Keynote Speakers
Mr Isidro Laso - European Commission
Prof. Colin Fyfe - University of the West of Scotland
Prof. Xindong Wu - University of Vermont (USA)
Prof. B. Apolloni & S. Bassis - University of Milan (Italy)
Prof. Francisco Herrera - University of Granada (Spain)
Mr Isidro Laso
Scientific Officer - Networked Media Systems Unit.
D.G. Information Society and Media. European Commission.
Talk: The future of Internet and AI - Research Funding Oportunities
Prof. Colin Fyfe
[top]University of the West of Scotland
Talk: Using Bregman Divergences for Exploratory Data Analysis
Abstract: We discuss the family of Bregman divergences and review links between the members of this family and the exponential families of distributions. Specifically we show that certain divergences are optimal for clustering samples from these distributions. We show how these divergences may be used to create topology preserving mappings which optimally capture the manifold on which the data lies. We also apply the divergences to create a Pseudo Metric Multidimensional Scaling which has the happy proprerty (like the Sammon Mapping) of discounting data which are far apart. Finally we show how Bregman divergences can be used to create interesting projections of data streams in which a human can search for structure by eye and extend these methods to dual stream data.
Dr. Colin Fyfe is an active researcher in Artificial Neural Networks, Genetic Algorithms and Artificial Life having written over 300 refereed papers, several book chapters and three books. He referees for most of the major journals in the Neural Networks field (Neural Computation, Neural Networks, Network:Computation in Neural Systems, Neural Processing Letters, IEEE Transactions on Neural Networks etc.). I am Series Co-Editor (with Prof L. Jain) of the series "Computational Intelligence: Theory and Applications" with IGP/INFOSCI/IRM Press. He has acted as Director of Studies for 19 PhDs (all successful) over the last few years: this group is gaining an international reputation.
He is a member of the Academic Advisory Board of the International Computer Science Conventions group and am Chair of the Steering Committee for the conferences Engineering Intelligent Systems. I have acted as Independent Assessor in respect of applications for Professorships in England, USA, Canada, India, Korea and Australia. I am a Committee member of the EU-funded project, EUNITE - the European Network of Excellence on Intelligent Technologies for Smart Adaptive Systems. I am on the Scientific Panel of Incite, a SHEFC-funded joint venture initiated by the universities of Paisley, Edinburgh and Stirling to facilitate technology transfer. He is on the Steering Committee of the EPSRC-funded "Blind Source Separation and Independent Component Analysis Research Network". He is a member of the WSEAS International Working Group on Data Mining, and a member of the Microsoft Silicon Minds academic committee.
He was a Scientific Collaborator for NASA project "Precision Mining of Large Spectral Data Volumes for Rapid Identification of Planetary Resources" (University of Arizona) and for a Scottish Enterprise project on intelligent project management.
Prof. Xindong Wu
University of Vermont (USA)
Talk: Pattern Matching and Mining with Wildcards
Abstract: This talk starts with a challenging problem of pattern matching with wildcards and length constraints, and presents our current research efforts towards both matching and mining on this challenging problem. For the matching component, the user can specify constraints on the number of wildcards between each two consecutive letters of a given pattern and the constraints on the length of each matching substring. We have developed an efficient algorithm to return each pattern occurrence in an on-line manner. For the mining component, we have developed a heuristic method that can automatically and efficiently find patterns with wildcards without the necessity of user-specified gap constraints. This research has been supported by both the U.S. National Natural Science Foundation (NSF) and the National Natural Science Foundation of China (NSFC).
Prof. B. Apolloni & S. Bassis
University of Milan (Italy)
Talk: Compatible worlds
Abstract: We discuss a bridge way of inference between Agnostic Learning and Prior Knowledge based on an inference goal represented not by the attainment of truth but simply by a suitable organization of the knowledge we have accumulated on the observed data. In a framework where this knowledge is not definite, we smear it across a series of possible models that we characterize through a probability measure of effectively explaining the observed data which denotes their compatibility with them. We point out the main features and benefits of our approach w.r.t.\ the two direct competitors: namely, the frequentist and Bayesian approaches, representative respectively of agnostic and a priori knowledge paradigms. Then we explore in greater depth its implementation for learning Boolean functions, showing an unprecedented relation between complexity of the concept class to be learnt and some peculiarities of the features through which the inference problem is represented.
Bruno Apolloni is full professor in Computer Science at the Department of Computer Science of the Milan University, Italy.
His main research interests are in the frontier area between probability, mathematical statistics and computer science, with special regard to statistical bases of learning, subsymbolic and symbolic learning processes, granular computing, and modeling of dynamical processes in biology. He introduced the Algorithmic Inference approach in statistics as a conceptual and methodological tool to solve modern computational learning problems with the massive use of computers. In particular, it provides a unifying theoretical framework to the various data analysis and management disciplines converging under the granular computing heading. He also introduced some non-markovian processes to model intentionality in a wide range of biological systems ranging from bacteria colonies to social communities.
Apolloni is head of the Neural Networks Research Laboratory (LAREN, http://laren.dsi.unimi.it) of the department of Computer Science of the University of Milan, past President of the Italian Society for Neural Networks (SIREN, http://siren.dsi.unimi.it), and member of the Internationa Neural Network Society board. He is a member of the editorial board of the many journals, among which: Neural Networks, Neurocomputing, International Journal of Hybrid Intelligent Systems, International Journal of Information and Communication Technology and International Journal of Computational Intelligence Studies.
Prof. Francisco Herrera
University of Granada (Spain)
Talk: Subgroup Discovery: Foundations and Applications.
Abstract: The problem of subgroup discovery which can be defined as: Given a population of individuals and a property of those individuals, we are interested in finding a population of subgroups as large as possible and in having the most unusual statistical characteristic with respect to
the property of interest. Subgroup discovery is well suited for finding such dependencies, i.e., discovering relations between a dependent variable (target variable) and (several) independent variables. The discovered subgroup patterns must essentially satisfy two conditions.
First, they have to be interpretable for the analyst, and second they
need to be interesting according to the criteria of the user. The
discovery of (interesting) subgroups has a high practical relevance in
all domains of science or business.
This talk presents the foundations of subgroup discovery and some applications.
Francisco Herrera received the M.Sc. degree in Mathematics in 1988 and the Ph.D. degree in Mathematics in 1991, both from the University of Granada, Spain.
He is currently a Professor in the Department of Computer Science and Artificial Intelligence at the University of Granada. He has published more than 150 papers in international journals. He is coauthor of the book “Genetic Fuzzy Systems: Evolutionary Tuning and Learning of Fuzzy Knowledge Bases" (World Scientific, 2001).
As edited activities, he has co-edited five international books and co-edited twenty special issues in international journals on different Soft Computing topics. He acts as associated editor of the journals: IEEE Transactions on Fuzzy Systesms, Mathware and Soft Computing, Advances in Fuzzy Systems, Advances in Computational Sciences and Technology, and International Journal of Applied Metaheuristic Computing. He currently serves as area editor of the Journal Soft Computing (area of genetic algorithms and genetic fuzzy systems), and he serves as member of the editorial board of the journals: Fuzzy Sets and Systems, Applied Intelligence, Knowledge and Information Systems, Information Fusion, Evolutionary Intelligence, International Journal of Hybrid Intelligent Systems, Memetic Computation, International Journal of Computational Intelligence Research, The Open Cybernetics and Systemics Journal, Recent Patents on Computer Science, Journal of Advanced Research in Fuzzy and Uncertain Systems, International Journal of Information Technology and Intelligent and Computing, and Journal of Artificial Intelligence and Soft Computing Research.
His current research interests include computing with words and decision making, data mining, data preparation, instance selection, fuzzy rule based systems, genetic fuzzy systems, knowledge extraction based on evolutionary algorithms, memetic algorithms and genetic algorithms.
Further details on keynote talks will appear shortly