Jussi Gillberg

M.Sc. (Tech.), Doctoral Student

Office:

Room T-A340 in Computer Science Building,
Konemiehentie 2, Otaniemi campus area, Espoo

Postal Address:

Aalto University School of Science,
Department of Information and Computer Science,
P.O. Box 15400, FI-00076 Aalto, Finland

Telephone:

+358 50 5380987

Email:

firstname.lastname@aalto.fi

Publications

2014

• Marttinen Pekka, Pirinen Matti, Sarin Antti-Pekka, Gillberg Jussi, Kettunen Johannes, Surakka Ida, Kangas Antti J, Soininen Pasi, O'Reilly Paul, Kaakinen Marika, Kähönen Mika, Lehtimäki Terho, Ala-Korpela Mika, Raitakari Olli T, Salomaa Veikko, Järvelin Marjo-Riitta, Ripatti Samuli, Kaski Samuel. Assessing multivariate gene-metabolome associations with rare variants using Bayesian reduced rank regression. Bioinformatics, 30(14):2026-34, 2014. [More info][Pdf] [BibTeX]
Preferred BibTeX:


@article{
    marttinen2014bioinformatics,
    author = {Marttinen, Pekka and Pirinen, Matti and Sarin, Antti-Pekka and Gillberg, Jussi and Kettunen, Johannes and Surakka, Ida and Kangas, Antti J and Soininen, Pasi and O{'}Reilly, Paul and Kaakinen, Marika and K{\"a}h{\"o}nen, Mika and Lehtim{\"a}ki, Terho and Ala-Korpela, Mika and Raitakari, Olli T and Salomaa, Veikko and J{\"a}rvelin, Marjo-Riitta and Ripatti, Samuli and Kaski, Samuel},
    volume = "30",
    impactfactor = "A1",
    language = "eng",
    title = "Assessing multivariate gene-metabolome associations with rare variants using {B}ayesian reduced rank regression",
    url = "http://bioinformatics.oxfordjournals.org/content/30/14/2026.long",
    journal = "Bioinformatics",
    issn = "1460-2059",
    year = "2014",
    number = "14",
    responsibleauthor = "Marttinen, Pekka and Gillberg, Jussi and Kaski, Samuel",
    juforank = "3",
    il = "yes",
    flags = "COIN HIIT TRITON public",
    unitcode = "T306-99,T312-1",
    kay = "NA",
    pdf = "marttinen_2014_bioinformatics.pdf",
    pages = "2026--34"
}

2013

• Faisal Ali, Gillberg Jussi, Leen Gayle, Peltonen Jaakko. Transfer Learning using a Nonparameteric Sparse Topic Model. Neurocomputing, 112(18):124-137, 2013. [More info][Pdf] [BibTeX]
Preferred BibTeX:


@article{
    Faisal13neurocomp,
    author = "Faisal, Ali and Gillberg, Jussi and Leen, Gayle and Peltonen, Jaakko",
    responsibleauthor = "Faisal, Ali and Gillberg, Jussi and Peltonen, Jaakko",
    respondibleauthor = "Faisal, Ali and Gillberg, Jussi and Peltonen Jaakko",
    unitcode = "T306-99,T312-1",
    language = "eng",
    title = "Transfer Learning using a Nonparameteric Sparse Topic Model",
    url = "http://dx.doi.org/10.1016/j.neucom.2012.12.038",
    country = "Netherlands",
    journal = "Neurocomputing",
    issn = "0925-2312",
    year = "2013",
    number = "18",
    volume = "112",
    doi = "10.1016/j.neucom.2012.12.038",
    juforank = "1",
    il = "no",
    flags = "COIN HIIT public",
    pdf = "Faisal13ncomp.pdf",
    kay = "NA",
    impactfactor = "A1",
    pages = "124--137"
}

• Marttinen P., Gillberg J., Havulinna A., Corander J., Kaski S.. Genome-wide association studies with high-dimensional phenotypes. Statistical Applications in Genetics and Molecular Biology, 12(4):413-431, 2013. [Pdf] [BibTeX]
Preferred BibTeX:


@article{
    marttinen13sagmb,
    author = "Marttinen, P. and Gillberg, J. and Havulinna, A. and Corander, J. and Kaski, S.",
    volume = "12",
    impactfactor = "A1",
    language = "eng",
    title = "Genome-wide association studies with high-dimensional phenotypes",
    country = "Germany",
    journal = "Statistical Applications in Genetics and Molecular Biology",
    issn = "1544-6115",
    year = "2013",
    number = "4",
    responsibleauthor = "Marttinen, Pekka and Gillberg, Jussi and Kaski, Samuel",
    juforank = "1",
    il = "no",
    flags = "COIN HIIT public",
    unitcode = "T306-99,T312-1",
    kay = "B",
    pdf = "marttinen13sagmb.pdf",
    pages = "413-431"
}

2012

• Faisal Ali, Gillberg Jussi, Peltonen Jaakko, Leen Gayle, Kaski Samuel. Sparse Nonparametric Topic Model for Transfer Learning. In Proceedings of 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, pages 269-274, 2012. [Pdf] [BibTeX]
Preferred BibTeX:


@inproceedings{
    Faisal12esann,
    author = "Faisal, Ali and Gillberg, Jussi and Peltonen, Jaakko and Leen, Gayle and Kaski, Samuel",
    responsibleauthor = "Faisal, Ali and Gillberg, Jussi and Peltonen, Jaakko and Kaski, Samuel",
    eventtime = "April 25-27",
    isbn = "978-2-87419-049-0",
    language = "eng",
    title = "Sparse Nonparametric Topic Model for Transfer Learning",
    eventlocation = "Bruges, Belgium",
    booktitle = "Proceedings of 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning",
    corerank = "B",
    unitcode = "T306-99,T312-1",
    juforank = "1",
    flags = "COIN HIIT public",
    il = "no",
    year = "2012",
    pdf = "faisal12esann.pdf",
    impactfactor = "A4",
    pages = "269-274"
}

2011

• Gillberg Jussi. Targeted learning by imposing asymmetric sparsity. 2011. [BibTeX]
Preferred BibTeX:


@mastersthesis{
    Gillberg11mscthesis,
    author = "Gillberg, Jussi",
    school = "Aalto University",
    language = "eng",
    title = "Targeted learning by imposing asymmetric sparsity",
    abstract = "Modern data sets often suffer from the problem of having measurements from very few samples. The small sample size makes modeling such data sets very difficult, as models easily overfit to the data. Many approaches to alleviate the problem have been taken. \par One such approach is multi-task learning, a subfield of statistical machine learning, in which multiple data sets are modeled simultaneously. More generally, multiple learning tasks may be learnt simultaneously to achieve better performance in each. \par Another approach to the problem of having too few samples is to to prevent overfitting by constraining the model by making suitable assumptions. \par Traditional multi-task methods treat all learning tasks and data sets equally, even thought we are usually mostly interested in learning one of them. This thesis is a case study about promoting predictive performance in a specific data set of interest in a multi-task setting by constraining the models for the learning tasks unevenly. The model for the data set of interest more sparse as compared to the models for the secondary data sets. \par To study the new approach, the research question is limited to the very specific and popular family of so-called topic models using Bayesian nonparametric priors. A new model is presented which enables us to study the effects of asymmetric sparsity. \par The effects of asymmetric sparsity are studied by using the new model on real data and toy data. Subtle beneficial effects of asymmetric sparsity are observed on toy data and the new model performs comparably to existing state-of-the-art methods on real data.",
    year = "2011",
    month = "June",
    responsibleauthor = "Gillberg, Jussi",
    flags = "AIRC HIIT public",
    il = "no",
    address = "Department of Information and Computer Science",
    keywords = "asymmetric multi-task learning, latent Dirichlet allocation, nonparametric Bayesian statistics, small sample size, sparsity",
    unitcode = "T306=99, T312=1",
    pdf = "gillberg11.pdf"
}