Giovanni E. PazienzaE. Gómez-Ramı́rez2026-03-222026-03-22200910.1109/ijcnn.2009.5178977https://doi.org/10.1109/ijcnn.2009.5178977https://andeanlibrary.org/handle/123456789/50733Citaciones: 5In this paper we show how polynomial cellular neural networks can be used to find new properties of two-dimensional binary cellular automata (CA). In particular, we define formally a complexity index for totalistic and semi-totalistic CA, and we discuss on the intrinsic complexity of universal CA finding a surprising result: universal rules are slightly more complex than linearly separable ones.enCellular automatonSeparable spacePolynomialBinary numberComputer scienceCellular neural networkMathematicsAutomatonArtificial neural networkTheoretical computer sciencearticle