Armin Stein

Lunchtime Seminar - Deep Recommendation based on Collective Knowledge

Tuesday, 10. April 2018 - 12:00 to Monday, 24. January 2022 - 20:14, Leo 18, Leonardo-Campus 3, 48149 Münster

Speaker: Prof. Marcin Maleszka

Abstract: Nowadays, we have a huge amount of information overload over Internet. To extract useful information, filtering is required. Search engines help to solve this problem to some extent but they do not deliver customized (personalized) information. Hence, there is a need for effective recommendation tools. This line of investigation leads to our central specific question for the present project. We rephrase Turing’s dictum in the following question. Can recommendation systems think? Answers to this question will have strong implications for the more general issue of whether and how far modern systems mirror our thinking. This observation has motivated us to investigate whether the collective knowledge of the community as a whole could be used to help computer systems extend their intelligent abilities.

Our common project focuses on various learning methods used in generating recommendation models and evaluation metrics used in measuring the quality and performance of recommendation algorithms. This knowledge will empower researchers from both universities and serve as a road map to improve the state of the art recommendation techniques. A combination of different complimentary methods is likely to give a more robust performance to the systems.

Bio: Dr. Marcin Maleszka received his M.Sc. and Ph.D. degrees in Computer Science in 2009 and 2013, respectively. Since 2013 he has been research assistant and since 2015, assistant professor, at Wroclaw University of Science and Technology in Poland. His scientific interests include general knowledge engineering and computational collective intelligence, specifically knowledge integration, dissemination and diffusion, multiagent simulation systems, collaborative approach to recommendation, hybrid intelligent techniques and hierarchical knowledge processing. His current research is focused on understanding integration over time and other knowledge diffusion processes. He has authored over 30 publications, including journal articles in Knowledge Based Systems, Expert Systems with Applications and Cybernetics and Systems, as well as conference papers and book chapters. He has served on programme committees for a number of international conferences in the area of grid computing, collective intelligence, big data, intelligent information and database system. He was an organizing chair or otherwise co-organized several conferences in the International Conference on Computational Collective Intelligence and Asian Conference on Intelligent Information and Database Systems series. He is also a reviewer for several journals, including Neurocomputing and Transactions on Data and Knowledge Engineering. His teaching activities spread from High School level to Graduate level, and included providing High School students possibilities for scientific publications in the multi-agent systems area.