Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces BraiNCA, a novel Neural Cellular Automata architecture that incorporates attention mechanisms, long-range connections, and complex topologies inspired by brain networks. BraiNCA outperforms vanilla NCAs in morphogenesis and motor control tasks, demonstrating improved robustness and learning speed. The results highlight the importance of interaction topology and dynamic information routing for sample-efficient and damage-tolerant self-organization in tasks requiring distributed coordination.
Brain-inspired Neural Cellular Automata (BraiNCA) show that mimicking the brain's complex connectivity and attention mechanisms can significantly boost the robustness and speed of learning in self-organizing systems.
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.