Prof Yukio Ohsawa
University of Tokyo, JapanBeyond Explainable Learning to Explanatory Intelligence
- A Systems Innovation Approach on Data Jackets -
Abstract:
The recent endeavors of researchers in artificial intelligence for explainable machine learning imply users still suffer the difficulty in understanding what/how the machine learned. The tools with AI for making the real world dealable may rather make things unclear for humans, and the decisions of humans nowadays may be rather influenced by incomprehensible logic. On the other hand, an important role of AI is to explain events and changes -- which may affect a human's life and why that happened and affects. In this talk, the speaker talks about the requirements of participants so far in the data marketplace organized using Data Jackets, to reveal participants' desire to computational intelligence for explaining events or changes. This is intended to go quite beyond the scope of learning from available data, toward the development of methods for human-machine interaction to reach the latent causalities involving events out of available or in unreachable data.
Biography:
Yukio Ohsawa is a professor of Systems Innovation in the School of Engineering. He received BE, ME, and PhD from the School of Engineering, The University of Tokyo (1995). Then worked for the School of Engineering Science at Osaka University (research associate, 1995-1999), Graduate School of Business Sciences at University of Tsukuba (associate professor, 1999-2005), and moved back to The Univ. of Tokyo. He started researches from non-linear optics, and, via artificial intelligence, created a new domain chance discovery meaning to discover events of significant impact on decision making, since year 2000. About chance discovery he gave keynote talks in conferences, e.g., Knowledge-Based Intelligent Information and Engineering Systems, International Symposium on Knowledge and Systems Sciences, Int'l Conf. on Rough Sets and Fuzzy Sets, Joint Conf. on Information Sciences, etc. Chance discovery came to be embodied as innovators' marketplace, a methodology for innovation borrowing principles of the dynamics of markets. Then he, when biking from his job in a business school, invented the basic idea of Data Jackets as a new tool for enhancing chance discoveries via combining data from various data owners. Since then, he is introducing the method presented in this book to sciences, educations, and businesses. His original concepts and technologies have been published as books and monographs from global publishers such as Springer Verlag, Taylor & Francis, etc. Four of the most important books among them, for this talk, are "Chance Discovery" (2003 Springer, foreword given by Eric von Hippel), "Innovators' Marketplace: Using Games to Activate and Train Innovators" (2012 Springer, foreword given by Larry Leifer), and "Living Beyong Data" (Springer) and "Tools for Activating Data Marketplace" (Springer) being now edited by the speaker and his co-editor. Also, he edited special issues as guest editors for journals, mainly relevant to chance discovery, such as Intelligent Decision Technologies (2016), Information Sciences (2009), New Generation Computing (2003), Journal of Contingencies and Crisis Management (2002), etc. As the program chair of the Annual Conference of The Japanese Society on Artificial Intelligence, he is the first to change this domestic conference into an international conference from June 2019. He is also in the editorial board of Information, The Review of Socionetwork Strategies, International Journal of Computer Information Systems and Industrial Management Applications, etc., and is an academic member of KES Focus Group on Intelligent Decision Technologies.
Back to Keynote Speakers