Artificial SiNz:H Synapse Crossbar Arrays with Gradual Conductive Pathway for High-Accuracy Neuromorphic Computing

Tong Chen; Zhongyuan Ma; Hongsheng Hu; Yang Yang; Chengfeng Zhou; Furao Shen; Haitao Xu; Jun Xu; Ling Xu; Wei Li; Kunji Chen

doi:10.3390/nano13162362

Artificial SiN_z:H Synapse Crossbar Arrays with Gradual Conductive Pathway for High-Accuracy Neuromorphic Computing

Nanomaterials (Basel). 2023 Aug 18;13(16):2362. doi: 10.3390/nano13162362.

Authors

Tong Chen^{1

2

3}, Zhongyuan Ma^{1

2

3}, Hongsheng Hu^{1

2

3}, Yang Yang^{1

2

3}, Chengfeng Zhou^{1

2

3}, Furao Shen⁴, Haitao Xu^{5

6}, Jun Xu^{1

2

3}, Ling Xu^{1

2

3}, Wei Li^{1

2

3}, Kunji Chen^{1

2

3}

Affiliations

¹ School of Electronic Science and Engineering, Nanjing University, Nanjing 210093, China.
² Collaborative Innovation Center of Advanced Microstructures, Nanjing University, Nanjing 210093, China.
³ Jiangsu Provincial Key Laboratory of Photonic and Electronic Materials Sciences and Technology, Nanjing University, Nanjing 210093, China.
⁴ School of Artificial Intelligence, Nanjing University, Nanjing 210093, China.
⁵ Institute of Advanced Functional Materials and Devices, Shanxi University, Taiyuan 030031, China.
⁶ Institute of Carbon-Based Thin Film Electronics, Peking University, Taiyuan 030031, China.

Abstract

Inspired by its highly efficient capability to deal with big data, the brain-like computational system has attracted a great amount of attention for its ability to outperform the von Neumann computation paradigm. As the core of the neuromorphic computing chip, an artificial synapse based on the memristor, with a high accuracy in processing images, is highly desired. We report, for the first time, that artificial synapse arrays with a high accuracy in image recognition can be obtained through the fabrication of a SiN_z:H memristor with a gradient Si/N ratio. The training accuracy of SiN_z:H synapse arrays for image learning can reach 93.65%. The temperature-dependent I-V characteristic reveals that the gradual Si dangling bond pathway makes the main contribution towards improving the linearity of the tunable conductance. The thinner diameter and fixed disconnection point in the gradual pathway are of benefit in enhancing the accuracy of visual identification. The artificial SiN_z:H synapse arrays display stable and uniform biological functions, such as the short-term biosynaptic functions, including spike-duration-dependent plasticity, spike-number-dependent plasticity, and paired-pulse facilitation, as well as the long-term ones, such as long-term potentiation, long-term depression, and spike-time-dependent plasticity. The highly efficient visual learning capability of the artificial SiN_z:H synapse with a gradual conductive pathway for neuromorphic systems hold great application potential in the age of artificial intelligence (AI).

Keywords: Si dangling bond; artificial synapse; multilevel resistive switching; silicon nitride.

Abstract

Grants and funding