國外小組科研—EE電子工程專題: 基于石墨烯、量子點(diǎn)等低維納米半導(dǎo)體材料的AI芯片技術(shù)原理及其在人工智能與大數(shù)據(jù)中的應(yīng)用【大學(xué)組】

開始日期：

2023年10月14日

專業(yè)方向：

理工

導(dǎo)師：

Deep（賓夕法尼亞大學(xué) (UPenn) 教授）

課程周期：

7周在線小組科研學(xué)習(xí)+5周不限時(shí)論文指導(dǎo)學(xué)習(xí)

語言：

英文

建議學(xué)生年級：

大學(xué)生

項(xiàng)目產(chǎn)出：

7周在線小組科研學(xué)習(xí)+5周不限時(shí)論文指導(dǎo)學(xué)習(xí) 共125課時(shí) 項(xiàng)目報(bào)告 優(yōu)秀學(xué)員獲主導(dǎo)師Reference Letter EI/CPCI/Scopus/ProQuest/Crossref/EBSCO或同等級別索引國際會議全文投遞與發(fā)表指導(dǎo)（可用于申請） 結(jié)業(yè)證書 成績單

項(xiàng)目介紹：

本項(xiàng)目將從半導(dǎo)體中的固體物理基礎(chǔ)開始，主要包括半導(dǎo)體的電子帶結(jié)構(gòu)和光相互作用/光學(xué)性質(zhì)的原理，并特別關(guān)注低維半導(dǎo)體，如碳納米管、III-V量子阱、2D半導(dǎo)體、石墨烯以及量子點(diǎn)。隨后課程將介紹納米級器件，即p-n結(jié)，場效應(yīng)晶體管以及傳感器，這部分課程的重點(diǎn)將是理解納米尺度的靜電學(xué)以及材料和器件中的傳輸理論，涵蓋納米級晶體管和量子受限材料中的彈道傳輸理論。還將討論存儲設(shè)備的基本概念，如果時(shí)間允許，也會討論光的物理學(xué)和運(yùn)動(dòng)傳感器。在介紹設(shè)備之后，課程將進(jìn)一步介紹納米制造技術(shù)，包括光刻技術(shù)和半導(dǎo)體制造的進(jìn)展，有助于制造用于現(xiàn)代計(jì)算機(jī)和服務(wù)器的最新高性能芯片。在納米制造和制造之后，導(dǎo)師將更多地介紹納米電子硬件的當(dāng)前趨勢，用于人工智能和機(jī)器學(xué)習(xí)應(yīng)用程序的大數(shù)據(jù)處理，包括低功耗/資源的邊緣計(jì)算。將詳細(xì)討論存儲設(shè)備、低功耗邏輯設(shè)備以及它們?nèi)绾卧谀Ｊ阶R別等機(jī)器學(xué)習(xí)應(yīng)用中協(xié)同工作。項(xiàng)目旨在于目為學(xué)生提供與計(jì)算過程和制造相關(guān)的基本物理框架，以及高性能節(jié)能大數(shù)據(jù)計(jì)算的硬件需求。討論的具體器件包括晶體管、存儲器件和傳感器(包括光電探測器和MEMS)。 This is a online program starting with nanoelectronics devices and the role nanoscale electronics hardware plays in AI systems. After that the course will move into nanoscale devices namely p-n junctions, field-effect transistors as well as sensors. The focus in this part of the course will be to understand nanoscale electrostatics as well as transport theory in materials and devices. The theory of nanoscale transistor and ballistic transport in quantum confined materials will be covered. Basic concepts of memory devices will also be discussed. If time permits physics of light and motion sensors will also be discussed.After devices, the course will move into nanofabrication techniques including advances in lithography and semiconductor manufacturing that helps makes the latest high-performance chips used in modern computers and servers. After nanofabrication and manufacturing the course will more into and current trends in nanoelectronics hardware for handling big data for AI and machine learning applications including edge computing with low-power/resources. Detailed discussion on memory devices, low-power logic devices and how they work together in machine learning applications such as pattern recognition will be discussed. The aim of the course is to provide the student a fundamental physics framework pertaining to computing processes and fabrication as well as hardware needs for high performance energy efficient, big-data computation. Specific devices to be discussed include transistors, memory devices and sensors (including photodetectors and MEMS). The program aims to provide the students a high-level framework towards the understanding of nanoelectronics and optoelectronic devices. The course will help the students making informed decisions about their career choice and further having an upper hand when they take courses during graduate studies.