Emergent Dynamics in Neural Cellular Automata (2404.06406v3)
Abstract: Neural Cellular Automata (NCA) models are trainable variations of traditional Cellular Automata (CA). Emergent motion in the patterns created by NCA has been successfully applied to synthesize dynamic textures. However, the conditions required for an NCA to display dynamic patterns remain unexplored. Here, we investigate the relationship between the NCA architecture and the emergent dynamics of the trained models. Specifically, we vary the number of channels in the cell state and the number of hidden neurons in the MultiLayer Perceptron (MLP), and draw a relationship between the combination of these two variables and the motion strength between successive frames. Our analysis reveals that the disparity and proportionality between these two variables have a strong correlation with the emergent dynamics in the NCA output. We thus propose a design principle for creating dynamic NCA.
- A database and evaluation methodology for optical flow. International Journal of Computer Vision, 92(1):1–31.
- Describing textures in the wild. In Proceedings of the IEEE Conf. on Computer Vision and Pattern Recognition (CVPR).
- Gardner, M. (1970). Mathematical games. Scientific american, 222(6):132–140.
- Growing neural cellular automata. Distill. https://distill.pub/2020/growing-ca.
- Collective control of modular soft robots via embodied spiking neural cellular automata. arXiv preprint arXiv:2204.02099.
- Asynchronicity in neural cellular automata. In Artificial Life Conference Proceedings 33, volume 2021, page 116. MIT Press One Rogers Street, Cambridge, MA 02142-1209, USA journals-info ….
- Self-organising textures. Distill, 6(2):e00027–003.
- Mesh neural cellular automata. arXiv preprint arXiv:2311.02820.
- Dynca: Real-time dynamic texture synthesis using neural cellular automata. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 20742–20751.
- Self-classifying mnist digits. Distill. https://distill.pub/2020/selforg/mnist.
- Growing 3d artefacts and functional machines with neural cellular automata. In Artificial Life Conference Proceedings 33, volume 2021, page 108. MIT Press One Rogers Street, Cambridge, MA 02142-1209, USA journals-info ….
- Goal-guided neural cellular automata: Learning to control self-organising systems. arXiv preprint arXiv:2205.06806.
- Two-stream convolutional networks for dynamic texture synthesis. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 6703–6712.
- Theory of self-reproducing automata. IEEE Transactions on Neural Networks, 5(1):3–14.
- A new kind of science. Appl. Mech. Rev., 56(2):B18–B19.