Towards Machines that Learn like Humans

演讲者: Prof. Bing Liu University of Illinois at Chicago

时间:2017-12-25 13:30-15:00

地点: 106 Lecture Hall, Institute of computer science & technology of Peking University

Abstract:    The classic machine learning (ML) paradigm works by learning a model from a set of training examples without considering any other information. Although this paradigm has been very successful, it requires a large volume of labeled data and a huge amount of human labeling effort, and it is only suitable for well-defined, static, and narrow domains. As we go forward, this kind of isolated learning will no longer be sufficient. For example, it is almost impossible for humans to provide labeled data or supervised information for all possible scenarios faced by chatbots and self-driving cars. Such systems must learn continuously on the job, retain the knowledge learned in the past, and use it help future learning. When faced with an unfamiliar situation, it needs to adapt its past knowledge to deal with the situation and to learn from it. This general learning capability is one of the hallmarks of the human intelligence. Lifelong learning (LL) is an area of study that aims to achieve this learning capability on machines. In this talk, I will discuss some of our recent work on LL and its applications in NLP.   

Biography:    Bing Liu is a distinguished professor of Computer Science at the University of Illinois at Chicago. He received his Ph.D. in Artificial Intelligence from the University of Edinburgh. His research interests include sentiment analysis, lifelong learning, data mining, machine learning, and natural language processing (NLP). He has published extensively in top conferences and journals. Two of his papers have received 10-year Test-of-Time awards from KDD. He also authored four books: two on sentiment analysis, one on lifelong learning, and one on Web mining. Some of his work has been widely reported in the press, including a front-page article in the New York Times. On professional services, he served as the Chair of ACM SIGKDD (ACM Special Interest Group on Knowledge Discovery and Data Mining) from 2013-2017. He also served as program chair of many leading data mining conferences, including KDD, ICDM, CIKM, WSDM, SDM, and PAKDD, as associate editor of leading journals such as TKDE, TWEB, DMKD and TKDD, and as area chair or senior PC member of numerous NLP, AI, Web, and data mining conferences. He is a Fellow of ACM, AAAI and IEEE.