Helsinki ICT Research Events

Abstract: Despite significant advances in omics techniques, the identification of genes causing rare genetic diseases and the understanding of the molecular networks underlying those disorders remains difficult. Gene prioritization attempts to integrate multiple, heterogeneous data sources to identify candidate genes most likely to be associated with or causative for a disorder. Such strategies are useful...

Prof. Brian Roark, Oregon Health & Science University, USA

Discriminative language modeling methods learn language model parameterizations from system outputs when applied to training data, by optimizing objective functions close to actual system objectives via algorithms such as the perceptron. Thus, for speech recognition, training data utterances are recognized with a baseline recognizer, and the...

M.Sc. Sami Virpioja will defend his doctoral dissertation Learning Constructions of Natural Language: Statistical Models and Evaluations on 10 December 2012 in lecture hall TU1 (TUAS building). The opponents are Prof. Brian Roark, Oregon Health & Science University, USA and Docent Krister Lindén, University of Helsinki. The custodian is Prof. Erkki Oja.

Announcement (fi, pdf)

Elias Weingärtner from RWTH Aachen will give a guest lecture on Tuesday 4.12. 14:15-15:00 in Exactum B120. The title of the lecture is "SliceTime: Enhancing the Applicability of Network Emulation". The SliceTime system was published in the prestigious NSDI conference in 2011. Elias is finalizing his doctoral dissertation this year.

The...

Abstract: In this talk, I will discuss a shortest path finding perspective for learning Bayesian network structures that optimize a scoring function for given data. The main idea is to formulate the problem as finding a shortest path in an implicit state-space search graph. This new formulation raises two orthogonal research issues: the development of search strategies for solving the shortest path finding...

M.Sc. Lauri Ahlroth will defend his doctoral dissertation Online Algorithms in Resource Management and Constraint Satisfaction on 30 November 2012 in lecture hall T2 (Computer Science building). The opponent is Prof. Gerhard Woeginger, Eindhoven University of Technology, The Netherlands. The custodian is Prof. Pekka Orponen.

Announcement (pdf, fi)

Hannes Schulz, University of Bonn, Germany

Unsupervised learning of feature hierarchies is often a good initialization for supervised training of deep architectures. In existing deep learning methods these feature hierarchies are built layer by layer in a greedy fashion using auto-encoders or restricted Boltzmann machines. Both yield encoders which compute linear projections followed by a smooth thresholding function. In this work...

Abstract:  Unsupervised learning of feature hierarchies is often a good initialization for supervised training of deep architectures.  In existing deep learning methods these feature hierarchies are built layer by layer in a greedy fashion using auto-encoders or restricted Boltzmann machines.  Both yield encoders which compute linear projections followed by a smooth thresholding function....