Jakub Tomczak

I am a deep learning research engineer (Engineer, Staff) in Qualcomm AI Rersearch in Amsterdam. Previously, I was a Marie Sklodowska-Curie fellow in Max Welling's group at University of Amsterdam. My main research interests include deep learning, Bayesian inference and deep generative modeling. Full CV: [here].

News

2018/10/03

A paper is accepted to Neural Processing Letters.

2018/05/16

Two papers are accepted as oral presentations at UAI 2018.

2018/05/16

Two papers are accepted at MIDL 2018.

2018/06/15

One paper is accepted at TADGM @ ICML 2018.

2018/05/11

One paper is accepted at ICML 2018.

2017/12/22

One paper is accepted as an oral presentation at AISTATS 2018.

2017/05/11

One paper is accepted at Benelearn 2017.

2016/11/30

One paper is accepted at Bayesian Deep Learning @ NIPS 2016.

2016/10/25

One paper is accepted at Machine Learning in Computational Biology @ NIPS 2016.

Publications



Journal articles

  1. Jakub M. Tomczak, Szymon Zaręba, Siamak Ravanbakhsh, Russell Greiner, Low-Dimensional Perturb-and-MAP Approach for Learning Restricted Boltzmann Machines, Neural Processing Letterss, online 3 October 2017, DOI: 10.1007/s11063-018-9923-4, [SpringerLink], [pdf]
  2. Magda Drewniak, Ewelina Węglarz-Tomczak, Katarzyna Ożga, Ewa Rudzińska-Szostak, Katarzyna Macegoniuk, Jakub M. Tomczak, Magdalena Bejger, Wojciech Rypniewski, Łukasz Berlicki, Helix-loop-helix peptide foldamers and their use in the construction of hydrolase mimetics, Bioorganic Chemistry, Vol. 81, pp. 356-361, DOI: 10.1016/j.bioorg.2018.07.012, [ScienceDirect]
  3. Adam Gonczarek, Jakub M. Tomczak, Szymon Zaręba, Joanna Kaczmar, Piotr Dąbrowski, Michał Walczak, Interaction prediction in structure-based virtual screening using deep learning, Computers in Biology and Medicine, online 14 September 2017, DOI: 10.1016/j.compbiomed.2017.09.007, [ScienceDirect], [pdf]
  4. Maciej Zięba, Sebastian Tomczak, Jakub M. Tomczak, Ensemble Boosted Trees with Synthetic Features Generation in Application to Bankruptcy Prediction, Expert Systems with Applications, Vol. 58, pp. 593-101, 2016, DOI: 10.1016/j.eswa.2016.04.001, [ScienceDirect], [pdf], [Draft]
  5. Jakub M. Tomczak, On some properties of the low-dimensional Gumbel perturbations in the Perturb-and-MAP model, Statistics and Probability Letters, ACCEPTED March 29 2016, DOI: 10.1016/j.spl.2016.03.019, [ScienceDirect], [pdf]
  6. Jakub M. Tomczak, Adam Gonczarek, Learning invariant features using Subspace Restricted Boltzmann Machine, Neural Processing Letters, ACCEPTED March 29 2016, DOI: 10.1007/s11063-016-9519-9, [SpringerLink], [pdf], [Draft]
  7. Adam Gonczarek, Jakub M. Tomczak, Articulated tracking with manifold regularized particle filter, Machine Vision and Applications, Volume 27, Issue 2, pp 275–286, DOI:10.1007/s00138-016-0748-8, [SpringerLink], [pdf]
  8. Jakub M. Tomczak, Learning Informative Features from Restricted Boltzmann Machines, Neural Processing Letters, DOI:10.1007/s11063-015-9491-9, [SpringerLink], [pdf]
  9. Jakub M. Tomczak, Maciej Zięba, Probabilistic combination of classification rules and its application to medical diagnosis, Machine Learning, Vol. 101, Issue 1, pp. 105-135, DOI:10.1007/s10994-015-5508-x, [SpringerLink], [pdf]
  10. Jakub M. Tomczak, Maciej Zięba, Classification Restricted Boltzmann Machine for comprehensible credit scoring model, Expert Systems with Applications, Volume 42, Issue 4, March 2015, DOI:10.1016/j.eswa.2014.10.016, [ScienceDirect], [pdf]
  11. Maciej Zięba, Jakub M. Tomczak, Boosted SVM with active learning strategy for imbalanced data, Soft Computing, August 2014, Pages 99–108, DOI: 10.1007/s00500-014-1407-5, [Scopus], [pdf]
  12. Maciej Zięba, Jakub M. Tomczak, Jerzy Świątek, Marek Lubicz, Boosted SVM for extracting rules from imbalanced data in application to prediction of the post-operative life expectancy in the lung cancer patients, Applied Soft Computing, Volume 14, Part A, January 2014, Pages 99–108, DOI: 10.1016/j.asoc.2013.07.016, [ScienceDirect], [pdf], [DATA] , [UCI ML Repository]
  13. Jakub M. Tomczak, Adam Gonczarek, Decision rules extraction from data stream in the presence of changing context for diabetes treatment, Knowledge and Information Systems, 2013, Vol. 34, Issue 3, pp. 521-546, DOI: 10.1007/s10115-012-0488-7 [SpringerLink], [pdf]

Conferences (selected)

  1. Tim Davidson, Luca Falorsi, Nicola de Cao, Thomas Kipf, Jakub M. Tomczak, Hyperspherical Variational Auto-Encoders, UAI, Monterey, California, the USA, 2018, [arxiv], [PDF], [CODE], [BLOG]
  2. Rianne van den Berg, Leonard Hasenclever, Jakub M. Tomczak, Max Welling, Sylvester Normalizing Flow for Variational Inference, UAI, Monterey, California, the USA, 2018, [arxiv], [PDF]
  3. Philip Botros, Jakub M. Tomczak, Hierarchical VampPrior Variational Fair Auto-Encoder, ICML Workshop on Theoretical Foundations and Applications of Deep Generative Models, Stockholm, Sweden, 2018, [arxiv], [PDF]
  4. Maximilian Ilse, Jakub M. Tomczak, Max Welling, Attention-based Deep Multiple Instance Learning, ICML, Stockholm, Sweden, 2018, [arxiv], [PDF], [CODE]
  5. Nathan Ing, Beatrice S. Knudsen, Arkadiusz Gertych, Jakub M. Tomczak, Max Welling, Isla P. Garraway, Eric Miller, A deep multiple instance model to predict prostate cancer metastasis from nuclear morphology, Medical Imaging with Deep Learning (MIDL), Amsterdam, the Netherlands, 2018, [OpenReview], [PDF]
  6. Jakub M. Tomczak, Maximilian Ilse, Max Welling, Marnix Jansen, H.G Coleman, Marit Lucas, Kikki de Laat, Martijn de Bruin, Henk Marquering, Myrtle J. van der Wel, Onno J. de Boer, C. Dilara Savci Heijink, Sybren L. Meijer, Histopathological classification of precursor lesions of esophageal adenocarcinoma: A Deep Multiple Instance Learning Approach, Medical Imaging with Deep Learning (MIDL), Amsterdam, the Netherlands, 2018, [OpenReview], [PDF]
  7. Jakub M. Tomczak, Max Welling, VAE with a VampPrior, AISTATS, the Canary Islands, 2018, [arxiv], [PDF], [CODE]
  8. Jakub M. Tomczak, Maximilian Ilse, Max Welling, Deep Learning with Permutation-invariant Operator for Multi-instance Histopathology Classification, NIPS Workshop on Medical Imaging Meets NIPS, Long Beach, the USA, 2017 [arxiv], [PDF]
  9. Leonard Hasenclever, Jakub M. Tomczak, Rianne van den Berg, Max Welling, Variational Inference with Orthogonal Normalizing Flows, NIPS Workshop on Bayesian Deep Learning, Long Beach, the USA, 2017, [PDF]
  10. Jakub M. Tomczak, Max Welling, Improving Variational Auto-Encoders using convex combination linear Inverse Autoregressive Flow, Benelearn 2017, Eindhoven, the Netherlands, 2017 [arxiv], [PDF], [CODE]
  11. Jakub M. Tomczak, Max Welling, Improving Variational Auto-Encoders using Householder Flow, NIPS Workshop on Bayesian Deep Learning, Barcelona, Spain, 2016 [arxiv], [PDF], [CODE]
  12. Adam Gonczarek, Jakub M. Tomczak, Szymon Zaręba, Joanna Kaczmar, Piotr Dąbrowski, Michał J. Walczak, Learning Deep Architectures for Interaction Prediction in Structure-based Virtual Screening, NIPS Workshop on Machine Learning in Computational Biology, Barcelona, Spain, 2016 [arxiv], [PDF]

Reviewer



Conferences

ICML 2019, ICLR (2019), AISTATS (2019), NIPS (2018), MIDL (2018), NIPS Workshop on Bayesian Deep Learning (2017, 2018), ISAT (2012-2016), ICSS (2014, 2016)

Journals

IEEE Transactions on Pattern Analysis and Machine Intelligence, Bioinformatics, Medical Image Analysis, Expert Systems with Applications, BMC Bioinformatics, IEEE Journal of Biomedical and Health Informatics, IEEE Transactions on Neural Systems \& Rehabilitation Engineering, European Journal of Operation Research, Neural Processing Letters, Operations Research and Decisions, Knowledge-Based Systems, International Journal of Approximate Reasoning, Biocybernetics and Biomedical Engineering