Self-rectifying memristor arrays integrate simulated annealing for advanced neuromorphic computing. (IMAGE)

Tsinghua University Press

Self-rectifying memristor arrays integrate simulated annealing for advanced neuromorphic computing.

Caption

This image illustrates the 1 kbit self-rectifying memristor (SRM) array developed in the study, which shows superior rectification and on/off ratios, along with low-power reading, multi-state storage, and multi-level switching. It features exceptional fluctuation suppression and high consistency, operating stably under repeated cycles and low voltages. Also depicted is its integration with a simulated annealing algorithm via a dedicated test board, enabling rapid, efficient image restoration that outperforms conventional methods—offering new paradigms for in-memory computing hardware.

Credit

J. Bian, Y. Zhu, S. Yan, Y. Tang, J. Guo, G. Li, J. Zhao, Q. Zhong, Q. Li, S. Liu, R. Liu, Q. Chen, Y. Xiao, X. Zhu, Q. Li, M. Tang, Nano Research 2025. DOI: 10.26599/NR.2025.94907803, Tsinghua University Press.

Usage Restrictions

This image may be used or redistributed by news outlets, academic institutions, and related organizations with proper attribution, solely for coverage or promotion of this research.

License

Original content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.