Highly Reliable Bi2O2Se Dendritic Neuron Enabling Spatial-Temporal Signal Processing for Real-World Image Classification
Source abstract
Abstract
Artificial intelligence (AI) has made significant strides by imitating biological neurons and synapses through simplified models, yet incomplete neuron functionalities can limit performance and energy efficiency in handling complex tasks. Biological neurons process input signals nonlinearly, utilizing dendrites to process spatial-temporal information. This study demonstrates the compact artificial dendrite device employing memristors based on bismuth oxyselenide (Bi 2 O 2 Se). Transfer-free Bi 2 O 2 Se switching medium is directly grown on the metal-patterned substrates via 350 °C selenization process. The layered Bi 2 O 2 Se structure, limiting metal injection, results in reliable dynamic resistive switching with excellent cycle uniformity and exceptional endurance over 2 million cycles. The highly reliable current response of dynamic resistive switching is modeled with respect to the spatial-temporal voltage input. With the Bi 2 O 2 Se dendrite device, dendritic neuron model is implemented, and the proposed neural network achieved high recognition rates of 78.3% with the street view house numbers (SVHN) data set.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced Memory and Neural Computing · Ferroelectric and Negative Capacitance Devices · Neuroscience and Neural Engineering
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea
Department of Materials Science and Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea
Graduate School of Semiconductor Technology, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea
Funding
Ministry of Science and ICT, South Korea · National Research Foundation of Korea
References (40)
Show source-provided references
1. 10.1109/MSP.2012.220559710.1109/MSP.2012.2205597 ↗
2. 10.1002/rob.2027610.1002/rob.20276 ↗
3. Brown, T.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J. D.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A. In Language Models are Few-Shot Learners, Advances in Neural Information Processing Systems 33; NIPS, 2020; pp 1877–1901.
4. Team, G.; Anil, R.; Borgeaud, S.; Wu, Y.; Alayrac, J.B.; Yu, J.; Soricut, R.; Schalkwyk, J.; Dai, A. M.; Hauth, A. Gemini: A Family of Highly Capable Multimodal Models. 2023, arXiv:2312.11805. arXiv.org e-Printarchive. https://arxiv.org/abs/2312.11805.
5. Touvron, H.; Martin, L.; Stone, K.; Albert, P.; Almahairi, A.; Babaei, Y.; Bashlykov, N.; Batra, S.; Bhargava, P.; Bhosale, S. Llama 2: Open Foundation and Fine-Tuned Chat Models. 2023, arXiv:2307.09288. arXiv.org e-Printarchive. https://arxiv.org/abs/2307.09288.
6. 10.1016/j.lindif.2023.10227410.1016/j.lindif.2023.102274 ↗
7. Bender, E. M.; Gebru, T.; McMillan-Major, A.; Shmitchell, S. In On the Dangers of Stochastic Parrots: Can. Language Models Be Too Big?, Proceedings of the 2021 ACM conference on fairness, accountability, and transparency; 2021; pp 610–623.10.1145/3442188.3445922 ↗
8. 10.1126/science.121036210.1126/science.1210362 ↗
9. 10.1038/nn.385110.1038/nn.3851 ↗
10. 10.1038/s41467-023-44614-z10.1038/s41467-023-44614-z ↗
11. 10.1038/s41467-022-35747-810.1038/s41467-022-35747-8 ↗
12. 10.1038/s41583-020-0301-710.1038/s41583-020-0301-7 ↗
13. Schemmel, J.; Kriener, L.; Müller, P.; Meier, K. In An Accelerated Analog Neuromorphic Hardware System Emulating NMDA-and Calcium-Based Non-Linear Dendrites, 2017 International Joint Conference on Neural Networks (IJCNN); IEEE, 2017; pp 2217–2226.10.1109/IJCNN.2017.7966124 ↗
14. 10.1162/neco_a_0104510.1162/neco_a_01045 ↗
15. 10.1002/adma.20220368410.1002/adma.202203684 ↗
16. 10.1038/s41565-020-0722-510.1038/s41565-020-0722-5 ↗
17. 10.1038/nmat475610.1038/nmat4756 ↗
18. 10.1038/s41467-020-17215-310.1038/s41467-020-17215-3 ↗
19. 10.1038/s41467-022-29727-110.1038/s41467-022-29727-1 ↗
20. 10.1002/adma.20230733410.1002/adma.202307334 ↗
21. 10.1002/adfm.20230905810.1002/adfm.202309058 ↗
22. Shi, Y.; Pan, C.; Chen, V.; Raghavan, N.; Pey, K.; Puglisi, F.; Pop, E.; Wong, H.S.; Lanza, M. In Coexistence of Volatile and Non-Volatile Resistive Switching in 2D h-BN Based Electronic Synapses, 2017 International Electron Devices Meeting (IEDM); IEEE, 2017; pp 5.4. 1–5.4. 4.10.1109/IEDM.2017.8268333 ↗
23. 10.1002/smll.20230022310.1002/smll.202300223 ↗
24. 10.1038/s41928-021-00573-110.1038/s41928-021-00573-1 ↗
25. 10.1038/s41563-023-01704-z10.1038/s41563-023-01704-z ↗
26. 10.1038/s41586-023-05973-110.1038/s41586-023-05973-1 ↗
27. 10.1002/adma.20210365610.1002/adma.202103656 ↗
28. 10.1002/aisy.20220033810.1002/aisy.202200338 ↗
29. Wu, X.; Liu, X.; Li, W.; Wu, Q. In Improved Expressivity through Dendritic Neural Networks, Advances in Neural Information Processing Systems 31; NIPS, 2018.
30. 10.1038/s41928-018-0118-910.1038/s41928-018-0118-9 ↗
31. 10.1021/jp507826j10.1021/jp507826j ↗
32. 10.1103/PhysRevB.75.09410410.1103/PhysRevB.75.094104 ↗
33. 10.1016/j.mser.2014.06.00210.1016/j.mser.2014.06.002 ↗
34. 10.1038/s41467-018-07979-010.1038/s41467-018-07979-0 ↗
35. 10.1109/LED.2018.286845910.1109/LED.2018.2868459 ↗
36. 10.1038/s41928-024-01133-z10.1038/s41928-024-01133-z ↗
37. 10.1002/adma.20230002310.1002/adma.202300023 ↗
38. 10.1002/adma.20230931410.1002/adma.202309314 ↗
39. 10.1038/s41467-022-30539-610.1038/s41467-022-30539-6 ↗
40. Netzer, Y.; Wang, T.; Coates, A.; Bissacco, A.; Wu, B.; Ng, A. Y. In Reading Digits in Natural Images with Unsupervised Feature Learning, NIPS Workshop on Deep Learning and Unsupervised Feature Learning; NIPS: Granada, Spain, 2011; p 7.