journal article·2022-03-01Open access

Role of delay-times in delay-based photonic reservoir computing [Invited]

Tobias Hülser, Felix Köster, Lina Jaurigue, Kathy Lüdge

Optical Materials Express· Volume 12· Issue 3

Abstract

Delay-based reservoir computing has gained a lot of attention due to the relative simplicity with which this concept can be implemented in hardware. However, unnecessary constraints are commonly placed on the relationship between the delay-time and the input clock-cycle, which can have a detrimental effect on the performance. We review the existing literature on this subject and introduce the concept of delay-based reservoir computing in a manner that demonstrates that no predefined relationship between the delay-time and the input clock-cycle is required for this computing concept to work. Choosing the delay-times independent of the input clock-cycle, one gains an important degree of freedom. Consequently, we discuss ways to improve the computing performance of a reservoir formed by delay-coupled oscillators and show the impact of delay-time tuning in such systems.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Neural Networks and Reservoir Computing · Optical Network Technologies · Advanced Memory and Neural Computing

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Technische Universität Berlin

Technische Universität Ilmenau

Funding

Deutsche Forschungsgemeinschaft

References (62)

Show source-provided references
1. Maass · Neural Comput. · 2002 · 14 · 253110.1162/089976602760407955 ↗
2. Hochreiter · Int. J. Unc. Fuzz. Knowl. Based Syst. · 1998 · 06 · 10710.1142/S0218488598000094 ↗
3. Dockendorf · BioSystems · 2009 · 95 · 9010.1016/j.biosystems.2008.08.001 ↗
4. Antonik · IEEE Trans. Neural Netw. Learn. Syst. · 2017 · 28 · 268610.1109/TNNLS.2016.2598655 ↗
5. Vandoorne · Nat. Commun. · 2014 · 5 · 354110.1038/ncomms4541 ↗
6. Sackesyn · Opt. Express · 2021 · 29 · 3099110.1364/OE.435013 ↗
7. Appeltant · Nat. Commun. · 2011 · 2 · 46810.1038/ncomms1476 ↗
8. Larger · Opt. Express · 2012 · 20 · 324110.1364/OE.20.003241 ↗
9. Paquot · Sci. Rep. · 2012 · 2 · 28710.1038/srep00287 ↗
10. Chen · Opt. Express · 2019 · 27 · 2743110.1364/OE.27.027431 ↗
11. Duport · Sci. Rep. · 2016 · 6 · 2238110.1038/srep22381 ↗
12. Brunner · Nat. Commun. · 2013 · 4 · 136410.1038/ncomms2368 ↗
13. Dejonckheere · Opt. Express · 2014 · 22 · 1086810.1364/OE.22.010868 ↗
14. Vinckier · Optica · 2015 · 2 · 43810.1364/OPTICA.2.000438 ↗
15. Hou · Opt. Express · 2018 · 26 · 1021110.1364/OE.26.010211 ↗
16. Takano · Opt. Express · 2018 · 26 · 2942410.1364/OE.26.029424 ↗
17. Nakajima · Commun. Phys. · 2021 · 4 · 2010.1038/s42005-021-00519-1 ↗
18. Harkhoe · Opt. Express · 2020 · 28 · 308610.1364/OE.382556 ↗
19. Duport · Opt. Express · 2012 · 20 · 2278310.1364/OE.20.022783 ↗
20. Dion · J. Appl. Phys. · 2018 · 124 · 15213210.1063/1.5038038 ↗
21. Bueno · Opt. Express · 2017 · 25 · 240110.1364/OE.25.002401 ↗
22. Kuriki · Opt. Express · 2018 · 26 · 577710.1364/OE.26.005777 ↗
23. Nguimdo · Opt. Express · 2014 · 22 · 867210.1364/OE.22.008672 ↗
24. Larger · Phys. Rev. X · 2017 · 7 · 01101510.1103/PhysRevX.7.011015 ↗
25. Argyris · IEEE J. Sel. Top. Quantum Electron. · 2020 · 26 · 110.1109/JSTQE.2019.2936947 ↗
26. Sorokina · Opt. Express · 2019 · 27 · 238710.1364/OE.27.002387 ↗
27. Ortín · Cognitive Comput. · 2017 · 9 · 32710.1007/s12559-017-9463-7 ↗
28. Sugano · IEEE J. Sel. Top. Quantum Electron. · 2020 · 26 · 110.1109/JSTQE.2019.2929179 ↗
29. Lukosevicius · Comput. Sci. Rev. · 2009 · 3 · 12710.1016/j.cosrev.2009.03.005 ↗
30. Van der Sande · Nanophotonics · 2017 · 6 · 56110.1515/nanoph-2016-0132 ↗
31. Brunner · J. Appl. Phys. · 2018 · 124 · 15200410.1063/1.5042342 ↗
32. Tanaka · Neural Netw. · 2019 · 115 · 10010.1016/j.neunet.2019.03.005 ↗
33. Botchkarev · Interdiscip. J. Inf. Knowl. Manag. · 2019 · 14 · 04510.28945/4184 ↗
34. Flach · AAAI-19 Proc. · 2019 · 33 · 980810.1609/aaai.v33i01.33019808 ↗
35. Carroll · Chaos · 2020 · 30 · 12110910.1063/5.0038163 ↗
36. Appeltant · Sci. Rep. · 2015 · 4 · 362910.1038/srep03629 ↗
37. Soriano · Opt. Express · 2013 · 21 · 1210.1364/OE.21.000012 ↗
38. Argyris · Sci. Rep. · 2021 · 11 · 670110.1038/s41598-021-86150-0 ↗
39. Yue · Opt. Express · 2019 · 27 · 1993110.1364/OE.27.019931 ↗
40. Toutounji · Neural Comput. · 2015 · 27 · 115910.1162/NECO_a_00737 ↗
41. Röhm · IEEE J. Sel. Top. Quantum Electron. · 2020 · 26 · 110.1109/JSTQE.2019.2927578 ↗
42. Stelzer · Neural Netw. · 2020 · 124 · 15810.1016/j.neunet.2020.01.010 ↗
43. Hale · 1993
44. Arecchi · Phys. Rev. A · 1992 · 45 · R422510.1103/PhysRevA.45.R4225 ↗
45. Köster · JPhys Photonics · 2021 · 3 · 02401110.1088/2515-7647/abf237 ↗
46. Panchuk · Int. J. Bifurc. Chaos · 2013 · 23 · 133003910.1142/S0218127413300395 ↗
47. Calleja · SIAM J. Appl. Dyn. Syst. · 2017 · 16 · 147410.1137/16M1087655 ↗
48. Jaurigue · Phys. Rev. Lett. · 2016 · 117 · 15410110.1103/PhysRevLett.117.154101 ↗
49. Proskurkin · Russ. J. Phys. Chem. · 2015 · 89 · 33110.1134/S0036024415020223 ↗
50. Nieters · IBM J. Res. Dev. · 2017 · 61 · 710.1147/JRD.2017.2664698 ↗
51. Ortín · Front. Phys. · 2019 · 7 · 21010.3389/fphy.2019.00210 ↗
52. Jaurigue · Entropy · 2021 · 23 · 156010.3390/e23121560 ↗
53. Martinenghi · Phys. Rev. Lett. · 2012 · 108 · 24410110.1103/PhysRevLett.108.244101 ↗
54. Röhm · J. Phys. Commun. · 2018 · 2 · 08500710.1088/2399-6528/aad56d ↗
55. Guo · Opt. Express · 2019 · 27 · 2329310.1364/OE.27.023293 ↗
56. Hou · Opt. Commun. · 2019 · 433 · 21510.1016/j.optcom.2018.10.014 ↗
57. Liang · Opt. Commun. · 2021 · 495 · 12712010.1016/j.optcom.2021.127120 ↗
58. Yue · IEEE Photonics J. · 2021 · 13 · 110.1109/JPHOT.2021.3075055 ↗
59. Sanderson · JOSS · 2016 · 1 · 2610.21105/joss.00026 ↗
60. Bishop · Neural Comput. · 1995 · 7 · 10810.1162/neco.1995.7.1.108 ↗
61. Perlikowski · Phys. Rev. E · 2010 · 82 · 03620810.1103/PhysRevE.82.036208 ↗
62. Goldmann · Chaos · 2020 · 30 · 09312410.1063/5.0017974 ↗