the hypothesis that, for tasks requiring distributed coordination over extended spatial and temporal scales, the choice of interaction topology and the ability to dynamically route information will impact the robustness and speed of learning of an NCA. More broadly, BraiNCA provides brain-inspired NCA formulation that preserves the decentralized local update principle while better reflecting non-local connectivity patterns, making it a promising substrate for studying collective computation under biologically-realistic network structure and evolving cognitive substrates.