主讲人：宋士吉教授
　　时间：2017年10月18日13：30
　　地点：机电学院仰仪南楼207-2
　　欢迎广大师生参加！

　　　　　　　Topic: Stochastic Depth and Densely Connected Convolutional Networks
　　　　　　　　　　　　　　　　随机深度和稠密联结的卷积网络
　　
　　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.

　　讲座人简介：
　　宋士吉: 男，1965年5月生，清华大学自动化系教授、博士生导师。1996年获得哈尔滨工业大学数学博士学位；1996至2000年，在中国海洋大学物理海洋专业、东南大学控制理论与应用专业2次完成博士后研究。
　　长期从事复杂制造系统建模优化与控制技术、机器学习与故障诊断、水下机器人智能控制等方向研究工作。在国内外重要学术期刊会议发表论文200余篇，其中IEEE Transactions 系列期刊长文、国际著名专业期刊SCI检索论文近100篇，担任《IEEE T SMC:Systems》，《中国科学-信息科学》及《自动化学报》等期刊编委，《人工智能与机器人研究》副主编。获得教育部自然科学二等奖励2项，黑龙江生自然科学二等奖1项，江苏省自然科学一等奖1项。
　　主持完成了国家自然科学基金重大科学仪器研制项目、重点项目、面上项目、科技部重点专项、中国大洋协会专项课题等30余项。