Keynote Speaker

description here

CITEC Centre of Excellence,
Bielefeld University, Germany

Structure metric learning in prototype-based models and its application for intelligent tutoring

Prototype-based learning techniques enjoy a wide popularity due to their intuitive training and model interpretability. Applications include biomedical data analysis, image classification, or fault detection in technical systems. Recently, first promising attempts incorporate such models into the domain of intelligent tutoring systems (ITS): in a nutshell, ITSs provide automated, personalised feedback to learners when performing some learning task such as learning how to program. Here a challenge is to avoid time-consuming expert generation of how to provide such feedback; machine learning technology offers promising ways to automate this process, specifically, prototype-based methods enable an automatic feedback generation by highlighting prototype solutions given a learner solution. This strategy relies on the core property of such models that they represent data in terms of typical representatives. Within the talk, we will mainly focus on modern variants of so-called learning vector quantization (LVQ) due to their strong learning theoretical background and exact mathematical derivative from explicit cost functions.

The use of LVQ in ITSs faces two challenges: 1) Data are typically non-vectorial, e.g. structured data such as sequences are present; since classical LVQ models have been designed for euclidean vectors only, the question is how to extend LVQ technology towards non-vectorial data. We will present relational extensions of LVQ technology which enable its use for proximity data as provided by structure metrics such as alignment in a very generic way. 2) Structure metrics crucially depend on model parameters such as the scoring function, and their optimum choice is not clear. Still, the accuracy of such models crucially depends on a correct choice of these metric parameters.
We will present recent results which allow to adjust structure metric parameters autonomously based on the given data and learning task only.

Biography: Barbara Hammer received her Ph.D. in Computer Science in 1995 and her venia legendi in Computer Science in 2003, both from the University of Osnabrueck, Germany. From 2000-2004, she was  chair of the junior research group ‘Learning with Neural Methods on Structured Data’ at University of Osnabrueck before accepting an offer as professor for Theoretical Computer Science at Clausthal University of Technology, Germany, in 2004. Since 2010, she is holding a professorship for Theoretical Computer Science for Cognitive Systems at the CITEC cluster of excellence at Bielefeld University, Germany. Several research stays have taken her to Italy, U.K., India, France, the Netherlands, and the U.S.A. Her areas of expertise include hybrid systems, self-organizing maps, clustering, and recurrent networks as well as applications in bioinformatics, industrial process monitoring, or cognitive science. She has been chairing the IEEE CIS Technical Committee on Data Mining in 2013 and 2014, and she is chair of the Fachgruppe  Neural Networks of the GI and vice-chair of the GNNS. She has published  more than 200 contributions to international conferences / journals, and she is coauthor/editor of four books.