Reservoir Computing with a Single Time-delay Autonomous Boolean Node
Overview
Physiology
Public Health
Affiliations
We demonstrate reservoir computing with a physical system using a single autonomous Boolean logic element with time-delay feedback. The system generates a chaotic transient with a window of consistency lasting between 30 and 300 ns, which we show is sufficient for reservoir computing. We then characterize the dependence of computational performance on system parameters to find the best operating point of the reservoir. When the best parameters are chosen, the reservoir is able to classify short input patterns with performance that decreases over time. In particular, we show that four distinct input patterns can be classified for 70 ns, even though the inputs are only provided to the reservoir for 7.5 ns.
Reservoir-computing based associative memory and itinerancy for complex dynamical attractors.
Kong L, Brewer G, Lai Y Nat Commun. 2024; 15(1):4840.
PMID: 38844437 PMC: 11156990. DOI: 10.1038/s41467-024-49190-4.
Liao Z, Yamahara H, Terao K, Ma K, Seki M, Tabata H Sci Rep. 2023; 13(1):5260.
PMID: 37002272 PMC: 10066395. DOI: 10.1038/s41598-023-32084-8.
Time series reconstructing using calibrated reservoir computing.
Chen Y, Qian Y, Cui X Sci Rep. 2022; 12(1):16318.
PMID: 36175460 PMC: 9522934. DOI: 10.1038/s41598-022-20331-3.
A Hopf physical reservoir computer.
Shougat M, Li X, Mollik T, Perkins E Sci Rep. 2021; 11(1):19465.
PMID: 34593935 PMC: 8484469. DOI: 10.1038/s41598-021-98982-x.
Stelzer F, Rohm A, Vicente R, Fischer I, Yanchuk S Nat Commun. 2021; 12(1):5164.
PMID: 34453053 PMC: 8397757. DOI: 10.1038/s41467-021-25427-4.