Mimicking Cellular Automata with Machine Learning part6
- Modelling reliability of reversible circuits with 2D second-order cellular automata(arXiv)
Author : Alexander Yu. Vlasov
Abstract : The cellular automaton is a widely known model of both reversible and irreversible computations. The family of reversible second-order cellular automata considered in this work is appropriate both for construction of logic gates and analysis of damage distribution. The quantities such as formal dimension of damage patterns can be used only for rough estimation of consequences of particular faults and numerical experiments are provided for illustration of some subtleties. Such analysis demonstrates high sensitivity to errors from defects, lack of synchronization and too short intervals between signals
2. Exploring Multiple Neighborhood Neural Cellular Automata (MNNCA) for Enhanced Texture Learning(arXiv)
Author : Magnus Petersen
Abstract : Cellular Automata (CA) have long been foundational in simulating dynamical systems computationally. With recent innovations, this model class has been brought into the realm of deep learning by parameterizing the CA’s update rule using an artificial neural network, termed Neural Cellular Automata (NCA). This allows NCAs to be trained via gradient descent, enabling them to evolve into specific shapes, generate textures, and mimic behaviors such as swarming. However, a limitation of traditional NCAs is their inability to exhibit sufficiently complex behaviors, restricting their potential in creative and modeling tasks. Our research explores enhancing the NCA framework by incorporating multiple neighborhoods and introducing structured noise for seed states. This approach is inspired by techniques that have historically amplified the expressiveness of classical continuous CA. All code and example videos are publicly available on https://github.com/MagnusPetersen/MNNCA
