主講人:宋士吉教授
時間:2017年10月18日13:30
地點:機電學院仰儀南樓207-2
歡迎廣大師生參加!
Topic: Stochastic Depth and Densely Connected Convolutional Networks
隨機深度和稠密聯結的卷積網絡
Abstract: Deep learning methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains. In particular, Convolutional Neural Networks (CNNs) were popularized within the vision community in 2009 through AlexNet and its celebrated victory at the ImageNet competition. In this talk, we will introduce two effective convolutional neural networks: Deep Networks with Stochastic Depth and Densely Connected Convolutional Networks (DenseNet). Stochastic Depth enables the seemingly contradictory setup to train short networks and use deep networks at test time. With stochastic depth we can increase the depth of residual networks even beyond 1200 layers and still yield meaningful improvements in test error (4.91% on CIFAR-10). DenseNet connects each layer to every other layer in a feed-forward fashion, which could alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. DenseNet obtains significant improvements over the state-of-the-art on most of object recognition benchmark tasks, whilst requiring less memory and computation to achieve high performance.
講座人簡介:
宋士吉: 男,1965年5月生,清華大學自動化系教授、博士生導師。1996年獲得哈爾濱工業大學數學博士學位;1996至2000年,在中國海洋大學物理海洋專業、東南大學控制理論與應用專業2次完成博士后研究。
長期從事復雜制造系統建模優化與控制技術、機器學習與故障診斷、水下機器人智能控制等方向研究工作。在國內外重要學術期刊會議發表論文200余篇,其中IEEE Transactions 系列期刊長文、國際著名專業期刊SCI檢索論文近100篇,擔任《IEEE T SMC:Systems》,《中國科學-信息科學》及《自動化學報》等期刊編委,《人工智能與機器人研究》副主編。獲得教育部自然科學二等獎勵2項,黑龍江生自然科學二等獎1項,江蘇省自然科學一等獎1項。
主持完成了國家自然科學基金重大科學儀器研制項目、重點項目、面上項目、科技部重點專項、中國大洋協會專項課題等30余項。