HIIT - kumpula1.jpg

Break in shell.hiit.fi at 2017-11-10 11:10 - 11:20

pmtonter — Fri, 10 Nov 2017 09:10:00 +0000

Schedule:

2017-11-10 11:10 to 11:20

Duration:

10 min

Affected services:

shell.hiit.fi

Description:

General purpose GNU/Linux server shell.hiit.fi will be rebooted due to kernel upgrade. All other pending updates will be installed as well.

Intelligent Interactive Information Access (INTENT)

floreen — Mon, 22 Jun 2015 10:07:51 +0000

Overview

The INTENT research subgroup of CoSCo focuses on intelligent access to personal data repositories, proactive and exploratory information retrieval, and ubiquitous and context-aware computing.

A summer job offer appared here. The application deadline has passed and the student for this was selected.

Team

Docent Patrik Floréen (Subgroup Leader, Principal Investigator)

Alumni

PhD Dorota Glowacka, now at University of Edinburgh.
Research assistant Ada-Maaria Hyvärinen
PhD (Tech.) Markus Koskela, now at CSC - IT Center for Science
MSc Petri Luukkonen
PhD (Tech.) Mats Sjöberg, now at Aalto University.

Multi-source Probabilistic Inference

aklami — Tue, 21 Jan 2014 08:02:11 +0000

The Multi-source Probabilistic Inference group develops probabilistic machine learning models and inference techniques for analyzing and understanding complex heterogeneous data collections. For most data analysis tasks it is beneficial to jointly analyze all available data, but often the different data sources are not directly commensurable. For example, a data scientist studying demographics of a neighborhood might have static spatial information about the buildings, dynamic group-level information on public transportation, large collections of time-stamped and user-specific social media content both as text as images, and perhaps even some interview questionnaires. All of these sources provide information on the demographics, but standard modeling tools do not help much in providing an overall picture.

The goal of this research group is to overcome the theoretical and practical challenges needed for integrating such heterogeneous data sources, by building statistical models for various types of data and especially hierarchical models for joint analysis of them even in cases where there are no obvious ways of linking the sources with each other. We also develop statistical machine learning methods in more general, focusing on computationally efficient approximative inference, transfer learning, domain adaptation, and other techniques crucial for learning complex models (including deep neural networks) from limited data collections.

The group is part of Finnisch Center for Artificial Intelligence (FCAI).

Open positions

There are currently no open calls, but we are constantly looking for talented postdoctoral researchers and PhD students to join the group. For both levels we consider both candidates with existing machine learning research track and those switching from other computational fields (physics, statistics, mathematics, economics, ...) towards machine learning and artificial intelligence. Contact the group leader by email if interested.

Research themes

Multi-view learning, data integration, cross-domain object matching
Approximative Bayesian inference; MCMC, variational approximation
Nonparametric Bayesian modeling
Scalable probabilistic models, probabilistic programming

Projects

Traces of Information: Intelligence from fragmented data (Academy of Finland, 2013-2019)
RAB-ML: Robust Automatic Bayesian Machine Learning (Academy of Finland, 2018-2019, with Aki Vehtari and Antti Honkela)
SPA: Scalable Probabilistic Analytics (Tekes, 2016-2018, with Petri Myllymäki and Teemu Roos)
ILCIS: Improved Learning by Combining Information Sources (Xerox Foundation, 2013-2015)

People

Arto Klami, PhD, Assistant Professor, Academy Research Fellow
Aditya Jitta, Doctoral student
Joseph Sakaya, Doctoral student
Jarkko Lagus, Doctoral student
Krista Longi, Doctoral student
Chang Rajani, Research assistant

Alumni (MSc+)

Liye He, MSc
Johannes Sirola, MSc

Selected recent publications

Semi-supervised convolutional neural networks for identifying Wi-Fi interference sources. Krista Longi, Teemu Pulkkinen and Arto Klami. In Proceedings of Asian Conference on Machine Learning (ACML), 2017. [pdf]
Importance sampled stochastic optimization for variational inference. Joseph Sakaya and Arto Klami. In Proceedings of Uncertainty in Artificial Intelligence (UAI), 2017. [pdf, code]
Partially hidden Markov models for privacy-preserving modeling of indoor trajectories. Aditya Jitta and Arto Klami. Neurocomputing, 2017. [doi]
Probabilistic size-constrained microclustering. Arto Klami and Aditya Jitta. In Proceedings of Uncertainty in Artificial Intelligence (UAI), 2016. [pdf]
Using regression makes extraction of shared variation in multiple datasets easy. Jussi Korpela, Andreas Henelius, Lauri Ahonen, Arto Klami, and Kai Puolamäki. Data Mining and Knowledge Discovery, 2016. [html]
Towards brain-activity-controlled information retrieval: Decoding image relevance from MEG signals. Jukka-Pekka Kauppi, Melih Kandemir, Veli-Matti Saarinen, Lotta Hirvenkari, Lauri Parkkonen, Arto Klami, Riitta Hari, and Samuel Kaski. Neuroimage, 2015. [doi]
Group factor analysis. Arto Klami, Seppo Virtanen, Eemeli Leppäaho, and Samuel Kaski. IEEE Transactions in Neural Networks and Learning Systems, 2015. [preprint]
Latent-feature regression for multivariate count data. Arto Klami, Johannes Sirola, Lauri Väre, Abhishek Tripathi, and Frederic Roulland. In Proceedings of Artificial Intelligence and Statistics, 2015. [pdf]
Group-sparse embeddings in collective matrix factorization. Arto Klami, Guillaume Bouchard, and Abhishek Tripathi. In Proceedings of International Conference on Learning Representations, 2014. [http://arxiv.org/abs/1312.5921]
Bayesian object matching. Arto Klami. Machine Learning, 92(2):225-250, 2013. [doi:10.1007/s10994-013-5357-4, preprint]
Bayesian canonical correlation analysis. Arto Klami, Seppo Virtanen, and Samuel Kaski. Journal of Machine Learning Research, 14:965-1003, 2013. [pdf]

NS Jam Session on 12th December 10:00 with Airi Lampinen

hoggan — Mon, 10 Dec 2012 13:20:24 +0000

Airi Lampinen will talk about account sharing in the context of social network services. The main emphasis will be on a qualitative study in which altogether sixteen people (eight women and eight men) from eight multi-person households who offer to host strangers viaCouchsurfing.org were interviewed about their experiences with the site. Findings illustrate challenges in three key areas: (1) presenting multiple people with a single profile, (2) negotiating access to domestic spaces, and (3) accounting for a reputation that is accumulated jointly over time.

The talk is based on recent research conducted over the summer at Microsoft Research New England as well as ongoing thinking about how to conceptualize social media use beyond the individual and how to design with shared use in mind.

As the industry internship recruitment season for next summer is on at the moment, we can also discuss internships and application processes briefly, if it is of interest to the audience.

The session will take place in the video conferencing room in OIH and in Exactum, Kumpula (A114).

Break in windows 32 bit printing services - 05.10.2012, 15:00 - 11.10.2012, 13:24

pvettenr — Thu, 11 Oct 2012 11:06:41 +0000

Schedule:

2012-10-05 15:00 to 2012-10-11 13:24

Duration:

7 days

Affected services:

All windows 32 operating systems

Description:

None of our 32 bit windows operating systems could not print during 05.10.2012, 15:00 - 11.10.2012, 13:24. On friday 05.10.2012 15:00 cups.cs.helsinki.fi's hard drive filled up and because of that samba server seems to have corrupt the windows 32 bit printer drivers. Windows 64 bit printing has worked just fine.

CoSCo People and Contact Information

myllymak — Tue, 18 Sep 2012 12:14:47 +0000

Current CoSCo Group Members

The list of current group members can be found on the CoSCo home page. To contact or find a group member, please check the HIIT contact page. Most of us have our (main) office in the Kumpula Site of HIIT, in the premises of the Computer Science Department (Exactum building, Kumpula Campus, street address: Pietari Kalmin katu 3).

CoSCo Alumni Members

Anupam Arohi
- ~~Senior Software Engineer, Digital Foodie Ltd, Finland~~
- Project Manager, Solibri, Inc.
Wray Buntine
- ~~Principal Researcher, Canberra Research Laboratory, NICTA, Australia~~
- Professor, Monash University, Australia
Ciprian Giurcaneanu
- Senior Lecturer, Department of Statistics, University of Auckland, New Zealand
Raul Hakli
- Postdoctoral Researcher, Department of Political and Economic Studies, University of Helsinki, Finland
Liye He
- Doctoral Student at Institute for Molecular Medicine Finland (FIMM)
Matti Jokipii
- Software Developer, Futucraft Ltd., Finland
Ksenia Konyushkova
- Doctoral student at EPFL, Switzerland
Jaakko Kurhila
- ~~Head of Studies, Dept. of Computer Science, University of Helsinki, Finland~~
- Director, Open University at the University of Helsinki.
Jussi Lahtinen
- Technology Developer, M-Brain, Finland
Tei Laine
- ~~Senior Research Engineer, IHPC, A*STAR, Singapore~~
- Visiting scholar at Maison des Sciences de l'Homme-Alpes, Grenoble, France
Tuomas Lepola
- IT Manager, Institute for Statistical and Epidemiological Cancer Research, Finland
Jaakko Löfström
- Founder, Iloinen Piano Inc., Finland
Brandon Malone
- Postdoctoral Researcher, MPI Cologne, Germany
Miikka Miettinen
- Technology Specialist, Exakti Intelligence, Finland
Tommi Mononen
- Postdoctoral Researcher, Aalto University, Finland
Quan Nguyen
- Doctoral student at TU Eindhoven, The Netherlands
Petri Nokelainen
- Professor, School of Education, University of Tampere, Finland
Pekka Orponen
- Professor, Aalto University, Finland
Sami Perttu
- ~~Programmer, Futuremark Corporation, Finland~~
- Free-lance programmer, professional net poker player
Vladimir Poroshin
- Senior R&D Engineer, M-Brain, Finland
Tomi Silander
- ~~Senior Research Fellow, National University of Singapore~~
- Senior Scientist, Xerox Research Centre Europe, Grenoble, France
Sotiris Tasoulis
- Lecturer, John Moores University, Liverpool, UK.
Henry Tirri
- ~~Executive Vice President/CTO, Nokia, USA~~
- Experienced C-level Executive, President and Founder at Beaivi LLC
Antti Tuominen
- Technology Developer, M-Brain, Finland
Ville Tuulos
- ~~Co-Founder, Bitdeli, USA~~
- Principal Engineer, AdRoll, USA
Kimmo Valtonen
- CTO, M-Brain, Finland
Hannes Wettig
- IT consultant, Quinctiq, Finland
Pekka Uronen
- Co-Founder, Huikea Experience, Finland
Mika Urtela
- Co-Founder, Soul Aim Studios, Finland
Taneli Vähäkangas
- Senior Software Engineer, Enevo, Finland
Ziran Wang
- ~~Data Analyst, Teradata, China~~
- Data Mining Analyst, Alibaba.com, China
Lilu Xu
- Software Engineer, Google, San Francisco, USA

Helsinki Privacy Experiment

jperkio — Mon, 17 Sep 2012 14:51:03 +0000

Summary

Ubiquitous surveillance refers to unilateral collection of data on people with sensors embedded in their everyday environment. Enabled by progress in ubiquitous computing, surveillance is penetrating into activities that used to be regarded private. With browsers, phones, credit cards, CCTV, e-mail, social media, telecommunications, television and entertainment media, digital documents, and health records already tapped, it is harder and harder to find a sphere of life where data was not collected, indexed, distributed, searched, and inferred. The means for control, if provided at all, are opaque or incomprehensible. These qualities raise ubiquitous surveillance as among the most alarming developments of our time. The Helsinki Privacy Experiment contributes to the understanding of privacy under these conditions.

The Helsinki Privacy Experiment project is a study of the long-term effects of ubiquitous surveillance in home. Ten volunteering households were instrumented with a surveillance and logging system covering the following:

3-5 video cameras with microphones
the use of computer (screenshots and keylogging)
wireless and wired network
smartphone
TV
DVD
customer loyalty cards

The project examined the participants'

stress and anxiety
privacy concerns
privacy-seeking behavior

after six and twelve months. The findings provide first insight into the privacy-invading character of ubiquitous surveillance. The first paper reports results after six months (see below for download).

Additionally, the project studies the use of different data analysis and fusion methods in order to gain insight into the limits of user profiling and the associated privacy implications. Governments and companies who engage in data collection do not disclose their findings about what can be reliably inferred about humans. We publish our findings about the limits of computer inference in ubiquitous surveillance to inform the stakeholders.

Team

Antti Oulasvirta
Petri Myllymäki
Jukka Perkiö
Aurora Pihlajamaa
Lasse Tyrväinen
Debarshi Ray
Andreas Forsblom
Taneli Vähäkangas

Due to the sensitivity of the collected data only part of the team has access to the actual data.

Downloads

This section will be updated with software for BOB in October 2012.

Funding

The Helsinki Privacy Experiment is funded by an Academy of Finland project grant (2010-2012).

Publications

Long-term Effects of Ubiquitous Surveillance in the Home. Antti Oulasvirta, Aurora Pihlajamaa, Jukka Perkiö, Debarshi Ray, Taneli Vähäkangas, Tero Hasu, Niklas Vainio, Petri Myllymäki, in Proceedings of The 14th International Conference on Ubiquitous Computing (Ubicomp 2012). Presentation slides

Turn your dreams into music

pmoen — Fri, 07 Sep 2012 08:55:19 +0000

Computer scientists have developed a method that automatically composes music out of sleep measurements. The composition service works live on the Web at sleepmusicalization.net.

Developed under Hannu Toivonen, Professor of Computer Science at the University of Helsinki, the software automatically composes synthetic music using data related to a person’s own sleep as input.

The composition program is the work of Aurora Tulilaulu, a student.

”The software composes a unique piece based on the stages of sleep, movement, heart rate and breathing. It compresses a night’s sleep into a couple of minutes,” she describes.

”We are developing a novel way of illustrating, or in fact experiencing, data. Music can, for example, arouse a variety of feelings to describe the properties of the data. Sleep analysis is a natural first application,” Hannu Toivonen justifies the choice of the research topic.

The project utilises a sensitive force sensor placed under the mattress.

”Heartbeats and respiratory rhythm are extracted from the sensor’s measurement signal, and the stages of sleep are deducted from them,” says Joonas Paalasmaa, a postgraduate student in the department. He designed the sleep stage software at Beddit, a company that provides services in the field.

The composition service is available online at http://sleepmusicalization.net. The users of Beddit’s service can have music composed from their own sleep, while others can listen to the compositions. The online service is the work of the fourth team member, Mikko Waris.

The study Sleep Musicalization: Automatic Music Composition from Sleep Measurements will be presented at the International Symposium on Intelligent Data Analysis in Helsinki in October 2012. IDA symposiums are well-known for presenting multidisciplinary research without prejudice.

Text: Minna Meriläinen

Information, Complexity and Learning

myllymak — Thu, 06 Sep 2012 08:58:52 +0000

Group Leader: Teemu Roos

The Information, Complexity and Learning (ICL) research group is a part of the Cosco research group and studies the theory and applications of probabilistic models, especially graphical models. A particular area of interest is information theoretic methods. Application domains where we have continued collaboration include human–computer interaction, digital humanities, and bioinformatics.

News and Events (see also Cosco News on the right)

October 26, 2018: The Elements of AI reaches 100k participants!
August, 2018: Elias Jääsaari moves to Kvasir Ltd in Cambridge. We wish Elias good luck!
May 15, 2018: The Elements of AI online course is launched in collaboration with Reaktor.
April 2018: Elias Jääsaari presents "Minimax optimal Bayes mixtures for memoryless sources over large alphabets" at ALT-2018, Lanzarote.
March 26, 2018: Teemu Roos gives an invited talk at Google Inc. (Pittsburgh)
March 21, 2018: Teemu Roos gives an invited talk at Apple Inc. (Apple Park)
Papers accepted to Digital Scholarship in the Humanities ("Quantitative methods for the analysis of Medieval calendars") and the forthcoming book Online Distribution of Content in the EU ("Digital distribution of AI-generated content: Authorship and inventorship in the age of artificial intelligence")
Ville Hyvönen visits Sanjoy Dasgupta's group at UC San Diego in February-April 2018
Papers accepted to ALT 2018 ("Minimax optimal Bayes mixtures for memoryless sources over large alphabets") and AISTATS 2018 ("Quotient normalized maximum likelihood criterion for learning Bayesian network structures")
December 13, 2017: Teemu Roos gives a keynote talk "Forget about the Terminator already! AI Education for All" at the 1st AI Day Finland. (Slides on SlideShare)
November 8, 2017: Teemu Roos discusses the past, present, and future of AI in an public event at @ThinkCorner (in Finnish)
10/2017: The Academy of Finland awards 2-year funding for out joint proposal with Prof Fluyra Djurabekova and Prof Kai Nordlund (Department of Physics) on "Machine Learning for Quantum Mechanics Based Material Design"
6/2017: The Academy of Finland awards 4-year funding for our joint proposal with Prof. Tapio Pahikkala (Turku) on "Tensor-Based Machine Learning for Big Data with Inherent Dependencies".
Papers accepted to International Journal of Approximate Reasoning, New Generation Computing, and Pattern Recognition Letters (see below).
6/2017: Jukka Kohonen joins the ICL group as a postdoc. Welcome Jukka!
We will co-organize the 10th WITMSE workshop in Paris on September 11-13, 2017.
4/2017: Our joint proposal with Prof. Pulkit Grover (CMU) on ''Efficient and Robust Cognitive IoT Systems using Unreliable Sensors'' is funded by the Academy of Finland and NSF.
Teemu Pitkänen moves to Google Research Europe in Zürich. We wish Teemu good luck!
3/2017: Teemu Roos teaches at the 21st CIMO Winter School, Tvärminne Zoological Station, Finland
March 3rd, 2017: Yuan Zou defended her doctoral thesis on "Model Selection for Bayesian Networks and Sparse Logistic Regression". Congratulations to Yuan!
2/2017: Teemu Roos gives a talk at the Workshop on Mathematical Approaches to Evolutionary Trees and Networks in Banff, Canada. Video available.
10/2016: Joonas Miettinen joins the group as a PhD student supervised by Teemu Roos and Janne Pitkäniemi (Finnish Cancer Registry). Welcome Joonas!
Former ICL postdoc Sotiris Tasoulis is a co-chair of the 2nd Workshop on Advances in High Dimensional Big Data on December 5-8, 2016.
Teemu Roos gives talks at the University of Melbourne (details) on October 6, 2016 and Monash University on October 12, 2016.
"Minimum Description Length Principle" by Teemu Roos appears in the Encyclopedia of Machine Learning and Data Mining.
We are organizing the 9th Workshop on Information Theoretic Methods in Science and Engineering (WITMSE-2016) in Helsinki on September 19-21, 2016.
May 27th 2016: Jussi Määttä will defend his PhD thesis "Model selection methods for linear regression and phylogenetic reconstruction" (2pm, Exactum B123).
May 17th 2016: Teemu Roos gives a talk on "Directed acyclic graphs as a model for biological and cultural evolution" at Purdue University, USA.
April 24th 2016: Teemu Roos gives a talk on "Machine learning and the evolution of fairy tales" in the Informatics Colloquium at the Martin Luther University, Halle, Germany.
Summer 2016 internship to Elias Jääsaari. Welcome Elias!
Papers accepted to PLOS ONE, IEEE Transactions on Big Data, and EuroVis 2016 conference.
Ville Hyvönen joins the group as a PhD student under the Scalable Probabilistic Analysis project. Welcome Ville!

(Click here for older events.)

People

Senior Members			AVAILABLE ONLINE B-Course
Teemu Roos, PhD Associate professor	Jukka Kohonen, PhD Postdoc	Jussi Määttä, PhD Postdoc
Students
Ville Hyvönen PhD student	Janne Leppä-aho PhD student	Joonas Miettinen PhD student

Past members & alumni Elias Jääsaari (MSc 2018) >> Kvasir Ltd (Cambridge) Yuan Zou (PhD 2017) Teemu Pitkänen (MSc 2016) >> Google Research Europe (Zurich) Jussi Määttä (PhD 2016) >> Data Scientist @ Swap.com Santeri Räisänen (research assistant 6/2014–12/2015) Yang Zhao (research assistant 6/2014–12/2015) Sotiris Tasoulis (postdoc 9/2013–8/2015) >> Liverpool John Moores University Quan (Eric) Nguyen (MSc, research assistant 5/2013–8/2015) >> TU Eindhoven Arttu Modig (MSc, research assistant 1/2012–5/2015) >> Finland's Slot Machine Association Simo Linkola (MSc, research assistant 1/2011-4/2014) >> Computational Creativity Group Nikolay Vasilev (intern summer 2013)

Recent Papers and Preprints

2018+

E. Jääsaari, V. Hyvönen, T. Roos (2019). Efficient autotuning of hyperparameters in approximate nearest neighbor search, to appear in Proc. 23rd Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD-2019), Macau, China. C++ library with Python bindings

T. Heikkilä and T. Roos (2018), Quantitative methods for the analysis of Medieval calendars, Digital Scholarship in the Humanities, 33(4):766–787.

U. Sheth, S. Dutta, M. Chaudhari, H. Jeong, Y. Yang, J. Kohonen, T. Roos, and P. Grover (2018). An application of storage-optimal MatDot codes for coded matrix multiplication: Fast k-nearest neighbors estimation, to appear in IEEE Big Data Conference, Seattle, December 10–13, 2018

J. Leppä-aho, S. Räisänen, X. Yang, and T. Roos (2018). Learning non-parametric Markov networks with mutual information, in Proc. 9th Int Conf on Probabilistic Graphical Models, Prague, September 11–14, 2018. Best student paper award

E. Jääsaari, J. Leppä-aho, T. Silander and T. Roos (2018). Minimax optimal Bayes mixtures for memoryless sources over large alphabets, in Proc. Int. Conf. on Algorithmic Learning Theory (ALT 2018)

T. Silander, J. Leppä-aho, E. Jääsaari, and T. Roos (2018). Quotient normalized maximum likelihood criterion for learning Bayesian network structures, in Proc. 21st Int. Conf. on Artificial Intelligence and Statistics, PMLR 84:948-957 (AISTATS 2018) (+ supplementary PDF)

2017

J. Leppä-aho, S. Räisänen, X. Yang, and T. Roos (in preparation). Learning non-parametric Markov networks with mutual information, arXiv:1708.02497.

Y. Zou, J. Pensar, and T. Roos (2017). Representing local structure in Bayesian networks by Boolean functions, accepted to Pattern Recognition Letters.

J. Leppä-aho, J. Pensar, T. Roos, and J. Corander (2017). Learning Gaussian graphical models with fractional marginal pseudo-likelihood, International Journal of Approximate Reasoning, arXiv:1602.07863

Y. Zou and T. Roos (2017). On model selection, Bayesian networks, and the Fisher information integral, New Generation Computing 35(1) (Special Issue on AMBN 2015), January 2017.

2016

V. Hyvönen, T. Pitkänen, S. Tasoulis, E. Jääsaari, R. Tuomainen, L. Wang, J. Corander, and T. Roos. Fast nearest neighbor search through sparse random projections and voting, 2016 IEEE International Conference on Big Data (IEEE Big-Data 2016), Washington DC, Dec. 5–8. C++ library (with Python bindings) | benchmarks

T. Roos (2016). Minimum Description Length Principle, in Sammut, C. and Webb, G.I. (eds), Encyclopedia of Machine Learning and Data Mining.

T. Heikkilä and T. Roos, (2016). Thematic Section on Studia Stemmatologica, Digital Scholarship in the Humanities 31(3):520–522, doi:10.1093/llc/fqw038.

L. Wang, S. Tasoulis, T. Roos, and J. Kangasharju (2016). Kvasir: Scalable provision of semantically relevant web content on big data framework, IEEE Transactions on Big Data.

Y. Zhao, S. Tasoulis, and T. Roos (2016). Manifold visualization via short walks, EuroVis-2016.

J. Määttä and T. Roos (2016). Maximum parsimony and the skewness test: A simulation study of the limits of applicability, PLOS ONE 11(4):e0152656.

Y. Zou and T. Roos (2016). Sparse Logistic Regression with Logical Features, Proc. 20th Pacific Asia Conference on Knowledge Discovery and Data Mining (PAKDD-2016).

J. Määttä and T. Roos (2016). Robust Sequential Prediction in Linear Regression with Student’s t-distribution, in Proc. 14th International Symposium on Artificial Intelligence and Mathematics (ISAIM 2016).

2015

R. Eggeling, T. Roos, P. Myllymäki, and I. Grosse (2015). Inferring intra-motif dependencies of DNA binding sites from ChIP-seq data, BMC Bioinformatics.

Y. Zou and T. Roos (2015). On model selection, Bayesian networks, and the Fisher information integral, in Proc. 2nd Workshop on Advanced Methodologies for Bayesian Networks (AMBN-2015).

J. Määttä, D. F. Schmidt, and T. Roos, (2015). Subset Selection in Linear Regression using Sequentially Normalized Least Squares: Asymptotic Theory, Scandinavian Journal of Statistics.

J. Tehrani, Q. Nguyen, and T. Roos, (2015). Oral fairy tale or literary fake? Investigating the origins of Little Red Riding Hood using phylogenetic network analysis, Digital Scholarship in the Humanities.

Q. Nguyen and T. Roos, (2015). Likelihood-based inference of phylogenetic networks from sequence data by PhyloDAG, in Proc. 2nd International Conference on Algorithms for Computational Biology (AlCoB-2015).

K. Watanabe abd T. Roos, (2015). Achievability of asymptotic minimax regret by horizon-dependent and horizon-independent strategies, JMLR.

(Click here for older papers.)

FuNeSoMo August 2012 Call for research exchange with ICSI and UCB

karvonen — Tue, 29 May 2012 06:50:13 +0000

AUGUST 2012 CALL for applications for funding research exchange between ICSI Berkeley or UCB and HIIT

DEADLINE 10.8.2012 http://www.hiit.fi/funesomo/august2012call

Future Networks, Society and Modeling (FuNeSoMo) project is announcing an open call for applications for funding for research visits between Finland and US. This call is directed primarily to cover research exchange between Aalto University and University of Helsinki and the International Computer Science Institute ICSI Berkeley and/or University of California, Berkeley (UCB). Research exchange plans scheduled to take place in fall 2013 are given highest priority, but other times can also be considered.

The call is intended to support research visits of 3-11 months. For senior applicants, also shorter research visits can be funded (minimum 2 weeks) but visit duration cannot exceed 6 months. The research visits cannot extend beyond December 2013.

The application consists of the following documents:

A list of possible hosts within ICSI and/or UCB or at Aalto/UH. An already established contact is not required in order to suggest a host. Suggested hosts will be contacted in collaboration with ICSI and UCB or Aalto and UH. If established contact exists, a recommendation letter from the suggested host is advisable to be added to the application, but is not obligatory.
A high-quality research plan in the area of FuNeSoMo with tentative schedule and tentative budget covering all expected main costs (direct salary costs, housing, travel) demonstrating tight connection with FuNeSoMo thematic research areas and an outline of planned collaboration with the possible host.
CV including publication list
Students only: A recommendation letter from supervisor
Students only: Transcript of study record
Students only: Master's degree certificate

To apply, send your application by email to the coordinator kristiina.karvonen(at)hiit.fi containing all required documents as separate pdf files as attachments by 10.8.2012. Incomplete or late applications will not be considered. For any questions relating to the applying procedure, please get in touch with the coordinator early on (available until 21.6.2012 and between 6.-10.8.2012.)

A successful candidate will have a good track record of high-quality research in the area of FuNeSoMo (depending on the career phase). The main target group of the call is senior candidates, but applications from graduate students are also more than welcome. The junior applicants must have at least a master's level degree and be enrolled as a graduate student in either Aalto University or University of Helsinki to be eligible to apply for funding from FuNeSoMo.

FuNeSoMo funding will cover the salary, daily allowance and travel expenses and a fixed sum for housing expenses during the research visits for the successful candidates. Additional family costs are for the most not covered from FuNeSoMo, but applicant is free to seek for complementary funding to cover these costs from elsewhere. The salary during FuNeSoMo funded exchange is based on HIIT/Aalto salary policy and the applicant will in most cases become HIIT/Aalto employee during the exchange. Applicants from companies should get in touch with the coordinator to inquire how to apply for funding from FuNeSoMo for a research exchange to ICSI or UCB.

The FuNeSoMo steering group will choose the best applications for funding. The funding decisions will be announced 24.8.2012 directly to all applicants.

FuNeSoMo has 2-3 calls annually. The next call deadline is planned for late 2012 - early 2013.
To find out more about the project contents and thematic research areas, visit project website at
http://www.hiit.fi/funesomo and download project description (.pdf).

For all inquiries, please contact
(available until 21.6.2012 and between 6.-10.8.2012.)

Dr. Kristiina Karvonen Coordinator, FuNeSoMo
Helsinki Institute for Information Technology HIIT www.hiit.fi
Aalto University www.aalto.fi and University of Helsinki www.helsinki.fi/university
Email: kristiina.karvonen at hiit.fi
Tel. +358 50 3841 624

http://www.hiit.fi/funesomo/august2012call

Research evaluation at Univ Helsinki: Excellent scores to HIIT-affiliated communities

ebingham — Thu, 24 May 2012 12:42:13 +0000

Research and doctoral training were evaluated in University of Helsinki in 2011. This time, researchers were allowed to volunteer for evaluation as bottom-up organized research communities. Three HIIT communities participated successfully:

* The research community of Algorithms and Machine Learning, which to a large degree overlaps with HIIT's ADA and CI programmes on the University of Helsinki side, scored at the absolute top of the whole university. The community participated in the "international cutting edge" category and received highest possible marks in every single aspect: "The community constitutes one of the world-leading centres in the area of algorithmic and computational data analysis". "The community is excellently positioned, with an outstanding scientific record in which foundational and application-oriented research are both excellently represented."

* The research community of Networks and Distributed Systems, also containing several HIIT groups, received the best scores in another category: "The community is in an excellent stage of development and the overall focus is very strong. The subject area is highly relevant and well-positioned in the foundational and technical research for modern ICT systems." "The community has an excellent record of industrial cooperation and actively contributes to leading standardization bodies like the IETF, ISO, the WWRF forum and the W3C consortium."

* The research community Bayes, consisting of two research groups another of which is by a new HIIT group leader Jukka Corander, participated in the category of "research having a highly significant societal impact". It was also assessed outstanding: "their results have been well adopted by the decision-makers". "Bayes is an excellent example of the successful combination of strong methodological and thematic research groups resulting in both scientific excellence and high societal impact."

More information in Finnish at http://www.cs.helsinki.fi/uutiset/71938

Full version of the evaluation report in English at http://www.helsinki.fi/arviointi2010-2012/tulokset.htm.

Report on the Algorithmics and Machine Learning community, in English, at http://www.helsinki.fi/julkaisut/aineisto/rc_evaluation2012/hallinnon_julkaisuja_80_70_2012.pdf

Report on the Networks and Distributed Systems community, in English, at http://www.helsinki.fi/julkaisut/aineisto/rc_evaluation2012/hallinnon_julkaisuja_80_54_2012.pdf

Collaborative Networking

karvonen — Tue, 15 May 2012 14:07:17 +0000

We investigate novel network architectures, in particular in the areas of content distribution and content management. Our current primary focus is in information-centric networking, mobile opportunistic content sharing and green networking. Our work is experimentation-oriented and in our research we combine modeling, simulations, and practical experiments. In opportunistic content sharing, we have developed the floating content paradigm where information is published to a particular location and then replicated in an ad hoc manner between mobile devices, attempting to keep the information available in the area where it was published. Our work assumes no support from the infrastructure.

We have developed in-network caching architectures and devised caching mechanisms for information-centric networks. Our solutions cover simple, decentralized caching algorithms and their evaluation. In the area of green networking, we have continued our work on data center cooling optimization solutions, with work on cold aisle containment and its evaluation.

Currently we are extending this work to include heat harvesting and we have built a greenhouse where we are experimenting if the exhaust heat from computers is sufficient to heat up the greenhouse sufficiently
to allow for plants to grow.

Key publications:

Joerg Ott, Esa Hyytiä, Pasi Lassila, Tobias Vaegs, Jussi Kangasharju, Sougata Santra. Floating Content for Probabilistic Information Sharing. Pervasive and Mobile Computing, 7(6):671–689, December 2011.
Mikko Pervilä, Jussi Kangasharju. Cold Air Containment. In Proceedings of ACM SIGCOMM Workshop on Green Networking and Smart Systems, Toronto, Canada, August 2011.
Walter Wong, Marcus V. L. Giraldi, Mauricio F. Magalhäes, Jussi Kangasharju, Content Routers. Fetching Data on Network Path. In Proceedings of IEEE ICC, Kyoto, Japan, June 2011.
Esa Hyytiä, Jorma Virtamo, Pasi Lassila, Jussi Kangasharju, Joerg Ott. When Does Content Float? Characterizing Availability of Anchored Information in Opportunistic Content Sharing. In Proceedings of IEEE Infocom, Shanghai, China, April 2011.
Joerg Ott, Esa Hyytiä, Pasi Lassila, Tobias Vaegs, Jussi Kangasharju. Floating Content: Information Sharing in Urban Areas. In Proceedings of IEEE International Conference on Pervasive Computing and Communications, Seattle, WA, March 2011.
Mikko Pervilä, Jussi Kangasharju. Running Servers around Zero Degrees. Computer Communications Review, 41(1):96–101, January 2011.

People:

Jussi Kangasharju
Mikko Pervilä
Sougata Santra

Break in arod.it.hiit.fi at 2012-04-11 10:30 - 10:40

pvettenr — Wed, 11 Apr 2012 07:30:47 +0000

Schedule:

2012-04-11 10:30 to 10:40

Duration:

10 min

Affected services:

none

Description:

Following updates will be installed

* Security Update for Microsoft .NET Framework 3.5.1 on Windows 7 and Windows Server 2008 R2 for x64-based Systems (KB2656372)
A security issue has been identified that could allow an authenticated remote attacker to compromise your system and gain control over it.

* Cumulative Security Update for Internet Explorer 8 for Windows Server 2008 R2 x64 Edition (KB2675157)
Security issues have been identified that could allow an attacker to compromise a system that is running Microsoft Internet Explorer and gain control over it.

* Security Update for Windows Server 2008 R2 x64 Edition (KB2653956)
A security issue has been identified that could allow an unauthenticated remote attacker to compromise your system and gain control over it.

Break in meriadoc.it.hiit.fi at 2012-02-16 08:30 - 08:40

pvettenr — Thu, 16 Feb 2012 07:27:33 +0000

Schedule:

2012-02-16 08:30 to 08:40

Duration:

10 min

Affected services:

Remote Windows server (rwin.hiit.fi)

Description:

Operating system update installations as follows and the needed reboot.

Installed updates:

Definition Update for Windows Defender - KB915597 (Definition 1.119.1924.0)
Security Update for Windows Server 2008 R2 x64 Edition (KB2654428)
Security Update for Microsoft .NET Framework 4 on XP, Server 2003, Vista, Windows 7, Server 2008, Server 2008 R2 for x64 (KB2633870)
Security Update for Windows Server 2008 R2 x64 Edition (KB2643719)
Security Update for Windows Server 2008 R2 x64 Edition (KB2645640)
Security Update for Windows Server 2008 R2 x64 Edition (KB2660465)
Security Update for Microsoft Silverlight (KB2668562)
Security Update for Microsoft .NET Framework 3.5.1 on Windows 7 and Windows Server 2008 R2 for x64-based Systems (KB2633879)
Update for Microsoft Office 2007 suites (KB2597998)
Cumulative Security Update for Internet Explorer 8 for Windows Server 2008 R2 x64 Edition (KB2647516)

Change of name of prof. Veli Mäkinen's group

ebingham — Wed, 04 Jan 2012 18:05:36 +0000

The research group led by professor Veli Mäkinen at Department of Computer Science, University of Helsinki is re-named as Genome-Scale Algorithms (previously Succinct data structures).

The web page of the group is http://www.cs.helsinki.fi/gsa/

We develop algorithms and data structures for the analysis of genome-scale data. Such data is abundant due to modern molecular biology measurement techniques like high-throughput sequencing. We are especially interested in applications of compressed data structures, that make it possible to analyse the often highly redundant data within the space of their information content. We also study other scalability aspects like distributed computation/storage around genome-scale data.

Break in file service fs at 2011-09-26 18:00-19:22

pmtonter — Thu, 22 Sep 2011 10:58:50 +0000

Schedule:

2011-09-26 18:00 to 19:22

Duration:

1 h 22 min

Affected services:

File services (fs), cluster file services (hpc-fs), web services, entry server shell.

Description:

Operating system of file server frodo.it.hiit.fi will be upgraded. Pending firmware upgrades will also be installed.

The following web-sites will also be affected due to their dependency on file service:

www.futureinternet.fi
betelgeuse.hiit.fi
cgi.hiit.fi
cosco.hiit.fi
packages.hiit.fi
pgm2010.hiit.fi
www.mdl-research.org

There will be few short (< 15 min) breaks in file service.

Update at 19:24: The break was over at 19:22. There was one longer break (approx. 30 minutes) in Windows file sharing due to behaviour change of ldap ssl directive.

Break in meriadoc.it.hiit.fi at 2011-01-14 07:00 - 07:15

pvettenr — Fri, 14 Jan 2011 10:45:47 +0000

Schedule:

2011-01-14 07:00 to 07:15

Duration:

15 min

Affected services:

General purpose Windows server rwin.hiit.fi.

Description:

Monthly security updates wil be installed and system will be rebooted.

Break in meriadoc.it.hiit.fi at 2010-01-07 16:50 - 2010-01-08 13:03

jmalahti — Thu, 07 Jan 2010 13:50:00 +0000

Description:

Schedule:

2010-01-07 16:50 - 2010-01-08 13:03

Duration:

20:13 h

Affected services:

Generic remote windows server

Reason:

Rebooted due to unresponsivenes. After installing updates system became unstable.

Update: Reason was old version of virus shield which is now updated.

AICA: Adaptive Interfaces for Consumer Applications

aforsblo — Wed, 30 Dec 2009 12:59:11 +0000

AICA is a Tekes project in the Ubicom programme for 1 November 2009 to 31 March 2012. AICA is a continuation to the PUPS project. The PUPS project was originally outlined as a four-year project; building on the results so far, we will in AICA focus on topics that have turned out to be the most promising and we will add some new aspects that have emerged and are worth further study.

Context-awareness and personalisation are key enablers for the ubiquitous computing vision. From the end user’s point of view, they are essential for managing the complexity of future services and applications. The goal of this project is to enable adaptive interfaces to information by combining context-awareness with personalisation and to perform user acceptance studies on a number of prototypes for ubicom consumer applications. We will continue working on our intelligent mobile shopping assistant Ma$$iv€. We will also work on new interaction methods (e.g., UbiLight, a prototype of a system using hand movement as an interactive spatial interaction method). We aim at ideas that could be commercialised in a few years’ time.

The research groups involved in the project cover a large spectrum of scientific and technical expertise and the project partners include different types of stakeholders: a retail chain, mobile technology providers, a teleoperator and representatives of diverse user groups. Project partners offer for the project also their own technology and expertise in addition to the financial support they provide for the project.

Our trial area is K-Citymarket Ruoholahti.

Consortium

The main project research partners are:

The companies are:

Bitlips Oy
Ekahau Oy
Elisa Oyj
K-Plus Oy (part of Kesko Oyj)
Nokia Oyj
FAIDD (Finnish Association on Intellectual and Developmental Disabilities, Kehitysvammaliito)

Contact Person

Consortium Coordinator is Dr Patrik Floréen.

Break in storage area network (SAN) at 2009-09-07 13:55-18:30

jmalahti — Mon, 07 Sep 2009 11:54:28 +0000

Description:

Schedule:

2009-09-07 13:55 - 18:30

Duration:

4:35

Affected services:

At least VCS, Wiki, WWW, Windows AD. Possibly others.

Reason:

Problems with SAN.

Update: Problems were caused by faulty SFP (fibre adapter).

It caused one blade-enclosure's one uplink-port to fluctuate up and down thus messing up the SAN-fabric using that port. And, of course, availability of paths to LUNs and other resources accessed via that fabric fluctuated too. Because the port wasn't down all the time, determining the cause of problem wasn't clear, paths sometimes worked and sometimes didn't. Because of this, an incorrect desicion of rebooting one of the SAN-swithches, the one in the functioning fabric, at 14:18:35 caused some of the hosts to temporarely lose all paths to LUNs in SAN.

Linux is especially cranky when it comes to losing it's disks, even temporarely. It determines the disk to be read-only quite soon, even the disk would come back in a few seconds. To gain read-write access, a reboot was required.

The faulty SFP started to be down longer periods of time later and thus was discovered and replaced with a working one. Breaks to services were between 9 and 44 minutes. Kernel updates were installed to servers that needed them during the breaks as well.