Journal of the Semiconductor & Display Technology (반도체디스플레이기술학회지)

The Korean Society Of Semiconductor & Display Technology (한국반도체디스플레이기술학회)
권호 표지

Optimization of Memristor Devices for Reservoir Computing

축적 컴퓨팅을 위한 멤리스터 소자의 최적화

  • Kyeongwoo Park (System Semiconductor Engineering Department at Sangmyung University) ;
  • HyeonJin Sim (System Semiconductor Engineering Department at Sangmyung University) ;
  • HoBin Oh (System Semiconductor Engineering Department at Sangmyung University) ;
  • Jonghwan Lee (System Semiconductor Engineering Department at Sangmyung University)
  • 박경우 (상명대학교 시스템반도체공학과) ;
  • 심현진 (상명대학교 시스템반도체공학과) ;
  • 오호빈 (상명대학교 시스템반도체공학과) ;
  • 이종환 (상명대학교 시스템반도체공학과)
  • Received : 2023.12.08
  • Accepted : 2024.03.20
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, artificial neural networks have been playing a crucial role and advancing across various fields. Artificial neural networks are typically categorized into feedforward neural networks and recurrent neural networks. However, feedforward neural networks are primarily used for processing static spatial patterns such as image recognition and object detection. They are not suitable for handling temporal signals. Recurrent neural networks, on the other hand, face the challenges of complex training procedures and requiring significant computational power. In this paper, we propose memristors suitable for an advanced form of recurrent neural networks called reservoir computing systems, utilizing a mask processor. Using the characteristic equations of Ti/TiOx/TaOy/Pt, Pt/TiOx/Pt, and Ag/ZnO-NW/Pt memristors, we generated current-voltage curves to verify their memristive behavior through the confirmation of hysteresis. Subsequently, we trained and inferred reservoir computing systems using these memristors with the NIST TI-46 database. Among these systems, the accuracy of the reservoir computing system based on Ti/TiOx/TaOy/Pt memristors reached 99%, confirming the Ti/TiOx/TaOy/Pt memristor structure's suitability for inferring speech recognition tasks.

Keywords

Acknowledgement

This work was supported by the International Science & Business Belt support program, through the Korea Innovation Foundation funded by the Ministry of Science and ICT. This research was supported in part by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (No. 2022R1I1A3064285).

References

  1. Yeon Ho Chu, Young Kyu Choi, "A Deep learning based IOT device recognition system", Journal of The Korean Society of Semiconductor & Display, Vol.18, pp.1-5, 2019.
  2. Geon Woo Park, Jae Gyu Kim, Geon Woo Choi, "A Review of RRAM-based Synaptic Device to Improve Neuromorphic Systems", Journal of The Korean Society of Semiconductor & Display, Vol.21, pp50-56, 2022
  3. Rodrigo Leal Martyr, Maria Jose Sanchez, Myriam Aguirre, Walter Quinonez, Christian Ferreyra, Carlos Acha, Jerome Lecourt, Ulrike Luders, Diego Rubi, "Oxygen vacancy dynamics in Pt/TiOx/TaOy/Pt memristors: exchange with the environment and internal electromigration", Nanotechnology, Vol.34, No.9, 2022.
  4. Yanan Zhong, Jianshi Tang, Xinyi Li, Bin Gao, He Qian, Huaqiang Wu, "Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing", Nature Communications, pp. 2-6, 2021.
  5. Sachin Maheshwari, Spyros Stathopoulos, Jiaqi Wang, Alexander Serb, Yihan Pan, Andrea Mifsud, Lieuwe B. Leene, Jiawei Shen, Christos Papavassiliou, Timothy G. Constandinou, Themistoklis Prodromakis, "Design Flow for Hybrid CMOS/memristor systems-Part I: Modeling and Verification steps", IEEE Trans. Circuits and Systems I: Regular Papers, Vol.68, No.12, pp. 4862-4875, 2021.
  6. Jingbiao Cui, "Zinc oxide nanowires", Materials Characterization, Vol.64, pp.43-52, 2012.
  7. Junhee Cho, "The Study of nc-ZnO/ZnO Field-effect Transistors Fabricated by Spray-pyrolysis Process", Journal of The Korean Society of Semiconductor & Display, Vol.21, pp.22-25, 2022.
  8. Lixun Wang, Yuejun Zhang, Zhecheng Guo, Zhixin Wu, Xinhui Chen, Shimin Du, "Reservoir Computing-Based Design of ZnO Memristor-Type Digital Identification Circuits", Micromachines, Vol.13, No.13(10), pp.1-14, 2022.
  9. Enrique Miranda, Gianluca Milano, Carlo Ricciardi, "Modeling of Short-Term Synaptic Plasticity Effects in ZnO Nanowire-Based Memristors Using a Potentiation-Depression Rate Balance Equation", IEEE Trans. Nanotechology, Vol.19, pp. 609-612, 2020.
  10. Jie Cao, Xumeng Zhang, Hongfei Cheng, Jie Qiu, Xusheng Liu, Ming Wang, Qi Liu, "Emerging dynamic memristors for neuromorphic reservoir computing", Nanoscale, pp.207-548, 2022.
  11. Linfeng Sun, Zhongrui Wang, Jinbao Jiang, Yeji Kim, Bomin Joo, Shoujun Zheng, Seungyeon Lee, Woo Jong Yu, Bai-Sun Kong, AND Heejun Yang, "In-sensor reservoir computing for language learning via two-dimensional memristors", Science Advances, Vol.7, No.20, pp.1-8, 2021.
  12. NIST TI-46 Benchmark Test Data. Retrieved September 8, 2023, from https://www.nist.gov/ambench/benchmar-test-data