Home » 27 May 14:00 Samuel Kaski: Proactive interfaces
27 May 14:00 Samuel Kaski: Proactive interfaces
Samuel Kaski, Helsinki University of Technology
Place: *3rd floor meeting room*, Spektri, Pilotti
Time: 14.00-15.00, 27.5.2009
Proactive interfaces try to optimize the choices available to the user while keeping the user in control. I will focus on proactive information retrieval where the ultimate goal is to seamlessly access relevant multimodal information in a context-sensitive way. Usually explicit queries are not available or are insufficient, and the alternative is to try to infer users' interests from implicit feedback signals, such as clickstreams or gaze tracking. We have studied how to infer relevance of texts and images to the user from the gaze patterns. The interests, formulated as an implicit query, can then be used in further searches. I will discuss our recent results in this field, most recently formulating this task as a probabilistic model which can be interpreted as a kind of transfer or meta-learning, and ideas about interfaces.
Samuel Kaski is professor of Computer Science in Helsinki University of Technology, Department of Information and Computer Science. He is vice director of the department and of Adaptive Informatics Research Centre, a national Centre of Excellence, and a group leader in Helsinki Institute for Information Technology HIIT. His research field is statistical machine learning and computational data analysis, current application areas being in bioinformatics, neuroinformatics and proactive interfaces. He has published about 130 peer reviewed articles in these fields.