Lifelong Learning: Building Machines That Learn Like Humans
Lifelong learning (LL) is a machine learning (ML) paradigm that learns continuously, accumulates the knowledge learned in the past, and uses/adapts it to help future learning and problem solving. In the process, the learner becomes more and more knowledgeable and better and better at learning. This continuous learning ability is one of the hallmarks of human intelligence. However, the classic ML paradigm learns in isolation: given a training dataset, it runs a ML algorithm only on the dataset to produce a model. It makes no attempt to retain the learned knowledge and use it in subsequent learning. Although this isolated ML paradigm, primarily based on data-driven optimization, has been very successful, it requires a large amount of training data, and is only suitable for well-defined and narrow tasks in closed environments. In contrast, we humans learn effectively with a few examples and in the open world because our learning is also very much knowledge-driven: the knowledge learned in the past helps us learn new things with little data or effort and adapt to new/unseen situations. LL aims to achieve this capability and to build lifelong learning machines. Applications such as chatbots, self-driving cars, or any AI systems that interact with real-world environments are calling for this capability because they need to face the dynamic and open world which leaves them with no choice but to learn new things continuously in order to function well. In this talk, I will introduce this emerging ML paradigm, discuss some of our recent work, and speculate on how to build machines that learn like humans.
About the speaker:
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, natural language processing (NLP), data mining, machine learning, and Artificial Intelligence (AI). He has published extensively in top conferences and journals. Two of his papers received Test-of-Time awards from SIGKDD (ACM Special Interest Group on Knowledge Discovery and Data Mining). He is also a recipient of ACM SIGKDD Innovation Award (the most prestigious technical award from SIGKDD). He has 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 international press, including a front-page article in the New York Times. On professional services, he has served as the chair of ACM SIGKDD, 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 the ACM, AAAI, and IEEE.