油藏计算
晶体管
电解质
放松(心理学)
单层
计算机科学
材料科学
离子
系列(地层学)
联轴节(管道)
频道(广播)
混乱的
弹道
纳米技术
物理
电极
化学
电气工程
人工智能
电压
人工神经网络
工程类
物理化学
循环神经网络
电信
心理学
生物
古生物学
社会心理学
量子力学
冶金
天文
作者
Dongdong Sun,Ao Li,Xinyang Deng,Shaofan Zhao,Z. Xu,Qinghai Tan,Yi Wan,Xiangdong Li,Shaochuan Chen,Ilia Valov,Yuanyuan Shi
出处
期刊:Small
[Wiley]
日期:2025-06-25
卷期号:: e2504066-e2504066
被引量:6
标识
DOI:10.1002/smll.202504066
摘要
Abstract Physical reservoir computing (PRC) is considered as an efficient method for solving complex time series tasks due to its outstanding advantages such as easy training and hardware implementation. However, a memristor‐based reservoir with only a single timescale carrier/ion dynamics limits the performance of multiple timescale feature extraction. Here a fully volatile, electrolyte‐gated monolayer (ML) WSe2 transistor with a coexistent double relaxation timescale (DRT) is reported, which enriches the reservoir dynamics and has excellent time series prediction capability in PRC. The coexistence of DRT is achieved by the ion‐electron coupling effect between the electrolyte dielectric and the WSe2 channel. Compared with single relaxation timescale (SRT), the DRT in WSe2 transistor leads to enhanced information processing capability in chaotic time series prediction, multi‐scale time series prediction, and traffic trajectory prediction applications. This work paves the way for the development of complex timescale‐based dynamic devices for high‐performance reservoir computing networks.
科研通智能强力驱动
Strongly Powered by AbleSci AI