Game of Intelligent Life

TL;DR

This paper explores neural cellular automata by arranging convolutional neural networks in a grid to create prediction machines that learn to predict future states through local interactions and fitness-based updates.

Contribution

It introduces a novel approach of using neural cellular automata to grow prediction machines with self-organizing properties and adaptive movement capabilities.

Findings

Cells successfully learned to predict next states.

Movement and stochasticity improved exploration.

Fitness scores guided local learning effectively.

Abstract

Cellular automata (CA) captivate researchers due to teh emergent, complex individualized behavior that simple global rules of interaction enact. Recent advances in the field have combined CA with convolutional neural networks to achieve self-regenerating images. This new branch of CA is called neural cellular automata [1]. The goal of this project is to use the idea of idea of neural cellular automata to grow prediction machines. We place many different convolutional neural networks in a grid. Each conv net cell outputs a prediction of what the next state will be, and minimizes predictive error. Cells received their neighbors' colors and fitnesses as input. Each cell's fitness score described how accurate its predictions were. Cells could also move to explore their environment and some stochasticity was applied to movement.