Variational Neural Cellular Automata
This work addresses generative modeling for data self-organization, but it is incremental as it builds on existing cellular automata concepts with a probabilistic twist.
The authors tackled the problem of generative modeling by proposing the Variational Neural Cellular Automata (VNCA), a probabilistic model inspired by biological cellular growth, which learns to generate diverse outputs from a common vector format and can recover from damage, though it shows a significant gap to state-of-the-art performance.
In nature, the process of cellular growth and differentiation has lead to an amazing diversity of organisms -- algae, starfish, giant sequoia, tardigrades, and orcas are all created by the same generative process. Inspired by the incredible diversity of this biological generative process, we propose a generative model, the Variational Neural Cellular Automata (VNCA), which is loosely inspired by the biological processes of cellular growth and differentiation. Unlike previous related works, the VNCA is a proper probabilistic generative model, and we evaluate it according to best practices. We find that the VNCA learns to reconstruct samples well and that despite its relatively few parameters and simple local-only communication, the VNCA can learn to generate a large variety of output from information encoded in a common vector format. While there is a significant gap to the current state-of-the-art in terms of generative modeling performance, we show that the VNCA can learn a purely self-organizing generative process of data. Additionally, we show that the VNCA can learn a distribution of stable attractors that can recover from significant damage.