Transfer learning approach to analyzing the work function fluctuation of gate-all-around silicon nanofin field-effect transistors. (October 2022)

• Record Type: Journal Article
• Authors: Akbar, Chandni; Li, Yiming; Sung, Wen-Li
• Is Part Of: Computers & electrical engineering. Volume 103(2022)
• Publication Date: 2022-10
• Subjects: Gate-all-around -- Nanosheet -- Nanofin -- Field-effect transistors -- Random nanosized metal grain -- Work function fluctuation -- Statistical device simulation -- Machine learning -- Transfer learning; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108392
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: To overcome the challenges of the shrinking of technology nodes, machine learning (ML) is utilized to analyze the nanosized-metal-grain pattern-dependent device. The requisite ML technique, i.e., inevitable dataset, can be overcome by considering the transfer learning (TL) approach. To estimate the work-function-fluctuation-induced variability without executing a huge amount of device simulation of gate-all-around silicon nanofin field-effect transistors is followed along with the combination of collected data of gate-all-around silicon nanosheet field-effect transistors and TL technique. The proposed TL model show a significant improvement in terms of root mean square error value and R 2 -score as compared to the baseline ML model. Abstract: With the shrinking of technological nodes, analysis of nanosized-metal-grain pattern-dependent devices is becoming critical; various machine learning (ML) approaches have been utilized to study device characteristic and variability. The inevitable dataset, one of the requisite ML techniques, can be overcome by considering the transfer learning (TL) approach. In this work, an analysis of electrical characteristic affected by work function fluctuation (WKF) with a limited amount of dataset of gate-all-around (GAA) silicon (Si) nanofin (NF) field-effect transistors (FETs) is advanced along with the combination of collected data of GAA Si nanosheet (NS) FETs and TL models. Comparison of the baseline ML model and the proposed TL model shows significant improvement in terms of the values of root mean square error (RMSE) and R 2 -score. One of applications of this work is to estimate the WKF-induced variability without executing a huge amount of three-dimensional device simulation of GAA Si NF FETs. Graphical abstract: Plots in the first two frames illustrate 3D structures of the GAA Si NS FET and the GAA Si NF FET. Three frames represent the training and testing of the transfer learning-based neural network model of the GAA Si NS FET and the GAA Si NF FET, respectively. Image, graphical abstract