|contact: email@example.com||CV (pdf) icl_research teemu_roos teemu-roos|
NEW: We have released version 1.0 of our fast approximate nearest neighbor package. It is easy to install and use from C++ and Python and includes fully automated parameter tuning: MRPT on Github.
NEW: OPEN POSTDOC POSITION: I'm looking for smart, creative, and motivated people. I currently have a postdoc position open. If you have a solid understanding of machine learning, a good publication record and a curious mind, please drop me a mail. Underrepresented groups are explicitly encouraged to apply.
Janne Leppä-aho received the best student paper award at PGM-2018 with the paper 'Learning non-parametric Markov networks with mutual information'.
"Tekoälyn lukutaito" ("AI Literacy"; in Finnish), pääkirjoitus, Tieteessä tapahtuu 36(1), 2018:
Tavoitteena ei ole kouluttaa koko kansasta tekoälykoodareita. Sen sijaan perusteiden avulla saavutetaan kyky osallistua tekoälyyn liittyvään yhteiskunnalliseen keskusteluun ja arvioida kriittisesti esitettyjä väitteitä – "tekoälyn lukutaito". (Teemu Roos)
The aim is not to train the entire population as AI developers. Instead, knowing the basics enables one to engage in the public discourse on AI and to critically evaluate arguments about it – "AI literacy". (Teemu Roos)
My traveling/conference schedule in 2018:
- ITA-2018, San Diego, February 11–16
- UCSD, February 1–21
- UC Berkeley, February 26–March 22
- Apple, Cupertino, March 21
- Targeted Discovery in Brain Data Workshop, Simons Institute, Berkeley, March 19–22
- Princeton, March 23
- CMU, Pittsburgh, March 26–30
- Google AI, Pittsburgh, March 26
- ALT 2018, Lanzarote, April 7–9
- AISTATS 2018, Lanzarote, April 9–11
- WiFiUS Meeting and Summer School, Boston, June 11–16
- UCSC Milano, Milan, October 24–November 14
6/2017: The Academy of Finland has awarded two new grants to our research group. TensorML project (4 years) will study non-standard machine learning problems with applications in drug design, and MachQu project (2 years) will apply probabilistic machine learning to quantum-mechanics based material design.
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.
I host the Machine Learning Coffee Seminar together with Sami Kaski and H. Afrabandpey.
Selected conference and workshop involvement (program committee or equivalent): AISTATS-2011/2014/2015, ICML-2018, IJCAI-2013/2015/2018, NIPS-2014/2015/2016/2017/2018, UAI-2008/2009/2010/2011/2012/2013/2014/2015/2016/2017/2018.
In the academic year 2018–2019, I teach the following courses:
- DATA15001 Introduction to Artificial Intelligence (Johdatus tekoälyyn) in period I
- DATA11001 Introduction to Data Science also in period I
I am the instructor of the Undergraduate Research Track (tutkijalinja).
I currently supervise:
- Juho Lamminmäki (MSc student)
- Ilse Tse (MSc student)
- Ilkka Vähämaa (MSc student)
- Joonas Miettinen (PhD student; 1st year) co-supervised with Dr Janne Pitkäniemi (Finnish Cancer Registry)
- Ville Hyvönen (PhD student, 2nd year)
- Janne Leppä-aho (PhD student, 3rd year)
- Biyun Huang (MSc 2018)
- Carlos Santana Vega (MSc 2018)
- Sean Lang (MSc 2018)
- Sebastian Falk (MSc 2017)
- Joe Niemi (MSc 2017)
- Elias Jääsaari (MSc 2017)
- Tommi Jalkanen (MSc 2017) co-supervised with Dr Jutta Jokiranta (Theology)
- Laura Uusitalo (MSc 2017)
- Elaine Zosa (MSc 2017)
- Yuan Zou (PhD 2017)
- Teemu Pitkänen (MSc 2016)
- Jussi Määttä (PhD 2016)
- Antti Takalahti (MSc 2016) co-supervised with Prof Edward Haeggström (Physics)
- Risto Tuomainen (MSc 2016)
- Simo Linkola (MSc 2016)
- Kaj Sotala (MSc 2015)
- Quan Nguyen (MSc 2015)
- Peter Hedman (MSc 2015), co-supervised with Prof Jaakko Lehtinen (Aalto/NVIDIA Corp)
Acad. Assoc. for Maths and Natural Sciences (MAL) MSc Thesis Award
- Arttu Modig (MSc 2014), co-supervised with Prof Jouko Lampinen (Aalto)
- Janne Leppä-aho (MSc 2014), co-supervised with Prof Jukka Corander
- Henning Lübbers (MSc 2012), co-supervised with Prof Jyrki Kivinen
- Anupam Arohi (MSc 2011)
- Yuan Zou (MSc 2011)
- Teemu Pulkkinen (MSc 2011)
- Toni Merivuori (MSc 2009)
- Lari Latvala (MSc 2009), co-supervised with Prof Jouko Laasasenaho
Students interested in MSc/PhD thesis topics related to information theory, statistical modeling, machine learning, artificial intelligence, and digital humanities are welcome to contact me by e-mail (but see disclaimer below).
Disclaimer: If you currently not enrolled at the University of Helsinki, please do not send me e-mail, but contact the Department of Computer Science for information about the application process. Unfortunately I cannot reply to all e-mail inquiries.
``Your act was unwise,'' I exclaimed ``as you see by the
He solemnly eyed me. ``When choosing the course of my action,''
said he, ``I had not the outcome to guide me.''
I am the leader of the Information, Complexity and Learning (ICL) research group, which is a part of the CoSCo research group led by Prof Petri Myllymäki. I'm also affiliated with the Academy of Finland funded Centre of Excellence COIN.
Topics of my interest include the theory and applications of
- machine learning and big data
- probabilistic graphical models
- information theory
- digital humanities
Recent and ongoing work:
- 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.
- 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.
- 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
- 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
(+ supplementary PDF)
- J. Leppä-aho, S. Räisänen, X. Yang, and T. Roos
Markov networks with mutual information, in Proc. 9th Int Conf
on Probabilistic Graphical Models
September 11–14, 2018.
- R.M. Ballardini, K. He, and T. Roos (2018),
Digital distribution of
AI-generated content: Authorship and inventorship in the age of
artificial intelligence, in T. Pihlajarinne, J. Vesala, and
O. Honkkila (editors), Online Distribution of Content in the
EU, Edward Elgar Publishing Ltd. [Disclaimer: This is a draft
for private use only. The material cannot be used for any other
purpose without permission of the publisher.]
- T. Heikkilä and T. Roos (2018),
Quantitative methods for the analysis of Medieval calendars,
Digital Scholarship in the Humanities, 33(4):766–787.
- 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 83:21–42. preprint
- V. Hyvönen, T. Pitkänen, S. Tasoulis,
E. Jääsaari, R. Tuomainen, L. Wang, J. Corander, and T. Roos (2016).
Fast nearest neighbor search through sparse random projections and voting,
in Proc. 2016 IEEE International Conference on Big Data (IEEE Big-Data 2016), Washington DC, Dec. 5–8.
C++ library (with Python bindings) |
- T. Roos (2016). Minimum Description Length Principle,
in Sammut, C. and Webb G.I. (eds), Encyclopedia of Machine Learning and Data Mining, 2016.
- J. Tehrani, Q. Nguyen, and T. Roos, (2016).
Oral fairy tale or literary fake? Investigating the origins of Little
Red Riding Hood using phylogenetic network analysis,
Digital Scholarship in the Humanities 31(3):611–636.
- K. Watanabe and T. Roos, (2015).
Achievability of asymptotic minimax regret
by horizon-dependent and horizon-independent strategies,
- A. Barron, T. Roos, and K. Watanabe, (2014).
Bayesian properties of normalized
maximum likelihood and its fast computation,
in Proc. IEEE International Symposium on Information
IEEE Press, pp. 1667–1671.
- M. Sherman, G. Clark, Y. Yang, S. Sugrim, A. Modig, J. Lindqvist,
A. Oulasvirta, and T. Roos, (2014).
User-generated free-form gestures for authentication: security and memorability,
in Proc. 12th International Conference on Mobile Systems, Applications, and Services (MobiSys-2014), ACM Press, pp. 176–189.
- J. Rissanen, T. Roos, and P. Myllymäki, (2010).
Model selection by sequentially normalized least squares,
of Multivariate Analysis 101:4, 839–849.
| R code
My traveling/conference schedule in 2017:
- Workshop on Evolutionary Networks, Banff Intl. Research Station, Canada, February 13–17.
- 21st CIMO Winter School, Tvärminne Zoological Station, Finland, March 6–11.
- Studia Stemmatologica VII, Rome, Italy, May 17–19.
- Digital Classics/Medieval Studies Workshop, Rome, Italy, May 31–June 1.
- Sanger Institute, Cambridge, UK, August 23–25.
- WITMSE-2017, Paris, France, September 11–13.
We are organized the 10th Workshop on Information Theoretic Methods in Science and Engineering in Paris, September 11–13, 2017. WITMSE-2017
As of 1/2017, I've been appointed as an Associate Professor (tenure-track) at the Department of Computer Science, University of Helsinki.
The 9th Workshop on Information Theoretic Methods in Science and Engineering (WITMSE) was held in Helsinki on 19–21 September 2016. web page.
My traveling/conference schedule in 2016:
- HD Big Data Workshop, Cambridge, UK, January 22.
- Martin Luther University, Halle, Germany, April 25–28.
- Finnish Institute in Rome, Italy, May 6–10.
- Purdue, USA, May 15–20.
- WITMSE-2016, Helsinki, September 19–21.
- University of Melbourne, Australia, October 4–18.
- Eindhoven University of Technology, the Netherlands, December 6.
Between September 21–November 30, 2015, I was a Visiting Scholar at UC Berkeley, USC and UCSD.
The 8th Workshop on Information Theoretic Methods in Science and Engineering (WITMSE) was held in Copenhagen on 24–26 June 2015; co-chairs Harremoës, Forchhammer, Roos & Myllymäki. web page.
My traveling/conference schedule in 2015:
- Finnish Institute in Rome, December 27, 2014–January 4, 2015.
- E-Philology Lectures, Sorbonne University, Paris, January 12.
- ITA-2015, San Diego, February 1–6.
- COST Training School, Rome, 23–25 March.
- VU Amsterdam, May 13.
- University of Lancaster, University of Cambridge, May 18–22.
- COIN day, Stockholm, Sweden, June 15.
- WITMSE-2015, Copenhagen, June 24–26.
- AlCoB-2015, Mexico City, August 4–6.
- UC Berkeley, USC, UCSD, September 21–November 30.
- IEEE Big Data 2015, Santa Clara, CA, USA, October 29–November 1.
I was a member of the organizing committee of the 11th Conference of the European Society for Textual Scholarship (ESTS-2014). The conference was held in Helsinki on Oct 30-Nov 1, 2014.
We organized the 7th Workshop on Information Theoretic Methods in Science and Engineering (WITMSE) in Hawaii on July 5-8, 2014, right after the ISIT symposium. website
In October–December 2013, I was a Fellow at the Finnish Institute in Rome (Villa Lante).
Associated with our CHI-2013 paper, we are lauching a web server for computing the information capacity from your own motion capture data: infocapacity.hiit.fi. Please ask for a beta testing account.
I have been appointed from 4/2013 onwards as an Assistant Professor (tenure-track) at the Department of Computer Science, University of Helsinki.
My traveling/conference schedule in 2014:
- Finnish Institute in Rome, March 28–April 8.
- ISIT-2014 and WITMSE-2014, Hawaii, June 29–July 7.
- ESTS-2014, Helsinki, October 30–November 1.
- Royal Society meeting: Evolutionary analysis beyond the gene, Chicheley Hall, UK, 17–18 November.
I was a co-chair of WITMSE-2013 in Tokyo, Japan, August 26–29.
My traveling/conference schedule in 2013:
- University of Cambridge, UK, January 10–12.
- ITA-2013, San Diego, February 10–15.
- CHI-2013, Paris, April 27–May 2.
- WITMSE-2013, Tokyo, August 26–29.
- Finnish Institute in Rome, October 18–December 28.
Our paper "Information capacity of full-body movements" gets a Best Paper Honorable Mention Award at CHI-2013. If you are planning to attend the conference, please visit our fun interactive Kinect-based demo!
Special issue on selected papers from PGM-2010 in the International Journal of Approximate Reasoning (editors Roos, Myllymäki, Jaakkola): link to editorial and articles.
In January–April 2012, I was a Visiting Fellow at the University of Cambridge.
I was an external evaluator at the PhD thesis defense of Thomas Toftkjær at Aarhus University on January 10, 2012.
My traveling/conference schedule in 2012:
- University of Aarhus, Denmark, January 10.
- University of Cambridge, UK, January 16–April 30.
- ITA-2012, San Diego, February 6–10.
- University of Oxford, UK, March 7–8.
- University of East Anglia, UK, March 22–23.
- Durham University, UK, April 2–5.
- WITMSE 2012, Amsterdam, August 26—30.
- University of Bern, Switzerland, November 22–24.
The Academy of Finland Centre of Excellence COIN starts in 1/2012.
The 5th Brazilian Conference on Statistical Modelling in Insurance and Finance was held in Maresias, Brazil, on April 10–15, 2011. I gave a two-day short course on MDL. lecture notes | slides (day1) | slides (day2)
Tuomas Heikkilä, Petri Myllymäki and I organize a series of stemmatology workshops in Helsinki and elsewhere in 2010–2012. web pages
- Studia Stemmatologica IV, University of Cambridge and Microsoft Research, Cambridge, UK, March 21–26.
- BCSMIF-2011 and University of Sao Paulo, Brazil, April 9–17.
- ICANN-2011, Helsinki, June 14–17.
- ISIT-2011, St. Petersburg, Russia, July 31–August 5.
- WITMSE-2011, Helsinki, August 7–10.
- Studia Stemmatologica V, Rome, October 5–8.
- Nonlinear physics (!), Stockholm, October 18–20.
- ICDM-2011, Vancouver, December 11–14.
4/2011: I was conferred the title Adjunct Professor (in Finnish, dosentti) by the Faculty of Science, and appointed as a senior reseacher at HIIT.
I was invited to the senior program committee of UAI-2011.
The Academy of Finland has graciously decided to fund me under a postdoctoral researcher's project.
Petri Myllymäki, Tommi Jaakkola, and I were the program committee co-chairs of the 5th European Workshop on Probabilistic Graphical Models (PGM-2010) in Helsinki, September 13–15, 2010. web pages
My traveling schedule in 2010:
- MIT, Boston, February 8–April 30.
- Columbia University, New York, February 22–23.
- Yale, New Haven, April 1–2.
- Washington University, St. Louis, April 22–23.
- SCAS, Uppsala, Sweden, June 21–23.
- UCLA & UAI-2010, Los Angeles, July 8–11.
- WITMSE-2010, Tampere, Finland, August 16–18.
- Studia Stemmatologica, Pisa, Italy, November 21–24.
I got the ERCIM (European Research Consortium for Informatics and Mathematics) 2009 Cor Baayen Award.
- ITA-2009, San Diego & HP Labs, Palo Alto, February 8–13.
- ITW-2009, Volos, Greece, June 10–12.
- ISIT-2009, Seoul, Korea, June 28–July 3.
- WITMSE-2009, Tampere, Finland, August 17–19.
- ISTI/CNR & Univ. Pisa, Pisa, Italy, November 5–6.
The Finnish Cultural Foundation has awarded a Science Workshop grant (EUR 200,000) on stemmatology for the years 2009–2010. announcement (w/ fanfares) (in Finnish)
As of August 2008, I have been appointed as post-doctoral researcher at HIIT for three years.
During the Fall term 2007 I lectured the Three Concepts: Information course.
I defended my Ph.D. thesis "Statistical and Information-Theoretic Methods for Data Analysis" on June 9, 2007. The opponent was Prof. Alon Orlitsky (UCSD). Pre-examiners were Prof. Ioan Tabus (Tampere UT) and Prof. Tommi Jaakkola (MIT). electronic version (summary part).
I received a Ph.D. degree (in Computer Science) from the University of Helsinki in 2007. I was supported by HeCSE (Helsinki Graduate School in Computer Science and Engineering). My supervisors were Prof. Henry Tirri (on industrial leave), and Prof. Petri Myllymäki. In addition to computer science I have minors in mathematics and philosophy (see a list of finished courses).
am married to the loveliest girl in the world, the light of my life.
''You are the reason I am. You are all my reasons.''
Since July 31st 2003, the universe revolves around a boy. Since March 1st 2007, we have two boys!
Play a game of Rock, Paper, Scissors: rock beats scissors, paper beats rock, and scissors beat paper. Even such a simple game offers some theoretically interesting problems: Can one predict the other player's choice? What is the best strategy against a good opponent? (Yes, the computer could cheat, but I promise it doesn't.) Such questions were considered by Claude Shannon in the 1950s; see a modern variation of his 'Mind-Reading Machine' based on data-compression (CTW).