Author(s): Zhao, SF (Zhao, Shufang); Ran, WH (Ran, Wenhao); Lou, Z (Lou, Zheng); Li, LL (Li, Linlin); Poddar, S (Poddar, Swapnadeep); Wang, LL (Wang, Lili); Fan, ZY (Fan, Zhiyong); Shen, GZ (Shen, Guozhen)

Source: NATIONAL SCIENCE REVIEW DOI: 10.1093/nsr/nwac158 Early Access Date: AUG 2022

Abstract: High-accuracy neuromorphic devices with adaptive weight adjustment are crucial for high-performance computing. However, limited studies have been conducted on achieving selective and linear synaptic weight updates without changing electrical pulses. Herein, we propose high-accuracy and self-adaptive artificial synapses based on tunable and flexible MXene energy storage devices. These synapses can be adjusted adaptively depending on the stored weight value to mitigate time and energy loss resulting from recalculation. The resistance can be used to effectively regulate the accumulation and dissipation of ions in single devices, without changing the external pulse stimulation or preprogramming, to ensure selective and linear synaptic weight updates. The feasibility of the proposed neural network based on the synapses of flexible energy devices was investigated through training and machine learning. The results indicated that the device achieved a recognition accuracy of similar to 95% for various neural network calculation tasks such as numeric classification.

A novel neuromorphic device based on a flexible MXene energy storage device was designed that can achieve a self-adaption neural network to avoid the loss of time and energy caused by recalculation.

Accession Number: WOS:000857590200001

ISSN: 2095-5138

eISSN: 2053-714X

Full Text: https://academic.oup.com/nsr/advance-article/doi/10.1093/nsr/nwac158/6665934