题目：Explainable Lifelong Streaming Learning
主讲人：Loo Chu Kiong 教授
日期：2023年11月17日（星期五）
时间：上午10:30-11:30
地点：jbo竞博电竞官方网站A101会议室
主持：吴维刚 教授
摘要：
Real-time on-device continual learning applications are used on mobile phones, consumer robots, and smart appliances. Such devices have limited processing and memory storage capabilities, whereas continual learning acquires data over a long period of time. By necessity, lifelong learning algorithms could operate under such constraints while delivering good performance. This study presents the Explainable Lifelong Learning (ExLL) model, which incorporates several important traits: 1) learning to learn, in a single pass, from streaming data with scarce examples and resources; 2) a self-organizing prototype-based architecture that expands as needed and clusters streaming data into separable groups by similarity and preserves data against catastrophic forgetting; 3) an interpretable architecture to convert the clusters into explainable IF-THEN rules as well as to justify model predictions in terms of what is similar and dissimilar to the inference; and 4) inferences at the global and local level using a pairwise decision fusion process to enhance the accuracy of the inference, hence “Glocal Pairwise Fusion.” We compare ExLL against contemporary online learning algorithms for image recognition, using OpenLoris, F-SIOL-310, and Places datasets to evaluate several continual learning scenarios for video streams, low-sample learning, ability to scale, and imbalanced data streams. The algorithms are evaluated for their performance in accuracy, number of parameters, and experiment runtime requirements. ExLL outperforms all algorithms for accuracy in most of the tested scenarios.
个人简介：
Loo Chu Kiong 教授
Prof. Dr. Loo is a full Professor and the Dean of the Faculty of Computer Science & Information Technology, at Universiti Malaya. His research in Lifelong Streaming Learning Explainable AI in robotics and healthcare. He is a recipient of the Georg Forster Fellowship award from Germany, the JSPS Fellowship award from Japan, and the Belt and Road Academic Fellowship Scheme from Hong Kong. He has published more than 200 peer-reviewed journal and conference papers on neurorobotics and machine intelligence. He has been a visiting professor at Tokyo Metropolitan University, University of Prefectural Osaka University, Japan, and King Mongkut's Institute of Technology Ladkrabang, Thailand.
来源：陈樱樱
编辑：谈栩言、吴晓鸿
初审：王冬梅
审核：颜晓辉
审核发布：马啸