报告题目：Data-Knowledge Integrated AI Model for Human-Computer Partnership in Decision Making
报告人：英国阿尔斯特大学刘军教授
报告时间：2022年07月05日（周二）下午19:00
报告地点：腾讯会议（会议号：191-314-692）
主持人：李天瑞教授

报告摘要：
The recent rapid progress in machine learning, particularly deep learning, has led to resurgence in interest in explainable artificial intelligence (XAI). Providing an effective rule-based system is a general trend in XAI and has attracted a lot of attention and researches from different fields in order to support human in judging the quality of the assessment in the decision process, because rule-based systems represent knowledge in terms of rules that tell decision-makers what you should do or what you could conclude in different situations. Compared to all the approaches that use no self-explanatory modeling (black box), the rule-based systems foster the understanding of the underlying problem and the reasons behind intelligent decisions and predictions, i.e., its explanation capability. To make a black-box scheme into a white box is rather challenging. Starting from a white-box system, then try to enhance significantly their performance in terms of accuracy and efficiency without loss of transparency, interpretation and explainability could be an alternative, easier and feasible route in term of XAI. This forms one of the key motivations of our research work. The talk is focused on combining data driven and knowledge driven approaches for making sense to decision support. The key motivation is “making sense” in supporting human decision making, hence the advanced rule-base is centralized in the combination. The talk will introduce the generic framework, methodologies, tools and application of this new combination including some key issues related to data and knowledge representation to compromise each other, process transparency and interpretability, representation scheme and processing capabilities to handle simultaneously vagueness, incompleteness and uncertainty in conjunction with different types of input data formats, performance, flexibility and applicability as well as effectiveness and efficiency.

报告人简介：
Dr Jun Liu is currently a Reader in Computer Science, Director of Artificial Intelligent Research Centre (AIRC), School of Computing, Ulster University, Northern Ireland, UK. He received the BSc. and MSc. degrees in Applied Mathematics, and PhD. degree in Information Engineering from Southwest Jiaotong University, Chengdu, China. He worked in the field of AI for many years. His current research is focused on two themes: 1) data-knowledge integrated AI model/system with applications; 2) logic and automated reasoning methods for intelligent systems. He has authored or co-authored over 230 publications. He has been awarded over £5.5 Million of research funding from various funding bodies as grant holder and principle co-investigator. He serves as an Associate Editor of IEEE Transaction on Fuzzy Systems, Knowledge-Based Systems, Human-Centric Computing and Information Sciences, and International Journal of Computational Intelligence Systems; is also an Editor of Information Fusion Journal, Journal of Universal Computer Science, and International Journal of Knowledge and Systems Science. He is a Senior member of the IEEE including IEEE SMC and IEEE CI, the Member of IEEE CIS Emergent Technologies Technical Committee (ETTC), also the Chair of the IEEE System, Man and Cybernetics (SMC) Ireland Chapter (SMC28). He serves as chairs or co-chairs and program committees of a number of international conferences and workshops. He is a Fellow of the Higher Education Academy, and teaches at both undergraduate and postgraduate level.