首页|Findings from University of Waterloo Update Understanding of Carbon Nanotubes (A Random Forest Model for Predicting and Analyzing the Performance of Cnt Tfet Wi th Highly Doped Pockets)
Findings from University of Waterloo Update Understanding of Carbon Nanotubes (A Random Forest Model for Predicting and Analyzing the Performance of Cnt Tfet Wi th Highly Doped Pockets)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Investigators publish new report on Nanotechnolog y - Carbon Nanotubes. According to news reporting originating in Waterloo, Canad a, by NewsRx journalists, research stated, “This paper presents a Random Forest (RF) machine learning model that relates the DC characteristics and high-frequen cy response of a carbon nanotube (CNT) tunnel field-effect transistor (TFET) wit h highly doped pockets to the transistor parameters. The analysis of multiple fa ctors for a complex structure as the one studied here becomes expensive with the ordinary simulation techniques and hence machine learning (ML) offers a profici ent method to model and enhance the understanding of the key factors that influe nce the CNT TFET with pockets in considerably reduced time.” The news reporters obtained a quote from the research from the University of Wat erloo, “Numerical simulations are used to generate the data on which the model i s trained. This dataset comprises ten input features and four output attributes. The tuned model is capable of predicting the output characteristics of the devi ce with minimal mean squared error (MSE). The RF model is also compared to other ML algorithms to demonstrate its advantage. This study makes use of the interpr etable random forest model in identifying the key factors that affect the output characteristics of the Carbon nanotube TFET with highly doped pockets.”
WaterlooCanadaNorth and Central Amer icaCarbon NanotubesCyborgsEmerging TechnologiesMachine LearningNanotec hnologyNanotubesUniversity of Waterloo
NETL
NSTL
