DEMO Se­mi­nar: Data, Mac­hi­ne Lear­ning and Deci­sion Ma­king


18.12.2018 10:15 — 14:00

Location: Mattilanniemi, Agora, Ag C 132
Welcome to the DEMO seminar on different aspects of Decision Analytics! DEMO (Decision Analytics utilizing Causal Models and Multiobjective Optimization) is a profiling area of the University of Jyväskylä focusing on different elements of data-driven decision support, http://www.jyu.fi/demo. This seminar is aimed at all those who are interested in using data in different ways in decision making.

In this seminar, distinguished professors of the International Advisory Board of DEMO will present their data-related research. Some activities of DEMO will also be briefly described.

You are most welcome to hear more about how to make the most of the data and maybe bring collaboration ideas with you.

 Seminar program:

 10.15 Prof. Jian-Bo Yang (Decision and Cognitive Sciences Research Centre, Alliance Manchester Business School, The University of Manchester): Interpretable Machine Learning and Decision Making via Evidential Reasoning 

11.15 Brief introduction to DEMO

11.45 Lunch (free for those who register on time) 

12.30 Prof. Bülent Yener (Department of Computer Science, Data Science Research Center, Rensselaer Polytechnic Institute, Troy, New York): Learning from Complex Data 



If you can attend, please register at https://link.webropolsurveys.com/S/F92F62A7CD3A6D1F by December 11 and indicate your dietary restrictions (if any). 

You are warmly welcome! 

See abstracts and brief bios of the speakers below.


Interpretable Machine Learning and Decision Making via Evidential Reasoning

Professor Jian-Bo Yang, jian-bo.yang@manchester.ac.uk

Decision and Cognitive Sciences Research Centre, Alliance Manchester Business School, The University of Manchester, Manchester M13 9SS, United Kingdom

Abstract: In this presentation, we discuss the necessity of using both data and human judgments for scientific inference, intelligent modeling, and evidence-based decision making under uncertainty in business, management and engineering systems. The focus is on the analysis of uncertainty in data and judgments and how to model various types of uncertainty in an integrated framework including randomness, ambiguity, inaccuracy and inconsistency. In particular, the paradigm of evidential reasoning (ER) will be introduced as an extension to Bayesian inference and conventional rule based system modeling. In this presentation, a short overview of the ER developments as inspired by real word applications in a wide range of areas will be provided first, from ER multiple criteria assessment (MCA) and decision making (MCDM) under uncertainty, to the ER rule for information fusion and a new maximum likelihood ER (MAKER) framework for big data analytics, probabilistic inference and machine learning, and to the belief rule-base inference methodology using the evidential reasoning approach (RIMER) or belief rule-base (BRB) methodology in short for intelligent modeling and knowledge-based systems. The details of the ER approach for MCA and MCDM, the RIMER/BRB methodology for universal nonlinear system modeling and the ER rule and MAKER framework for information fusion, probabilistic inference with data and machine learning will be discussed with real world applications conducted by the researcher and his collaborators who have worked and made main contributions in these areas for years. The key software packages with application examples that has been developed by the researcher and his colleagues over many years will be demonstrated. 

Bio: Dr Jian-Bo Yang is Chair Professor of Decision and Systems Sciences and Director of the Decision and Cognitive Sciences Research Centre at The University of Manchester, UK. He is also Changjian Chair Professor specially appointed by the Education Ministry of China. In the past three decades, He has conducted research in the areas of multiple criteria decision analysis using both quantitative and qualitative information under uncertainties, probabilistic inference and decision making with data and judgments, complex system modeling, multiple objective optimisation and simulation or interpretable machine learning, hybrid decision methodologies combining techniques from systems theory, operational research and artificial intelligence, etc. The current application areas cover data-driven diagnosis and prognosis, design and operation decision making in healthcare and engineering systems, pattern identification and analysis of customer behaviours, public sentiments and system risks (financial or non-financial) from big data, new product development, aggregated production management, system maintenance management, risk and security modelling and analysis, performance analysis and improvement of products, processes and organizations, among others. He has been awarded research grants at the total value of over £5m by EPSRC, EC, DEFRA, SERC, HKRGC, NSFC and industry. He has published 4 books, over 200 journal papers and book chapters, and a similar number of conference papers, with high citations in Web of Science and Google Scholar, and developed several software packages in optimisation and decision making with wide applications.

* **

Learning from Complex Data 

Professor Bülent Yener

Department of Computer Science, Data Science Research Center, Rensselaer Polytechnic Institute (RPI), Troy, New York 

Abstract: Complex data is characterized by volume, rate, modality, noise, and heterogeneity. Learning the structure hidden in complex structures and their functional states requires extracting right features, and it is crucial for our understanding of the structure-function relationship.

In this talk we present novel techniques that are pipelined for modeling complex systems and predicting their behavior. Our discussion focuses on biomedical applications ranging from automated histopathology for cancer diagnosis to branching morphogenesis for organ development. 

We conclude by reviewing additional machine learning projects focusing on cybersecurity in our group. 

Bio: Bülent Yener is a Professor in the Department of Computer Science and the founding Director of Data Science Research Center at Rensselaer Polytechnic Institute (RPI) in Troy, New York.  Dr. Yener received his MS. and Ph.D. degrees in Computer Science, both from Columbia University, in 1987 and 1994, respectively. Before joining RPI, he was a Member of the Technical Staff at the Bell Laboratories in Murray Hill, NJ. He is a senior member of ACM and a Fellow of IEEE. 

More information

Kaisa Miettinen