Inverse Design of a Graphene-Based Quantum Transducer via Neuroevolution
Source abstract
Abstract
We introduce an inverse design framework based on artificial neural networks, genetic algorithms, and tight-binding calculations, capable to optimize the very large configuration space of nanoelectronic devices. Our non-linear optimization procedure operates on trial Hamiltonians through superoperators controlling growth policies of regions of distinct doping. We demonstrate that our algorithm optimizes the doping of graphene-based three-terminal devices for valleytronics applications, monotonously converging to synthesizable devices with high merit functions in a few thousand evaluations (out of ≃2 3800 possible configurations). The best-performing device allowed for a terminal-specific separation of valley currents with ≃96% (≃94%) K ( K ′) valley purity. Importantly, the devices found through our non-linear optimization procedure have both a higher merit function and higher robustness to defects than the ones obtained through geometry optimization.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Graphene research and applications · 2D Materials and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Physics, University of Ottawa, Ottawa, ON K1N 6N5, Canada
Vector Institute for Artificial Intelligence, Toronto, OM M5G 1M1, Canada
Center for Nanoscale Materials, Argonne National Laboratory, Lemont, Illinois 60439, United States
Northwestern Argonne Institute of Science and Engineering, Evanston, Illinois 60208, United States
National Research Council of Canada, Ottawa, ON K1N 5A2, Canada
Funding
Natural Sciences and Engineering Research Council of Canada · Argonne National Laboratory
References (48)
Show source-provided references
1. 10.1146/annurev-conmatphys-070909-10412310.1146/annurev-conmatphys-070909-104123 ↗
2. 10.1038/natrevmats.2016.5510.1038/natrevmats.2016.55 ↗
3. 10.1038/nnano.2012.9610.1038/nnano.2012.96 ↗
4. 10.1038/nnano.2012.9510.1038/nnano.2012.95 ↗
5. 10.1038/ncomms188210.1038/ncomms1882 ↗
6. 10.1126/science.125014010.1126/science.1250140 ↗
7. 10.1103/RevModPhys.81.10910.1103/RevModPhys.81.109 ↗
8. 10.1038/nphys54710.1038/nphys547 ↗
9. 10.1103/PhysRevLett.99.23680910.1103/PhysRevLett.99.236809 ↗
10. 10.1088/2053-1583/aaea8d10.1088/2053-1583/aaea8d ↗
11. 10.1021/acs.nanolett.7b0166310.1021/acs.nanolett.7b01663 ↗
12. 10.1126/science.119170010.1126/science.1191700 ↗
13. 10.1103/PhysRevB.77.20542110.1103/PhysRevB.77.205421 ↗
14. 10.1103/PhysRevB.93.03545610.1103/PhysRevB.93.035456 ↗
15. 10.1103/PhysRevLett.117.27680110.1103/PhysRevLett.117.276801 ↗
16. 10.1103/PhysRevB.98.16543710.1103/PhysRevB.98.165437 ↗
17. 10.1088/1367-2630/18/5/05301610.1088/1367-2630/18/5/053016 ↗
18. 10.1021/acs.nanolett.7b0316710.1021/acs.nanolett.7b03167 ↗
19. 10.1103/PhysRevB.99.03541110.1103/PhysRevB.99.035411 ↗
20. 10.7566/JPSJNC.16.1310.7566/JPSJNC.16.13 ↗
21. 10.1103/PhysRevApplied.11.05401910.1103/PhysRevApplied.11.054019 ↗
22. 10.1063/1.347372510.1063/1.3473725 ↗
23. 10.1103/PhysRevLett.106.13680610.1103/PhysRevLett.106.136806 ↗
24. 10.1103/PhysRevB.89.12140710.1103/PhysRevB.89.121407 ↗
25. 10.1126/science.113802010.1126/science.1138020 ↗
26. 10.1103/PhysRevApplied.11.04403310.1103/PhysRevApplied.11.044033 ↗
27. 10.1103/PhysRevLett.100.23680110.1103/PhysRevLett.100.236801 ↗
28. Aktor T. · arXiv preprint arXiv:1910.00489 · 2019
29. 10.1002/adma.20070168110.1002/adma.200701681 ↗
30. 10.1088/1367-2630/16/6/06306510.1088/1367-2630/16/6/063065 ↗
31. 10.1109/TNANO.2011.216616410.1109/TNANO.2011.2166164 ↗
32. 10.1038/nature2427010.1038/nature24270 ↗
33. 10.1038/nphoton.2015.6910.1038/nphoton.2015.69 ↗
34. 10.1021/acsphotonics.7b0098710.1021/acsphotonics.7b00987 ↗
35. 10.1002/cem.65110.1002/cem.651 ↗
36. 10.1103/PhysRevB.100.20541110.1103/PhysRevB.100.205411 ↗
37. 10.1038/s41467-019-12698-110.1038/s41467-019-12698-1 ↗
38. 10.1080/0022250X.1971.998979410.1080/0022250X.1971.9989794 ↗
39. 10.1103/RevModPhys.55.60110.1103/RevModPhys.55.601 ↗
40. Supplemental Information. 2020.
41. 10.1142/S021797920201491710.1142/S0217979202014917 ↗
42. Duvenaud, D. K.; Maclaurin, D.; Iparraguirre, J.; Bombarell, R.; Hirzel, T.; Aspuru-Guzik, A.; Adams, R. P. In Advances in Neural Information Processing Systems 28; Cortes, C., Lawrence, N. D., Lee, D. D., Sugiyama, M., Garnett, R., Eds. Curran Associates, Inc., 2015; pp. 2224–2232.
43. Kipf T. N. · arXiv preprint arXiv:1609.02907 · 2016
44. Beeler C. · arXiv preprint arXiv:1903.08543 · 2019
45. Such F. P. · arXiv preprint arXiv:1712.06567 · 2017
46. 10.7717/peerj.45310.7717/peerj.453 ↗
47. 10.1103/PhysRevLett.98.14640110.1103/PhysRevLett.98.146401 ↗
48. 10.1063/1.501977910.1063/1.5019779 ↗