%0 Journal Article %1 glover2024sensitivity %A Glover, Tom Eivind %A Jahren, Ruben %A Martinuzzi, Francesco %A Lind, Pedro Gonçalves %A Nichele, Stefano %D 2024 %J arXiv e-prints %K imported topic_earthenvironment %P arXiv: 2407.18017 %T A Sensitivity Analysis of Cellular Automata and Heterogeneous Topology Networks: Partially-Local Cellular Automata and Homogeneous Homogeneous Random Boolean Networks %X Elementary Cellular Automata (ECA) are a well-studied computational universe that is, despite its simple configurations, capable of impressive computational variety. Harvesting this computation in a useful way has historically shown itself to be difficult, but if combined with reservoir computing (RC), this becomes much more feasible. Furthermore, RC and ECA enable energy-efficient AI, making the combination a promising concept for Edge AI. In this work, we contrast ECA to substrates of Partially-Local CA (PLCA) and Homogeneous Homogeneous Random Boolean Networks (HHRBN). They are, in comparison, the topological heterogeneous counterparts of ECA. This represents a step from ECA towards more biological-plausible substrates. We analyse these substrates by testing on an RC benchmark (5-bit memory), using Temporal Derrida plots to estimate the sensitivity and assess the defect collapse rate. We …

@article{glover2024sensitivity, abstract = {Elementary Cellular Automata (ECA) are a well-studied computational universe that is, despite its simple configurations, capable of impressive computational variety. Harvesting this computation in a useful way has historically shown itself to be difficult, but if combined with reservoir computing (RC), this becomes much more feasible. Furthermore, RC and ECA enable energy-efficient AI, making the combination a promising concept for Edge AI. In this work, we contrast ECA to substrates of Partially-Local CA (PLCA) and Homogeneous Homogeneous Random Boolean Networks (HHRBN). They are, in comparison, the topological heterogeneous counterparts of ECA. This represents a step from ECA towards more biological-plausible substrates. We analyse these substrates by testing on an RC benchmark (5-bit memory), using Temporal Derrida plots to estimate the sensitivity and assess the defect collapse rate. We …}, added-at = {2024-11-29T11:53:34.000+0100}, author = {Glover, Tom Eivind and Jahren, Ruben and Martinuzzi, Francesco and Lind, Pedro Gonçalves and Nichele, Stefano}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/2522e53e62663eb2b12c8f718a5b02963/joum576e}, citation = {arXiv e-prints, arXiv: 2407.18017, 2024}, interhash = {399a75686cf06d1bd302095249d3256c}, intrahash = {522e53e62663eb2b12c8f718a5b02963}, journal = {arXiv e-prints}, keywords = {imported topic_earthenvironment}, pages = {arXiv: 2407.18017}, timestamp = {2024-11-29T11:53:34.000+0100}, title = {A Sensitivity Analysis of Cellular Automata and Heterogeneous Topology Networks: Partially-Local Cellular Automata and Homogeneous Homogeneous Random Boolean Networks}, year = 2024 }