油藏计算
适应性
计算机科学
建筑
晶体管
神经形态工程学
信号(编程语言)
人工神经网络
分布式计算
人工智能
循环神经网络
电气工程
工程类
电压
艺术
视觉艺术
生物
程序设计语言
生态学
作者
Ruiqi Chen,Haozhang Yang,Ruiyi Li,Guihai Yu,Yizhou Zhang,Junchen Dong,Dedong Han,Zheng Zhou,Peng Huang,Lifeng Liu,Xiaoyan Liu,Jinfeng Kang
出处
期刊:Science Advances
[American Association for the Advancement of Science (AAAS)]
日期:2024-02-16
卷期号:10 (7): eadl1299-eadl1299
被引量:38
标识
DOI:10.1126/sciadv.adl1299
摘要
Reservoir computing is a powerful neural network–based computing paradigm for spatiotemporal signal processing. Recently, physical reservoirs have been explored based on various electronic devices with outstanding efficiency. However, the inflexible temporal dynamics of these reservoirs have posed fundamental restrictions in processing spatiotemporal signals with various timescales. Here, we fabricated thin-film transistors with controllable temporal dynamics, which can be easily tuned with electrical operation signals and showed excellent cycle-to-cycle uniformity. Based on this, we constructed a temporal adaptive reservoir capable of extracting temporal information of multiple timescales, thereby achieving improved accuracy in the human-activity-recognition task. Moreover, by leveraging the former computing output to modify the hyperparameters, we constructed a closed-loop architecture that equips the reservoir computing system with temporal self-adaptability according to the current input. The adaptability is demonstrated by accurate real-time recognition of objects moving at diverse speed levels. This work provides an approach for reservoir computing systems to achieve real-time processing of spatiotemporal signals with compound temporal characteristics.
科研通智能强力驱动
Strongly Powered by AbleSci AI