A continuous time dynamical Turing machine
dc.contributor.author | Postlethwaite, CM | |
dc.contributor.author | Ashwin, P | |
dc.contributor.author | Egbert, M | |
dc.date.accessioned | 2024-05-03T14:07:46Z | |
dc.date.issued | 2024-05-16 | |
dc.date.updated | 2024-05-03T09:01:41Z | |
dc.description.abstract | Continuous time recurrent neural networks (CTRNN) are systems of coupled ordinary differential equations inspired by the structure of neural networks in the brain. CTRNN are known to be universal dynamical approximators: given a large enough system, the parameters of a CTRNN can be tuned to produce output that is arbitrarily close to that of any other dynamical system. However, in practise, both designing systems of CTRNN to have a certain output, and the reverse—understanding the dynamics of a given system of CTRNN—can be non-trivial. In this paper, we describe a method for embedding any specified Turing machine in its entirety into a CTRNN. As such, we describe in detail a continuous-time dynamical system that performs arbitrary discrete-state computations. We suggest that in acting as both a continuous-time dynamical system and as a computer, the study of such systems can help refine and advance the debate concerning the Computational Hypothesis that cognition is a form of computation and the Dynamical Hypothesis that cognitive systems are dynamical systems. | en_GB |
dc.description.sponsorship | Royal Society Te Aparangi (Marsden Fund Council, NZ) Government) | en_GB |
dc.description.sponsorship | Engineering and Physical Sciences Research Council (EPSRC) | en_GB |
dc.identifier.citation | Published online 16 May 2024 | en_GB |
dc.identifier.doi | 10.1109/TNNLS.2024.3397995 | |
dc.identifier.grantnumber | 21-UOA048 | en_GB |
dc.identifier.grantnumber | EP/T018178/1 | en_GB |
dc.identifier.grantnumber | EP/T017856/1 | en_GB |
dc.identifier.uri | http://hdl.handle.net/10871/135861 | |
dc.identifier | ORCID: 0000-0001-7330-4951 (Ashwin, Peter) | |
dc.language.iso | en | en_GB |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_GB |
dc.relation.url | https://github.com/mathclaire/ctrnn_turingmachine | en_GB |
dc.rights | © 2024 IEEE. For the purpose of open access, the authors have applied a Creative Commons Attribution (CC BY) license to any Accepted Manuscript version arising. | |
dc.subject | CTRNN | en_GB |
dc.subject | Turing machine | en_GB |
dc.subject | network attractor | en_GB |
dc.title | A continuous time dynamical Turing machine | en_GB |
dc.type | Article | en_GB |
dc.date.available | 2024-05-03T14:07:46Z | |
dc.identifier.issn | 2162-237X | |
dc.description | This is the author accepted manuscript. The final version is available from IEEE via the DOI in this record | en_GB |
dc.description | Code availability: The Matlab code used to implement the system described in this paper is available at https://github.com/mathclaire/ctrnn_turingmachine | en_GB |
dc.identifier.eissn | 2162-2388 | |
dc.identifier.journal | IEEE Transactions on Neural Networks and Learning Systems | en_GB |
dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | en_GB |
dcterms.dateAccepted | 2024-05-03 | |
dcterms.dateSubmitted | 2023-03-31 | |
rioxxterms.version | AM | en_GB |
rioxxterms.licenseref.startdate | 2024-05-03 | |
rioxxterms.type | Journal Article/Review | en_GB |
refterms.dateFCD | 2024-05-03T09:01:45Z | |
refterms.versionFCD | AM | |
refterms.dateFOA | 2024-06-13T09:03:50Z | |
refterms.panel | B | en_GB |
exeter.rights-retention-statement | Yes |
Files in this item
This item appears in the following Collection(s)
Except where otherwise noted, this item's licence is described as © 2024 IEEE. For the purpose of open access, the authors have applied a Creative Commons Attribution (CC BY) license to any Accepted Manuscript version arising.