journal article·2023-10-25

Bi2O2Se-Based Bimode Noise Generator for the Application of Generative Adversarial Networks

Bo Liu, XingYi Zheng, Dharmendra Verma, Yudi Zhao, Hanyuan Liang, Lain-Jong Li, Jenhui Chen, Chao-Sung Lai

ACS Applied Materials & Interfaces· Volume 15· Issue 42
Publisher page

Abstract

In the emerging technology, the generative aversive networks (GANs), randomness, and unpredictability of inputting noises are the keys to the uniqueness, diversity, robustness, and security of the generated images. Compared with deterministic software-based noise generation, hardware-based noise generation introduces physical entropy sources, such as electronic and photonic noises, to add unpredictability. In this study, bimode Bi 2 O 2 Se-based noise generators have been demonstrated for the application of GANs. Harnessing its ultrahigh carrier mobility, excellent air stability, marvelous optoelectronic performance, as well as the unique surface resistive switching effect and defect locations in the energy diagram, Bi 2 O 2 Se provides a good material platform to easily integrate with multiple device architectures for generating noises in different physical sources. The noise of the black current mode in a photodetector architecture and the random telegraph noise in a memristor mode were measured, characterized, compared, and analyzed. A method of Markov chain equipped with K-means clustering was carried out to calculate the discrete noise states and the transition probability matrix between them. To evaluate the generated properties of the GANs based on the hardware noise source, the inception score and Fréchet inception distance were evaluated.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Advanced Memory and Neural Computing · Ferroelectric and Negative Capacitance Devices · Neural dynamics and brain function

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

Affiliations

Faculty of Information Technology, College of Microelectronics, Beijing University of Technology, Beijing 100124, People’s Republic of China

Department of Computer Science and Information Engineering, Chang Gung University, Guishan Dist., Taoyuan City 33302, Taiwan

Department of Electronic Engineering, Chang Gung University, Guishan Dist., Taoyuan 33302, Taiwan

School of Information and Communication Engineering, Beijing Information Science & Technology University, Beijing 100101, China

School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, Pennsylvania 16801, United States

Department of Mechanical Engineering, The University of Hong Kong, Pokfulam Road, Kowloon, Hong Kong 999077, China

Artificial Intelligence and Green Technology Research Center, Chang Gung University, Guishan Dist., Taoyuan 33302,Taiwan

Department of Nephrology, Chang Gung Memorial Hospital, Guishan Dist., Linkou 33305, Taiwan

Department of Materials Engineering, Ming Chi University of Technology, Taishan Dist., New Taipei City 24301, Taiwan

Funding

National Natural Science Foundation of China · Ministry of Science and Technology, Taiwan · Chang Gung Memorial Hospital

References (48)

Show source-provided references
1. 10.1021/acsaelm.1c0134910.1021/acsaelm.1c01349 ↗
2. 10.1002/adfm.20180380710.1002/adfm.201803807 ↗
3. 10.1021/acs.nanolett.0c0485810.1021/acs.nanolett.0c04858 ↗
4. 10.1002/adma.20150009910.1002/adma.201500099 ↗
5. 10.1038/s41467-023-36313-610.1038/s41467-023-36313-6 ↗
6. 10.1002/adfm.20170486210.1002/adfm.201704862 ↗
7. 10.1038/s41586-023-05759-510.1038/s41586-023-05759-5 ↗
8. 10.1143/jjap.50.06ge0310.1143/jjap.50.06ge03 ↗
9. 10.1002/pssc.20100057310.1002/pssc.201000573 ↗
10. 10.1038/s41467-020-18195-010.1038/s41467-020-18195-0 ↗
11. 10.1021/acsnano.1c0598410.1021/acsnano.1c05984 ↗
12. 10.1002/adma.20210018510.1002/adma.202100185 ↗
13. 10.1021/acsnano.2c0178410.1021/acsnano.2c01784 ↗
14. 10.1109/LED.2018.286907210.1109/LED.2018.2869072 ↗
15. 10.1088/2634-4386/ac6d0510.1088/2634-4386/ac6d05 ↗
16. 10.1109/LED.2020.302159310.1109/LED.2020.3021593 ↗
17. 10.1038/s41928-020-0436-610.1038/s41928-020-0436-6 ↗
18. 10.1016/j.jjimei.2020.10000410.1016/j.jjimei.2020.100004 ↗
19. 10.1016/j.media.2019.10155210.1016/j.media.2019.101552 ↗
20. 10.1145/342262210.1145/3422622 ↗
21. Creswell A. · IEEE Signal Process. Magzine · 2019 · 40 · 74
22. 10.1109/JAS.2017.751058310.1109/JAS.2017.7510583 ↗
23. 10.1038/nphoton.2008.22710.1038/nphoton.2008.227 ↗
24. 10.1007/s12274-020-2945-z10.1007/s12274-020-2945-z ↗
25. 10.1016/j.matt.2022.11.00510.1016/j.matt.2022.11.005 ↗
26. 10.1021/accountsmr.1c0013010.1021/accountsmr.1c00130 ↗
27. 10.1002/adfm.20210579510.1002/adfm.202105795 ↗
28. 10.1002/adfm.20200159810.1002/adfm.202001598 ↗
29. 10.1021/acsami.1c0017710.1021/acsami.1c00177 ↗
30. 10.1039/D0QM00152J10.1039/D0QM00152J ↗
31. 10.1021/acsnano.0c0907810.1021/acsnano.0c09078 ↗
32. 10.1021/acsami.5b0660610.1021/acsami.5b06606 ↗
33. 10.1002/adfm.20160388610.1002/adfm.201603886 ↗
34. 10.1116/1.505938410.1116/1.5059384 ↗
35. 10.1002/adma.20180494510.1002/adma.201804945 ↗
36. 10.1063/1.509419210.1063/1.5094192 ↗
37. 10.1002/adfm.20170643710.1002/adfm.201706437 ↗
38. 10.1021/acsaelm.2c0153310.1021/acsaelm.2c01533 ↗
39. 10.1021/acsami.8b0468510.1021/acsami.8b04685 ↗
40. 10.1021/acsnano.8b0026810.1021/acsnano.8b00268 ↗
41. 10.1063/5.013724510.1063/5.0137245 ↗
42. 10.1038/s41467-020-16640-810.1038/s41467-020-16640-8 ↗
43. Degraeve, R.; Cho, M.; Govoreanu, B.; Kaczer, B.; Zahid, M. B.; Van Houdt, J.; Jurczak, M.; Groeseneken, G. Trap Spectroscopy by Charge Injection and Sensing (TSCIS): A Quantitative Electrical Technique for Studying Defects in Dielectric Stacks. 2008 IEEE International Electron Devices Meeting, 2008; pp 10–13.10.1109/IEDM.2008.4796812 ↗
44. 10.1016/j.chip.2023.10004010.1016/j.chip.2023.100040 ↗
45. Heusel, M.; Ramsauer, H.; Unterthiner, T.; Nessler, B.; Hochreiter, S. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. Conference on Neural Information Processing Systems, 2017; pp 6627–6638.
46. Salimans, T.; Goodfellow, I.; Zaremba, W.; Cheung, V.; Radford, A.; Chen, X. Improved Techniques for Training GANs. Conference on Neural Information Processing Systems, 2016; pp 2234–2242.
47. 10.1038/s42256-023-00680-y10.1038/s42256-023-00680-y ↗
48. 10.1002/admt.20190042210.1002/admt.201900422 ↗