Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing

• Published in: Nature communications Vol. 12; no. 1; pp. 408 - 9
• Main Authors: Zhong, Yanan, Tang, Jianshi, Li, Xinyi, Gao, Bin, Qian, He, Wu, Huaqiang
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 18.01.2021; Nature Publishing Group; Nature Portfolio
• Subjects: 639/925/927/1007; 639/925/929/115; Computing time; Efficiency; Errors; Hardware; Humanities and Social Sciences; Mean square errors; Memristors; multidisciplinary; Neural networks; Neurons; Parameters; Predictions; Recognition; Recurrent neural networks; Science; Science (multidisciplinary); Signal processing; Task complexity; Time series

Reservoir computing is a highly efficient network for processing temporal signals due to its low training cost compared to standard recurrent neural networks, and generating rich reservoir states is critical in the hardware implementation. In this work, we report a parallel dynamic memristor-based r...