Welcome to the homepage of the Machine Learning research group at the Institute of Computer Science, University of Tartu. Our main research topics are supervised learning (classifier adaptation, calibration, evaluation and ensembles) and applications of machine learning and deep learning for neuroscience, biology and health.


Academic staff:

Meelis Kull
Sven Laur
Leopold Parts
Raul Vicente Zafra

PhD students:

Mari-Liis Allikivi
Markus Kängsepp
Dmytro Fishman
Ilja Kuzovkin
Daniel Majoral

Master students in 2017/18:

Samreen Hassan
Theodore Heiser
Markus Kängsepp
Anton Potapchuk
Sten-Oliver Salumaa
Novin Shahroudi
Prabhant Singh
Martin Valgur
Brait Õispuu

Bachelor students in 2017/18:

Andreas Baum
Cardo Kambla
Joonas Kriisk
Laura Ruusmann
Egert Teesaar
Henry Teigar
Kristiina Uusna



2018 Spring

Machine Learning (6 ects) – lecturer: Meelis Kull – teaching assistants: Mari-Liis Allikivi, Liis Kolberg

Introduction to Computational Neuroscience (6 ects) – lecturer: Raul Vicente Zafra – teaching assistants: Aqeel Labash, Daniel Majoral Lopez

Computational Neuroscience Seminar (3 ects) – instructor: Raul Vicente Zafra

Special Course in Machine Learning: M4 Regression Competition (3 ects) – instructor: Meelis Kull

2017 Fall

Data Mining (6 ects)- lecturer: Meelis Kull – teaching assistants: Mari-Liis Allikivi, Dmytro Fishman

Neural Networks (6 ects)- lecturer: Raul Vicente Zafra – teaching assistants: Tambet Matiisen, Ardi Tampuu

Computational Neuroscience Seminar (3 ects) – instructor: Raul Vicente Zafra

Special Course in Machine Learning: Ensemble methods (3 ects) – instructor: Meelis Kull

Selected publications

Activations of Deep Convolutional Neural Network are Aligned with Gamma Band Activity of Human Visual Cortex
I Kuzovkin, R Vicente, M Petton, J Lachaux, M Baciu, P Kahane, S Rheims, JR Vidal, J Aru
Journal: To appear in Communications Biology, bioRxiv, 133694

Efficient neural decoding of self-location with a deep recurrent network
A Tampuu, T Matiisen, HF Ólafsdóttir, C Barry, and R Vicente
Journal: preprint (bioRxiv) 242867

JACKS: joint analysis of CRISPR/Cas9 knock-out screens
F Allen, F Behan, F Iorio, K Yusa, M Garnett, L Parts
Journal: preprint (bioRxiv)

Releasing eHealth Analytics into the Wild: Lessons Learnt from the SPHERE Project
T Diethe, M Holmes, M Kull, M Perello Nieto, K Sokol, H Song, E Tonkin, N Twomey, P Flach
Conference: KDD Applied Data Science track

Accurate Classification of Protein Subcellular Localization from High-Throughput Microscopy Images Using Deep Learning
T Pärnamaa, L Parts
Journal: G3: Genes, Genomes, Genetics

Beyond sigmoids: How to obtain well-calibrated probabilities from binary classifiers with beta calibration
M Kull, TM Silva Filho, P Flach
Journal: Electronic Journal of Statistics

Bivariate Partial Information Decomposition: The Optimization Perspective
M Abdullah, DO Theis, R Vicente
Journal: Entropy 19, no. 10, 530

Computational biology: deep learning
W Jones, K Alasoo, D Fishman, L Parts
Journal: Emerging Topics in Life Sciences

Linear Ensembles of Word Embedding Models.
A Muromägi, K Sirts, S Laur
Conference: NODALIDA (Nordic Conference on Computational Linguistics)

Multiagent cooperation and competition with deep reinforcement learning
A Tampuu, T Matiisen, D Kodelja, I Kuzovkin, K Korjus, Juhan Aru, Jaan Aru, R Vicente
Journal: PloS one 12, no. 4: e0172395

An efficient data partitioning to improve classification performance while keeping parameters interpretable
K Korjus, MN Hebart, R Vicente
Journal: PloS one 11, no. 8, e0161788.

Cost-sensitive boosting algorithms: Do we really need them?
N Nikolaou, N Edakunni, M Kull, P Flach, G Brown
Journal: Machine Learning
2016 – ACM Computing Reviews named it as one of the most notable items published in computer science in 2016

Deep learning for computational biology
C Angermueller, T Pärnamaa, L Parts, O Stegle
Journal: Molecular Systems Biology

EstNLTK – NLP Toolkit for Estonian
S Orasmaa, T Petmanson, A Tkachenko, S Laur, HJ Kaalep
Conference: LREC (International Conference on Language Resources and Evaluation)

Predicting quantitative traits from genome and phenome with near perfect accuracy
K Märtens, J Hallin, J Warringer, G Liti, L Parts
Journal: Nature Communications

Reframing in context: A systematic approach for model reuse in machine learning
J Hernández-Orallo, A Martínez-Usó, RBC Prudêncio, M Kull, P Flach, CF Ahmed, N Lachiche
Journal: AI Communications

The SPHERE challenge: Activity recognition with multimodal sensor data
N Twomey, T Diethe, M Kull, H Song, M Camplani, S Hannuna, X Fafoutis, …
arXiv preprint arXiv:1603.00797

Precision-recall-gain curves: PR analysis done right
P Flach, M Kull
Conference: NIPS’15 – Advances in Neural Information Processing Systems

Privacy-Preserving Statistical Data Analysis on Federated Databases.
D Bogdanov, L Kamm, S Laur, P Pruulmann-Vengerfeldt, R Talviste, J Willemson
Conference: APF (Annual Privacy Forum)

Reliability maps: a tool to enhance probability estimates and improve classification accuracy
M Kull, PA Flach
Conference: ECML-PKDD’14 – The European Conference on Machine Learning & Principles and Practice of Knowledge Discovery in Databases – Best paper award

A new way to protect privacy in large-scale genome-wide association studies.
L Kamm, D Bogdanov, S Laur, J Vilo
Journal: Bioinformatics