Title: Explainable AI and Operations Research:From Data to Symbols and Information Granules

Abstract:

With the vast amounts of data, one needs to resort herself to engaging abstract entities in order to cope with complexity of the real-world problems and transparency of solutions. All of those factors give rise to a recently pursued discipline of explainable AI. From the dawn of AI, symbols and ensuing symbolic process have assumed a central position and ways of symbol grounding become of interest. We advocate that in the realization of these two timely pursuits, information granules and Granular Computing play a significant role. In both cases, central to all pursuits is a process of formation of information granules and their prudent characterization. We discuss a comprehensive approach to the development of information granules by means of the principle of justifiable granularity. Here various construction scenarios are discussed including those engaging conditioning and collaborative mechanisms incorporated in the design of information granules. The mechanisms of assessing the quality of granules are presented. In the sequel, we look at the generative and discriminative aspects of information granules supporting their further usage in the AI constructs. A symbolic manifestation of information granules is put forward and analyzed from the perspective of semantically sound descriptors of data and relationships among data.

Lecturer: Roman Słowiński

Date/Time: 11:00 – 11:50AM, 14 Dec, 2019

Location: Room A0305, CEM Building, Jiangjun Rd. Campus

Brief introduction of the lecturer:

Witold Pedrycz is the Chair Professor of University of Alberta, Academician of the Royal Canadian Academy of Sciences, foreign Academician of the Polish Academy of Sciences, Chair of the Canadian Computing Intelligence Research Center, and Fellow of the International Electrical and Electronics Engineer Association. He is also the editor of plenty of journals, including0 Information Sciences, WIREs Data Mining and Knowledge Discovery and Granular Computing. He has published 18 monographs, H index 109, Total cites 63568.