Biomemristor Reservoir Computing With Multi-Value Mask for Improving Recognition Performance
IEEE Electron Device Letters · 2024-09 · 45 (9) · 1657-1660
DOI: 10.1109/led.2024.3424781 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Electron Device Letters, 2024-09. Verfasst von Yang Li und 15 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 27 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Concept Foundation of Hangzhou Institute of Technology, Xidian University, National Natural Science Foundation of China.
Abstract (Originalsprache)
In this letter, we report an efficient and affordable RC system where the masking process in input and reservoir layers are implemented by nonvolatile and volatile memristors, respectively. The nonvolatile memristors with a TiN/HfOx/TaOx/TiN structure show multilevel programmable resistance states, serving as multi-value mask matrices to increase the richness of reservoir state. Meanwhile, Ag/guar gum-WTe2 nanohybrid/Au biomemristor synapses exhibit short-term memory and nonlinear dynamics, fulfilling the implementation of physical reservoirs. The performance of the RC system was further evaluated by the tasks of speech digit recognition and electrocardiogram waveform classification. By implementing the multi-value mask, the accuracy rates of these two tasks were improved to 99.6% and 99.2%, respectively. Our findings suggest that the multi-value RC system shows a great potential for processing complex temporal signals in a low-cost and energy-efficient manner.
Förderung
- National Key Research and Development Program of China
- Concept Foundation of Hangzhou Institute of Technology, Xidian University
- National Natural Science Foundation of China
- Shanghai Pujiang Program
Zitieren
APA
Li, Y., Cao, J., Yu, J., Liu, M., Zhang, X., Chen, J., Xu, Q., Liu, X., Qiu, J., Chen, Y., Li, M., Zhu, C., Xu, Z., Ma, X., Wang, H., & Wang, M. (2024). Biomemristor Reservoir Computing With Multi-Value Mask for Improving Recognition Performance. IEEE Electron Device Letters, 45(9), 1657-1660. https://doi.org/10.1109/led.2024.3424781
Vancouver
Li Y, Cao J, Yu J, Liu M, Zhang X, Chen J, et al. Biomemristor Reservoir Computing With Multi-Value Mask for Improving Recognition Performance. IEEE Electron Device Letters. 2024;45(9):1657-1660. doi:10.1109/led.2024.3424781
BibTeX
@article{Li2024,
author = {Li, Yang and Cao, Jie and Yu, Jie and Liu, Mengyang and Zhang, Xumeng and Chen, Jiewen and Xu, Qian and Liu, Xusheng and Qiu, Jie and Chen, Yan and Li, Mingxun and Zhu, Chenxin and Xu, Zhongguang and Ma, Xiaohua and Wang, Hong and Wang, Ming},
title = {Biomemristor Reservoir Computing With Multi-Value Mask for Improving Recognition Performance},
journal = {IEEE Electron Device Letters},
year = {2024},
volume = {45},
number = {9},
pages = {1657--1660},
doi = {10.1109/led.2024.3424781}
}
EUVIMED