A Multiple‐State Ion Synaptic Transistor Applicable to Abnormal Car Detection with Transfer Learning. (1st March 2022)

• Record Type: Journal Article
• Authors: Yu, Ji-Man; Ham, Gyeongdo; Lee, Chungryeol; Lee, Jae-Hyeok; Han, Joon-Kyu; Kim, Jin-Ki; Jang, Donggon; Kim, Nahyun; Kim, Moon-Seok; Im, Sung Gap; Kim, Dae-Shik; Choi, Yang-Kyu
• Is Part Of: Advanced intelligent systems. Volume 4:Number 6(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-03-01
• Subjects: abnormal car detention (ACD) -- convolutional neural network (CNN) -- multiple-level weight neuromorphic system -- polymer electrolyte-gated synaptic transistor (pEGST) -- transfer learning; Artificial intelligence -- Periodicals; Robotics -- Periodicals; Control theory -- Periodicals; 006.3
• DOI: 10.1002/aisy.202100231
• Languages: English
• ISSNs: 2640-4567

Abstract

Abstract : An artificial synapse is an essential element to construct a hardware‐based artificial neural network (ANN). While various synaptic devices have been proposed along with studies on electrical characteristics and proper applications, a small number of conductance states with nonlinear and asymmetric conductance changes have been problematic and imposed limits on computational performance. Their applications are thus still limited to the classification of simple images or acoustic datasets. Herein, a polymer electrolyte‐gated synaptic transistor (pEGST) is demonstrated for video‐based learning and inference using transfer learning. In particular, abnormal car detection (ACD) is attempted with video‐based learning and inference to avoid traffic accidents. The pEGST showed multiple states of 8, 192 (=13 bits) for weight modulation with linear and symmetric conductance changes and helped reduce the error rate to 3% to judge whether a car in a video is abnormal. Abstract : A polymer electrolyte‐gated synaptic transistor (pEGST) is demonstrated for video‐based learning and inference using transfer learning. Abnormal car‐detecting application is attempted. The pEGST shows multiple states of 13 bits with linear and symmetric weight modulation and achieves 3% of the error rate compared with the upper limit of accuracy by use of cutting‐edge graphics processing units.