Open-World AI and Continual Learning-西安电子科技大学
您当前所在位置: 首页 > 讲座报告 > 正文
讲座报告

Open-World AI and Continual Learning

来源:计算机科学与技术学院‍          点击:
报告人 刘兵 IEEE/AAAI/ACM Fellow 时间 6月19日9:00
地点 北校区图书馆西裙楼2楼报告厅 报告时间

讲座名称Open-World AI and Continual Learning

讲座时间:2020-06-19 9:00

讲座人:刘兵

讲座地点:北校区图书馆西裙楼2楼报告厅


讲座人介绍:

刘兵(Bing Liu),现为美国伊利诺伊大学芝加哥分校(UIC)杰出教授(Distinguished Professor)、北京大学讲席教授(Chair Professor),IEEE Fellow、AAAI Fellow和ACM Fellow。他于1989年获爱丁堡大学人工智能专业博士学位,目前研究领域主要包括:终身机器学习、情感分析、数据挖掘、机器学习和自然语言处理等。以第一作者或通讯作者身份在国际顶级会议/期刊发表了大量学术论文,撰写专著4部,Google Scholar Citation达60000以上。其中2篇论文获得KDD Test-of-Time奖, 1篇论文获WSDM Test-of-Time奖, 1篇论文获WSDM Test-of-Time荣誉奖(Honorable mention)。他的开创性研究工作被媒体广泛报道,包括纽约时报的首页文章,2018年获 ACM SIGKDD创新奖。于2013.7-2017.7年担任数据挖掘领域顶级会议ACM SIGKDD主席,并曾担任多个顶级数据挖掘会议的程序主席,包括KDD,ICDM,CIKM,WSDM,SDM和PAKDD。同时担任多个顶级期刊的副编辑,包括TKDE, TWEB, DMKD和TKDD。现为自然语言处理、人工智能、网络和数据挖掘会议的领域主席或高级程序委员会成员。


讲座内容:

It has become increasingly apparent that it is difficult to build truly intelligent and autonomous systems such as self-driving cars and chatbots that function well in the real-world open environment using models built under the traditional machine learning paradigm. One key reason is that it is impossible to label data to cover all possible cases in the real-world environment, which is dynamic, evolving and full of unknowns. It is necessary for an intelligent system to learn by itself on the job in its interaction with humans and the environment continually, accumulate the learned knowledge, and use it to learn more and to learn better in the future. This general learning capability is one of the hallmarks of the human intelligence. In this talk, I will introduce this emerging machine learning paradigm and discuss some recent work. In the end, I will briefly discuss some issues related to human emotions and feelings and present an attempt to make a chatbot emotional.


主办单位:计算机科学与技术学院

123

南校区地址:陕西省西安市西沣路兴隆段266号

邮编:710126

北校区地址:陕西省西安市太白南路2号

邮编:710071

电话:029-88201000

访问量:

版权所有:西安电子科技大学     陕ICP备05016463号     建设与运维:信息网络技术中心