{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/reservoir-computing-using-non-uniform-binary","title":"Reservoir Computing Using Non-Uniform Binary Cellular Automata","arxiv_id":"1702.03812","date":"2017-02-13","proceeding":null,"authors":["Stefano Nichele","Magnus S. Gundersen"],"abstract":"The Reservoir Computing (RC) paradigm utilizes a dynamical system, i.e., a\nreservoir, and a linear classifier, i.e., a read-out layer, to process data\nfrom sequential classification tasks. In this paper the usage of Cellular\nAutomata (CA) as a reservoir is investigated. The use of CA in RC has been\nshowing promising results. In this paper, selected state-of-the-art experiments\nare reproduced. It is shown that some CA-rules perform better than others, and\nthe reservoir performance is improved by increasing the size of the CA\nreservoir itself. In addition, the usage of parallel loosely coupled\nCA-reservoirs, where each reservoir has a different CA-rule, is investigated.\nThe experiments performed on quasi-uniform CA reservoir provide valuable\ninsights in CA reservoir design. The results herein show that some rules do not\nwork well together, while other combinations work remarkably well. This\nsuggests that non-uniform CA could represent a powerful tool for novel CA\nreservoir implementations.","url_abs":"http://arxiv.org/abs/1702.03812v1","url_pdf":"http://arxiv.org/pdf/1702.03812v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"reservoir-computing-using-non-uniform-binary","repo_url":"https://github.com/magnusgundersen/spec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}