战略网络中的行为实验Behavioral Experiments in Strategic Networks |
|
课程网址: | http://videolectures.net/icwsm2010_kearns_bes/ |
主讲教师: | Michael Kearns |
开课单位: | 宾夕法尼亚大学 |
开课时间: | 2010-06-29 |
课程语种: | 英语 |
中文简介: | 四年来,我们一直在进行“中等规模”的实验,研究人类受试者在战略和经济环境中的行为,这些环境是由潜在的社会网络结构介导的。我们已经探索了广泛的网络,从文学的生成模型中得到启发,以及一系列多样的集体战略问题,包括偏向投票、图形着色、共识和网络交易。这些实验产生了大量关于人类主体如何在战略网络中相互作用的具体发现和新出现的一般主题。卡恩斯将回顾这些发现和主题,强调他们提出的问题比答案更多。迈克尔·卡恩斯是宾夕法尼亚大学的计算机和信息科学教授,他担任国家资源管理和技术中心主席。他是Penn工程公司新市场和社会系统工程(MKSE)项目的创始总监。卡恩斯在沃顿商学院的统计与运营与信息管理(OPIM)部门担任副教授,是宾夕法尼亚大学应用数学与计算科学研究生课程的附属教员。卡恩斯还担任Yodle、Kaching、Invite Media和Kwedit的顾问。他的研究兴趣包括机器学习、算法博弈论、社会网络、计算金融和人工智能。最近,他一直在进行有关社会网络中战略和经济互动的人体实验。1985年,卡恩斯在加州大学伯克利分校获得数学和计算机科学学士学位,1989年在哈佛大学获得计算机科学博士学位。他曾担任NIPS、AAAI、Colt和ACM EC的项目主席。他是NIPS基金会成员和雪鸟学习指导委员会的成员,并在麻省理工学院自适应计算和机器学习系列丛书上服务。 |
课程简介: | For four years now, we have been conducting “medium-scale” experiments in how human subjects behave in strategic and economic settings mediated by an underlying social network structure. We have explored a wide range of networks inspired by generative models from the literature, and a diverse set of collective strategic problems, including biased voting, graph coloring, consensus, and networked trading. These experiments have yielded a wealth of both specific findings and emerging general themes about how populations of human subjects interact in strategic networks. Kearns will review these findings and themes, with an emphasis on the many more questions they raise than answer. Michael Kearns is a professor of computer and information science at the University of Pennsylvania, where he holds the National Center Chair in Resource Management and Technology. He is the founding director of Penn Engineering’s new Market and Social Systems Engineering (MKSE) program. Kearns has secondary appointments in the Statistics and Op erations and Information Management (OPIM) departments of the Wharton School, and is an affiliated faculty member of Penn’s Applied Math and Computational Science graduate program. Kearns also serves as an advisor to Yodle, kaChing, Invite Media, and Kwedit. His research interests include topics in machine learning, algorithmic game theory, social networks, computational finance, and artificial intelligence. Most recently, he has been conducting human-subject experiments on strategic and economic interaction in social networks. Kearns received his B.S in mathematics and computer science from the University of California at Berkeley in 1985, and his Ph.D. in computer science from Harvard University in 1989. He has served as the program chair of NIPS, AAAI, COLT, and ACM EC. He is a member of the NIPS Foundation and the steering committee for the Snowbird Conference on Learning, and serves on the editorial board of The MIT Press series on adaptive computation and machine learning. |
关 键 词: | 机器学习; 算法博弈论; 社会网络; 人工智能 |
课程来源: | 视频讲座网 |
最后编审: | 2021-02-07:nkq |
阅读次数: | 67 |