4 papers
Self-Replicating Neural Cellular Automata: Quantifying Emergent Phenotypic and Genotypic Diversity in an OpenEnded Substrate
Sanyam Jain, Felix Simon Reimers, Stefano Nichele
We study an in-silico substrate in which every pixel of a two-channel cellular-automata grid carries a tiny neural network (an agent) that senses its Moore neighborhood. A cell per…
Repurposing Unified Topological Signatures for Graph Representation Learning
Sanyam Sanjay Jain, Anshika Krishnatray, Aditya Sharma +1
Message-passing Graph Neural Networks (GNNs) iteratively propagate and aggregate local neighborhood information followed by global readout to learn graph representations. However,…
Frequency-Histogram Coarse Graining in Elementary Cellular Automata and 2D CA
Sanyam Jain, Stefano Nichele
Cellular automata and other discrete dynamical systems have long been studied as models of emergent complexity. Recently, neural cellular automata have been proposed as models to i…
Emergent Dynamics in Heterogeneous Life-Like Cellular Automata
Aarati Shrestha, Felix Reimers, Sanyam Jain +4
The Game of Life (GoL), one well known 2D cellular automaton, does not typically ensure interesting long-term phenotypic dynamics. Therefore, while being Turing complete, GoL canno…