Multi-Task Preference Learning with Gaussian Processes


Tom Heskes
Tom Heskes
  • Speaker
Faculty of Science, Radboud University Nijmegen

Event Information

Type
Research Seminar
Programme
Information Management
Date
Wed. 23 May. 2012
Contact
Time
15:00-16:30 hours
E-mail
Location
Mandeville Building T3-42
Number


Abstract

Preference learning is concerned with the acquisition of preference models from data – it involves learning from observations that reveal information about the preferences of an individual or a class of individuals, and building models that generalize beyond such training data. In many cases, data for a single individual is scarce, and it pays to build a hierarchical model of preferences, where models for individuals share a common prior. This setting is referred to as multi-task learning. In particular, we here consider the application of multi-task Gaussian processes to the learning of preferences, where each of the models for individual subjects is a nonparametric Gaussian process. We demonstrate the usefulness of our approach on an audiological data set.
About Dr. Tom Heskes
Dr. Tom Heskes is a Professor in Artificial Intelligence, and he leads the Machine Learning Group, at the Institute for Computing and Information Sciences, Radboud University Nijmegen. His research is on probabilistic methods for machine learning and artificial intelligence, with applications in, among others, neuroscience and bioinformatics. He is a Vici laureate and Editor-in-Chief of Neurocomputing.
Contact information:
Dr. Wolf Ketter
Email
Wolfgang Ketter
Professor of Next Generation Information Systems
  • Coordinator