Toward grouped-reservoir computing: organic neuromorphic vertical transistor with distributed reservoir states for efficient recognition and prediction

Changsong Gao; Di Liu; Chenhui Xu; Weidong Xie; Xianghong Zhang; Junhua Bai; Zhixian Lin; Cheng Zhang; Yuanyuan Hu; Tailiang Guo; Huipeng Chen

doi:10.1038/s41467-024-44942-8

Toward grouped-reservoir computing: organic neuromorphic vertical transistor with distributed reservoir states for efficient recognition and prediction

Nat Commun. 2024 Jan 25;15(1):740. doi: 10.1038/s41467-024-44942-8.

Authors

Changsong Gao^{1

2}, Di Liu^{1

2}, Chenhui Xu^{1

2}, Weidong Xie^{1

2}, Xianghong Zhang^{1

2}, Junhua Bai³, Zhixian Lin^{1

4}, Cheng Zhang⁵, Yuanyuan Hu⁶, Tailiang Guo^{1

2}, Huipeng Chen^{7

8}

Affiliations

¹ Institute of Optoelectronic Display, National & Local United Engineering Lab of Flat Panel Display Technology, Fuzhou University, 350002, Fuzhou, China.
² Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China, 350100, Fuzhou, China.
³ Joint School of National University of Singapore and Tianjin University, International Campus of Tianjin University, Binhai New City, 350207, Fuzhou, China.
⁴ School of Advanced Manufacturing, Fuzhou University, 362200, Quanzhou, China.
⁵ Department of Physics, Fuzhou University, 350108, Fuzhou, China.
⁶ Changsha Semiconductor Technology and Application Innovation Research Institute, College of Semiconductors (College of Integrated Circuits), Hunan University, 410082, Changsha, China.
⁷ Institute of Optoelectronic Display, National & Local United Engineering Lab of Flat Panel Display Technology, Fuzhou University, 350002, Fuzhou, China. hpchen@fzu.edu.cn.
⁸ Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China, 350100, Fuzhou, China. hpchen@fzu.edu.cn.

Abstract

Reservoir computing has attracted considerable attention due to its low training cost. However, existing neuromorphic hardware, focusing mainly on shallow-reservoir computing, faces challenges in providing adequate spatial and temporal scales characteristic for effective computing. Here, we report an ultra-short channel organic neuromorphic vertical transistor with distributed reservoir states. The carrier dynamics used to map signals are enriched by coupled multivariate physics mechanisms, while the vertical architecture employed greatly increases the feedback intensity of the device. Consequently, the device as a reservoir, effectively mapping sequential signals into distributed reservoir state space with 1152 reservoir states, and the range ratio of temporal and spatial characteristics can simultaneously reach 2640 and 650, respectively. The grouped-reservoir computing based on the device can simultaneously adapt to different spatiotemporal task, achieving recognition accuracy over 94% and prediction correlation over 95%. This work proposes a new strategy for developing high-performance reservoir computing networks.