HIIT - Videos & webcasts

PUPS-IT video

noronen — Fri, 15 Aug 2008 11:00:13 +0000

PUPS-IT video demonstrates use of virtual post-it notes. The application has been made as a demonstration for the project Personalised Ubiservices in Public Spaces (PUPS), a Tekes Ubicom project.

Duration: 2:04
Recorded: Summer 2008

Video (edited)
www.hiit.fi/~mjmander/video/Pups-it.mov

Banner:

helsinki1.jpg

Videos & webcasts:

Videos & webcasts

Learning to Learn Implicit Queries from Gaze Patterns

noronen — Fri, 08 Aug 2008 13:38:57 +0000

A video lecture by Kai Puolamäki: In the absence of explicit queries, an alternative is to try to infer users' interests from implicit feedback signals, such as clickstreams or eye tracking. The interests, formulated as an implicit query, can then be used in further searches. We formulate this task as a probabilistic model, which can be interpreted as a kind of transfer learning and meta-learning. The probabilistic model is demonstrated to outperform an earlier kernel-based method in a small-scale information retrieval task.

Duration: 20:04
Recorded: The 25th International Conference on Machine Learning (ICML 2008), Helsinki, July 08

Webcast with integrated slide show
Videolectures.net »

Banner:

helsinki1.jpg

Videos & webcasts:

Videos & webcasts

Causal Modelling Combining Instantaneous and Lagged Effects: an Identifiable Model Based on Non-Gaussianity

noronen — Fri, 08 Aug 2008 13:33:01 +0000

A video lecture by Aapo Hyvärinen: Causal analysis of continuous-valued variables typically uses either autoregressive models or linear Gaussian Bayesian networks with instantaneous effects. Estimation of Gaussian Bayesian networks poses serious identifiability problems, which is why it was recently proposed to use non-Gaussian models. Here, we show how to combine the non-Gaussian instantaneous model with autoregressive models. We show that such a non-Gaussian model is identifiable without prior knowledge of network structure, and we propose an estimation method shown to be consistent. This approach also points out how neglecting instantaneous effects can lead to completely wrong estimates of the autoregressive coefficients.

Duration: 24:36
Recorded: The 25th International Conference on Machine Learning (ICML 2008) , Helsinki, July 08

Webcast with integrated slide show
Videolectures.net »

Banner:

helsinki1.jpg

Videos & webcasts:

Videos & webcasts

Virtual Economies Seminar

noronen — Fri, 06 Jun 2008 11:26:55 +0000

The AVEA project at the Helsinki Institute for Information Technology HIIT organized an open research seminar on so-called virtual economies. We focused on the following question: "Why should economists and social scientists be interested in virtual economies?" Through discussion and presentations by academic researchers and industry representatives, we investigated the potential of conducting quantitative research on virtual economies that is of interest to mainstream, "serious" researchers.

Duration: 2:15
Recorded: 2 June 08 at 9.45 EET (GMT+3)

Webcast (unedited)
Part 1 (RealMedia) »
Part 2 (RealMedia) »
Part 1-2 (QuickTime) »

Banner:

helsinki1.jpg

Videos & webcasts:

Videos & webcasts

CityWall

noronen — Fri, 31 Aug 2007 21:00:00 +0000

The CityWall is a large mutli-touch display installed in a central location in Helsinki which acts as a collaborative and playful interface for the everchanging media landscape of the city.

Duration: 2:54
Recorded: June 07

Video (edited)
Youtube »

Banner:

helsinki1.jpg

Videos & webcasts:

Videos & webcasts

BulkFS: a Distributed Fault-Tolerant File System for Massive Data Applications

noronen — Sat, 08 Jul 2006 10:41:24 +0000

A video lecture on: Tuominen, A.; V. Tuulos, V.: BulkFS: a Distributed Fault-Tolerant File System for Massive Data Application. In Book of Abstracts of the International Workshop on Intelligent Information Access (IIIA-2006), Helsinki, FInland, July 2006.

Duration: 27:27
Recorded: International Workshop on Intelligent Information Access IIA-2006, 6 - 8 July 2006, Helsinki

Webcast with integrated slide show
Videolectures.net »

Banner:

helsinki1.jpg

Videos & webcasts:

Videos & webcasts

User Models from Implicit Feedback for Proactive Information Retrieval

noronen — Sun, 05 Jun 2005 21:00:00 +0000

A video lecture by Samuel Kaski: Our research consortium develops user modeling methods for proactive applications. In this project we use machine learning methods for predicting users’ preferences from implicit relevance feedback. Our prototype application is information retrieval, where the feedback signal is measured from eye movements or user’s behavior. Relevance of a read text is extracted from the feedback signal with models learned from a collected data set. Since it is hard to define relevance in general, we have constructed an experimental setting where relevance is known a priori.

Duration: 18:44
Recorded:

Workshop on Machine Learning for User Modeling: Challenges (10th International Conference on User Modeling, UM05), Edinburgh, UK

Webcast with integrated slide show
Videolectures.net »

Banner:

helsinki1.jpg

Videos & webcasts:

Videos & webcasts