学院通知
计算机科学技术名家讲座(八)——许东
科研办 发布时间:2018-05-29 15:04  点击:

报告题目胶囊网络及其应用

报告时间201867周四下午1:30-5:30

报告地点:吉林大学南校区计算机大楼A521讲学厅

报告人:  许东教授

Department of Electrical Engineering and Computer Science  

Christopher S. Bond Life Sciences Center

University of Missouri, Columbia, MO, 65201, USA

报告摘要:

To address the problems of scalar neurons, a novel deep-learning architecture, known as Capsule Network (CapsNet) was introduced in 2017. The main building block of CapsNet is the capsule, which is a group of neuron vectors whose lengths represent the entity probabilities. Capsule provides a unique and powerful deep-learning building block to better model the diverse relationships inside internal representations of a neural network. We have applied CapsNet in several applications and achieved improved performance over previous deep-learning methods. In this talk, I will discuss the concept, implementation and applications of CapsNet in details.


主办单位:

吉林大学计算机科学与技术学院

吉林大学软件学院

吉林大学计算机科学技术研究所

符号计算与知识工程教育部重点实验室

海战场攻防对抗仿真技术教育部重点实验室


吉林大学计算机科学与技术学院 版权所有 © 2017

地址:吉林省长春市朝阳区前进大街2699号吉林大学前卫南区计算机楼 邮编:130012