Photoprogrammed Multifunctional Optoelectronic Synaptic Transistor Arrays Based on Photosensitive Polymer‐Sorted Semiconducting Single‐Walled Carbon Nanotubes for Image Recognition

• Published in: Advanced science Vol. 11; no. 29; pp. e2401794 - n/a
• Main Authors: Sui, Nianzi, Ji, Yixi, Li, Min, Zheng, Fanyuan, Shao, Shuangshuang, Li, Jiaqi, Liu, Zhaoxin, Wu, Jinjian, Zhao, Jianwen, Li, Lain‐Jong
• Format: Journal Article
• Language: English
• Published: Germany John Wiley & Sons, Inc 01.08.2024; John Wiley and Sons Inc; Wiley
• Subjects: Arrays; Brain; broadband response; Carbon; flexible optoelectronic synaptic devices; Light; multilevel storage; Neural networks; photosensitive conjugated polymer; Polymers; Power; spiking neural network; Transistors; flexible optoelectronic synaptic devices; multilevel storage; spiking neural network; broadband response; photosensitive conjugated polymer
• ISSN: 2198-3844; 2198-3844
• DOI: 10.1002/advs.202401794

The development of neuromorphic optoelectronic systems opens up the possibility of the next generation of artificial vision. In this work, the novel broadband (from 365 to 940 nm) and multilevel storage optoelectronic synaptic thin‐film transistor (TFT) arrays are reported using the photosensitive conjugated polymer (poly[(9,9‐dioctylfluorenyl‐2,7‐diyl)‐co‐(bithiophene)], F8T2) sorted semiconducting single‐walled carbon nanotubes (sc‐SWCNTs) as channel materials. The broadband synaptic responses are inherited to absorption from both photosensitive F8T2 and sorted sc‐SWCNTs, and the excellent optoelectronic synaptic behaviors with 200 linearly increasing conductance states and long retention time > 103 s are attributed to the superior charge trapping at the AlOx dielectric layer grown by atomic layer deposition. Furthermore, the synaptic TFTs can achieve IOn/IOff ratios up to 106 and optoelectronic synaptic plasticity with the low power consumption (59 aJ per single pulse), which can simulate not only basic biological synaptic functions but also optical write and electrical erase, multilevel storage, and image recognition. Further, a novel Spiking Neural Network algorithm based on hardware characteristics is designed for the recognition task of Caltech 101 dataset and multiple features of the images are successfully extracted with higher accuracy (97.92%) of the recognition task from the multi‐frequency curves of the optoelectronic synaptic devices. The authors selectively isolated from commercial SWCNTs using the photosensitive conjugated polymers, and the optoelectronic synaptic transistors are successfully constructed with low power consumption (59 aJ per spike) and excellent storage characteristics   for simulation of neuromorphic vision systems (the accuracy ≈97.92%). Their SWCNT optoelectronic synaptic transistors do not require the introduction of any additional photosensitive materials and exhibit excellent optoelectronic properties.