博雅計(jì)劃—博雅計(jì)劃：人工智能與深度學(xué)習(xí)專題： 告別“機(jī)器假學(xué)習(xí)”，下一代AI熱潮：因果推斷與強(qiáng)人工智能實(shí)現(xiàn)路徑研究【大學(xué)組】

開(kāi)始日期：

2023年7月8日

專業(yè)方向：

計(jì)算機(jī)與人工智能

導(dǎo)師：

Nicholas （劍橋大學(xué) University of Cambridge 終身教授）

課程周期：

7周在線小組科研+5周論文指導(dǎo)學(xué)習(xí)

語(yǔ)言：

英文

建議學(xué)生年級(jí)：

大學(xué)生

項(xiàng)目產(chǎn)出：

7周在線小組科研學(xué)習(xí)+5周論文指導(dǎo)學(xué)習(xí) 學(xué)術(shù)報(bào)告 EI/CPCI/Scopus/ProQuest/Crossref/EBSCO或同等級(jí)別索引國(guó)際會(huì)議全文投遞與發(fā)表（共同一作） 結(jié)業(yè)證書(shū) 成績(jī)單

項(xiàng)目介紹：

項(xiàng)目?jī)?nèi)容包括機(jī)器學(xué)習(xí)理論、應(yīng)用與技術(shù)，線性分類器，卷積神經(jīng)網(wǎng)絡(luò)，回歸神經(jīng)網(wǎng)絡(luò)等。學(xué)生將通過(guò)項(xiàng)目熟悉機(jī)器學(xué)習(xí)、神經(jīng)網(wǎng)絡(luò)、深度神經(jīng)網(wǎng)絡(luò)等理論知識(shí)與機(jī)器學(xué)習(xí)語(yǔ)音與圖像處理案例，在項(xiàng)目結(jié)束時(shí)，提交項(xiàng)目報(bào)告，進(jìn)行成果展示。 This course aims to provide an introduction to the fundamentals of deep learning. It will cover the most common forms of model architectures and primarily the algorithms used to train them. Attention will also be payed to how deep learning manifests in both distributed and constrained compute platforms (e.g., computing clusters, wearables and phones). Theory and principles will be presented, but this will go hand-in-hand with a focus on practical experience such as using existing frameworks and implementing (simplified versions) of core algorithms. Students will be taught the basics of neural networks, convolutional networks, recurrent networks; and introduced to concepts such as: dropout, batch normalization, and types of hyper-parameter optimization. Applications in the area of audio and image processing will be discussed.