Date:

Neural Cellular Automata

Contents

Thread Nav

This article is part of the Differentiable Self-organizing Systems Thread, an experimental format collecting invited short articles delving into differentiable self-organizing systems, interspersed with critical commentary from several experts in adjacent fields.

Differentiable Self-organizing Systems Thread
Self-classifying MNIST Digits

Model

Those in engineering disciplines and researchers often use many kinds of simulations incorporating local interaction, including systems of partial derivative equation (PDEs), particle systems, and various kinds of Cellular Automata (CA). We will focus on Cellular Automata models as a roadmap for the effort of identifying cell-level rules which give rise to complex, regenerative behavior of the collective.

Cell State

We will represent each cell state as a vector of 16 real values (see the figure above). The first three channels represent the cell color visible to us (RGB). The target pattern has color distribution is so strong it allowed us to build Neural CA models using components readily available in popular ML frameworks.

Discussion

Embryogenetic Modeling

Regeneration-capable 2-headed planarian, the creature that inspired this work

Reproduce in a Notebook

Swarm Robotics

One of the most remarkable demonstrations of the power of self-organisation is when it is applied to swarm modeling. Back in 1987, Reynolds’ Boids simulated the flocking behaviour of birds with just a tiny set of handcrafted rules. Nowadays, we can embed tiny robots with programs and test their collective behavior on physical agents, as demonstrated by work such as Mergeable Nervous Systems and Kilobots .

Conclusion

This article describes a toy embryogenesis and regeneration model. This is a major direction for future work, with many applications in biology and beyond.

Frequently Asked Questions

Q1: What is the main topic of this article?

A1: The main topic of this article is the concept of self-organisation and its applications in different fields, including biology and machine learning.

Q2: What are some examples of self-organising systems?

A2: Some examples of self-organising systems include flocks of birds, schools of fish, and social networks.

Q3: What are the benefits of self-organising systems?

A3: The benefits of self-organising systems include their ability to adapt to changing environments and to self-organise and self-repair.

Q4: What are the potential applications of self-organising systems?

A4: The potential applications of self-organising systems include biology, medicine, and engineering, among others.

Q5: How can self-organising systems be modelled?

A5: Self-organising systems can be modelled using a variety of methods, including cellular automata, agent-based models, and differential equations.

Latest stories

Read More

LEAVE A REPLY

Please enter your comment!
Please enter your name here