Symbolic Computation Using Cellular Automata-Based Hyperdimensional Computing
| dc.contributor.author | Yilmaz, Ozgur | |
| dc.date.accessioned | 2025-10-24T18:09:29Z | |
| dc.date.available | 2025-10-24T18:09:29Z | |
| dc.date.issued | 2015 | |
| dc.department | Malatya Turgut Özal Üniversitesi | |
| dc.description.abstract | This letter introduces a novel framework of reservoir computing that is capable of both connectionist machine intelligence and symbolic computation. A cellular automaton is used as the reservoir of dynamical systems. Input is randomly projected onto the initial conditions of automaton cells, and nonlinear computation is performed on the input via application of a rule in the automaton for a period of time. The evolution of the automaton creates a space-time volume of the automaton state space, and it is used as the reservoir. The proposed framework is shown to be capable of long-term memory, and it requires orders of magnitude less computation compared to echo state networks. As the focus of the letter, we suggest that binary reservoir feature vectors can be combined using Boolean operations as in hyperdimensional computing, paving a direct way for concept building and symbolic processing. To demonstrate the capability of the proposed system, we make analogies directly on image data by asking, What is the automobile of air? | |
| dc.description.sponsorship | Scientific and Technological Research Council of Turkey (TUBITAK) [114E554]; Turgut Ozal University BAP Grant [006-10-2013] | |
| dc.description.sponsorship | This research is supported by the Scientific and Technological Research Council of Turkey (TUBITAK) Career Grant 114E554 and Turgut Ozal University BAP Grant 006-10-2013. I thank Lenovo Group Ltd. Turkey Division, specifically Cagdas Ekinci and Alpay Erturkmen, for their support in this research. | |
| dc.identifier.doi | 10.1162/NECO_a_00787 | |
| dc.identifier.endpage | 2692 | |
| dc.identifier.issn | 0899-7667 | |
| dc.identifier.issn | 1530-888X | |
| dc.identifier.issue | 12 | |
| dc.identifier.pmid | 26496041 | |
| dc.identifier.scopus | 2-s2.0-84948971804 | |
| dc.identifier.scopusquality | Q1 | |
| dc.identifier.startpage | 2661 | |
| dc.identifier.uri | https://doi.org/10.1162/NECO_a_00787 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12899/3671 | |
| dc.identifier.volume | 27 | |
| dc.identifier.wos | WOS:000365674700006 | |
| dc.identifier.wosquality | Q2 | |
| dc.indekslendigikaynak | Web of Science | |
| dc.indekslendigikaynak | Scopus | |
| dc.indekslendigikaynak | PubMed | |
| dc.language.iso | en | |
| dc.publisher | Mit Press | |
| dc.relation.ispartof | Neural Computation | |
| dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | |
| dc.rights | info:eu-repo/semantics/closedAccess | |
| dc.snmz | KA_20251023 | |
| dc.subject | Systems; Architectures; Networks; Chaos; Edge | |
| dc.title | Symbolic Computation Using Cellular Automata-Based Hyperdimensional Computing | |
| dc.type | Article |












