Marek Śmieja
Jagiellonian University
Institute of Computer Science and Computational Mathematics

Books

  • Jacek Tabor, Marek Śmieja, Łukasz Struski, Przemysław Spurek, Maciej Wołczyk

    Głębokie uczenie. Wprowadzenie (en. Deep learning. Introduction),

    Helion, pp. 184, 2022

    (preview) (published)

Journal papers

  • Bartosz Wójcik, Jacek Grela, Marek Śmieja, Krzysztof Misztal, Jacek Tabor

    SLOVA: Uncertainty estimation using single label one-vs-all classifier,

    Applied Soft Computing, 126, pp.12, 2022

    (preprint) (published)

  • Lukasz Maziarka, Marek Smieja, Marcin Sendera, Lukasz Struski, Jacek Tabor, Przemyslaw Spurek

    OneFlow: One-class flow for anomaly detection based on a minimal volume region,

    IEEE Transactions on Pattern Analysis and Machine Intelligence, DOI: 10.1109/TPAMI.2021.3108223, 2021

    (preprint) (published)

  • Marek Śmieja, Maciej Wołczyk, Jacek Tabor, Bernhard C. Geiger

    SeGMA: Semi-Supervised Gaussian Mixture Autoencoder,

    IEEE Transactions on Neural Networks and Learning Systems, 32/9, pp. 3930-3941, 2021

    (preprint) (published)

  • Dawid Warszycki, Łukasz Struski, Marek Śmieja, Rafał Kafel, Rafał Kurczab

    Pharmacoprint – a combination of pharmacophore fingerprint and artificial intelligence as a tool for computer-aided drug design,

    Journal of Chemical Information and Modeling, 61, pp. 5054-5065, 2021

    (published)

  • Marek Śmieja, Łukasz Struski, Mario A. T. Figueiredo

    A Classification-Based Approach to Semi-Supervised Clustering with Pairwise Constraints,

    Neural Networks, 127, pp. 193-203, 2020

    (preprint) (published)

  • Łukasz Struski, Marek Śmieja, Jacek Tabor

    Pointed subspace approach to incomplete data,

    Journal of Classification, 37, pp.42-57, 2020

    (preprint) (published)

  • Marek Śmieja, Krzysztof Hajto, Jacek Tabor

    Efficient mixture model for clustering of sparse high dimensional binary data,

    Data Mining and Knowledge Discovery, 33/6, pp. 1583--1624, 2019

    (preprint) (published)

  • Marek Śmieja, Łukasz Struski, Jacek Tabor, Mateusz Marzec

    Generalized RBF kernel for incomplete data,

    Knowledge-Based Systems, 173, pp. 150-162, 2019

    (preprint) (published)

  • Łukasz Struski, Przemysław Spurek, Jacek Tabor, Marek Śmieja

    Projected memory clustering,

    Pattern Recognition Letters, 123, pp. 9-15, 2019

    (published)

  • Marek Śmieja, Jacek Tabor, Przemysław Spurek

    SVM with a neutral class,

    Pattern Analysis and Applicatins, 22/2, pp. 573-582, 2019

    (published)

  • Przemysław Spurek, Jacek Tabor, Łukasz Struski, Marek Śmieja

    Fast Independent Component Analysis algorithm with a simple closed-form solution,

    Konwledge-Based Systems, 161, pp. 26-34, 2018

    (published)

  • Marek Śmieja, Oleksandr Myronov, Jacek Tabor

    Semi-supervised discriminative clustering with graph regularization,

    Konwledge-Based Systems, 151, pp. 24-36, 2018

    (preprint) (published)

  • Marek Śmieja, Bernhard C. Geiger

    Semi-supervised cross-entropy clustering with information bottleneck constraint,

    Information Sciences, 421, pp. 245-271, 2017

    (preprint) (published)

  • Marek Śmieja, Łukasz Struski, Jacek Tabor

    Semi-supervised model-based clustering with controlled clusters leakage,

    Expert Systems with Applications, 85, pp. 146-157, 2017

    (preprint) (published)

  • Marek Śmieja, Magdalena Wiercioch

    Constrained clustering with a complex cluster structure,

    Advances in Data Analysis and Classification, 11/3, pp. 493-518, 2017

    (published)

  • Dawid Warszycki, Marek Śmieja, Rafał Kafel

    Practical application of the Average Information Content Maximization (AIC-MAX) algorithm – selection of the most important structural features for serotonin receptor ligands,

    Molecular Diversity, 21/2, pp. 407–412, 2017

    (published)

  • Przemysław Spurek, Konrad Kamieniecki, Jacek Tabor, Krzysztof Misztal, Marek Śmieja

    R Package CEC,

    Neurocomputing, 237, pp. 410-413, 2017,

    (preprint) (published)

  • Marek Śmieja, Dawid Warszycki

    Average Information Content Maximization - a new approach for fingerprint hybridization and reduction,

    PLoS ONE, 11/1, pp. e0146666, 2016

    (published)

  • Marek Śmieja, Jacek Tabor

    Entropy approximation in lossy source coding problem,

    Entropy, 17/5, pp. 3400-3418, 2015

    (published)

  • Marek Śmieja

    Weighted approach to general entropy function,

    IMA Journal of Mathematical Control and Information, 32/2, pp. 329-327, 2015

    (preprint) (published)

  • Marek Śmieja, Dawid Warszycki, Jacek Tabor, Andrzej Bojarski

    Asymmetric Clustering Index in a case study of 5-HT1A receptor ligands,

    PLoS ONE, 9/7, pp. e102069, 2014

    (published)

  • Marek Śmieja, Jacek Tabor,

    Entropy of the mixture of sources and entropy dimension,

    IEEE Transactions on Information Theory, 58/5, pp. 2719-2728, 2012,

    (preprint) (published)

Conference papers

  • Łukasz Struski, Tomasz Danel, Marek Śmieja, Jacek Tabor, Bartosz Zieliński

    SONG: Self-Organizing Neural Graphs,

    IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2023), pp. 10, 2023

    (preprint) (published)

  • Paweł Morawiecki, Andrii Krutsylo, Maciej Wołczyk, Marek Śmieja

    Hebbian Continual Representation Learning,

    HICSS Hawaii International Conference on System Sciences (HICSS 2023), pp. 10, 2023

    (preprint) (published)

  • Maciej Wołczyk, Magdalena Proszewska, Łukasz Maziarka, Maciej Zięba, Patryk Wielopolski, Rafał Kurczab, Marek Śmieja

    PluGeN: Multi-Label Conditional Generation From Pre-Trained Models,

    AAAI Conference on Artificial Intelligence (AAAI 2022), pp. 10, 2022

    (preprint) (published)

  • Marcin Przewięźlikowski, Marek Śmieja, Łukasz Struski, Jacek Tabor

    MisConv: Convolutional Neural Networks for Missing Data,

    Winter Conference on Applications of Computer Vision (WACV 2022), pp. 10, 2022

    (preprint) (published)

  • Sophie Steger, Bernhard C. Geiger, Marek Śmieja

    Semi-Supervised Clustering via Information-Theoretic Markov Chain Aggregation,

    ACM/SIGAPP Symposium On Applied Computing (SAC 2022), pp. 4, 2022

    (preprint) (published)

  • Maciej Wołczyk, Bartosz Wójcik, Klaudia Bałazy, Igor Podolak, Jacek Tabor, Marek Śmieja, Tomasz Trzciński

    Zero Time Waste: Recycling Predictions in Early Exit Neural Networks,

    Advances in Neural Information Processing Systems 34 (NeurIPS 2021), pp. 10, 2021

    (preprint) (published)

  • Bartosz Wójcik, Paweł Morawiecki, Marek Śmieja, Tomasz Krzyżek, Przemysław Spurek, Jacek Tabor

    Adversarial Examples Detection and Analysis with Layer-wise Autoencoders,

    IEEE International Conference on Tools with Artificial Intelligence (ICTAI 2021), pp. 5, 2021

    (preprint) (published)

  • Marek Śmieja, Maciej Kołomycki, Łukasz Struski, Mateusz Juda, Mario A. T. Figueiredo

    Iterative Imputation of Missing Data using Auto-encoder Dynamics,

    International Conference on Neural Information Processing (ICONIP 2020), pp. 258-269, 2020

    (preprint) (published)

  • Tomasz Danel, Marek Śmieja, Łukasz Struski, Przemysław Spurek, Łukasz Maziarka

    Processing of incomplete images by (graph) convolutional neural networks,

    International Conference on Neural Information Processing (ICONIP 2020), pp. 512-523, 2020

    (preprint) (published)

  • Tomasz Danel, Przemysław Spurek, Jacek Tabor, Marek Śmieja, Łukasz Struski, Agnieszka Słowik, Łukasz Maziarka

    Spatial Graph Convolutional Networks,

    International Conference on Neural Information Processing (ICONIP 2020), pp. 668-675, 2020

    (preprint) (published)

  • Marcin Przewięźlikowski, Marek Śmieja, Łukasz Struski

    Estimating conditional density of missing values using deep Gaussian mixture model,

    International Conference on Neural Information Processing (ICONIP 2020), pp. 220-231, 2020

    (preprint) (published)

  • Paweł Morawiecki, Przemysław Spurek, Marek Śmieja, Jacek Tabor

    Fast and Stable Interval Bounds Propagation for Training Verifiably Robust Models,

    European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2020), pp. 6, 2020

    (preprint) (published)

  • Sylwester Klocek, Łukasz Maziarka, Maciej Wołczyk, Jacek Tabor, Jakub Nowak, Marek Śmieja

    Hypernetwork functional image representation,

    International Conference on Artificial Neural Networks (ICANN 2019), pp. 496-510, 2019

    (preprint) (published)

  • Łukasz Maziarka, Marek Śmieja, Aleksandra Nowak, Jacek Tabor, Łukasz Struski, Przemysław Spurek

    Set Aggregation Network as a Trainable Pooling Layer,

    International Conference on Neural Information Processing (ICONIP 2019), pp. 419-431, 2019

    (preprint) (published)

  • Marek Śmieja, Łukasz Struski, Jacek Tabor, Bartosz Zieliński, Przemysław Spurek

    Processing of missing data by neural networks,

    Advances in Neural Information Processing Systems 31 (NeurIPS 2018), pp. 2719--2729, 2018

    (preprint) (published)

  • Łukasz Struski, Marek Śmieja, Bartosz Zieliński, Jacek Tabor

    Regression SVM for incomplete data,

    International Conference on Theoretical Foundations of Machine Learning (TFML 2017),

    published in Schedae Informaticae, pp.13, 2017

    (preprint) (published)

  • Marek Śmieja, Szymon Nakoneczny, Jacek Tabor

    Fast entropy clustering of sparse high dimensional binary data,

    IEEE International Joint Conference on Neural Networks (IJCNN 2016), pp. 2397-2404, 2016

    (preprint) (published)

  • Marek Śmieja, Jacek Tabor

    Spherical Wards clustering and generalized Voronoi diagrams,

    IEEE International Conference on Data Science and Advanced Analytics (DSAA 2015), pp. 1-10, 36678 2015

    (preprint) (published)

  • Magdalena Wiercioch, Marek Śmieja

    Mixture of metrics optimization for machine learning problems,

    International Conference on Theoretical Foundations of Machine Learning (TFML 2015),

    published in Schedae Informaticae, 24, pp.79-88, 2015

    (preprint) (published)

  • Przemysław Spurek, Marek Śmieja, Krzysztof Misztal

    Subspaces clustering approach to lossy image compression,

    International Conference on Computer Information Systems and Industrial Management Applications (CISIM 2014), pp. 571-579, 2014

    (preprint) (published)

  • Marek Śmieja, Jacek Tabor

    Renyi entropy dimension of the mixture of measures,

    Science and Information Conference (SAI 2014), pp. 685 - 689, 2014

    (preprint) (published)

  • Marek Śmieja, Jacek Tabor

    Image segmentation with use of cross-entropy clustering,

    International Conference on Computer Recognition Systems (CORES 2013), pp. 403-409, 2013,

    (preprint) (published)

Workshop materials

  • Tomasz Danel, Marek Śmieja, Łukasz Struski, Przemysław Spurek, Łukasz Maziarka

    Processing of incomplete images by (graph) convolutional neural networks,

    ICML Workshop on the Art of Learning with Missing Values (Artemiss 2020),

    available online, pp. 5, 2020

    (published)

  • Marcin Przewięźlikowski, Marek Śmieja, Łukasz Struski

    Estimating conditional density of missing values using deep Gaussian mixture model,

    ICML Workshop on the Art of Learning with Missing Values (Artemiss 2020),

    available online, pp. 7, 2020

    (published)

  • Marcin Sendera, Marek Śmieja, Łukasz Maziarka, Łukasz Struski, Przemysław Spurek, Jacek Tabor

    Flow-based SVDD for anomaly detection,

    ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (INNF+ 2020),

    available online, pp. 4, 2020

    (published)

  • Marek Śmieja, Maciej Kołomycki, Łukasz Struski, Mateusz Juda, Mário A. T. Figueiredo

    Can auto-encoders help with filling missing data?,

    ICLR workshop on Integration of Deep Neural Models and Differential Equations (DeepDiffEq 2020),

    available online, pp. 6, 2020

    (published)

  • Maciej Wołczyk, Jacek Tabor, Marek Śmieja, Szymon Maszke

    Biologically-Inspired Spatial Neural Networks,

    NeurIPS workshop on Real Neurons & Hidden Units (NeuroAI 2019),

    available online, pp. 5, 2019

    (preprint) (published)

  • Szymon Nakoneczny, Marek Śmieja

    Natural language processing methods in biological activity prediction,

    ECML PKDD workshop on Machine Learning and Life Science (MLLS 2016)

    published by Wroclaw University of Technology, pp. 25-36, 2016

    (published)

  • Magdalena Wiercioch, Marek Śmieja, Jacek Tabor

    Probability Index of Metric Correspondence as a measure of visualization reliability,

    ECML PKDD workshop on Machine Learning and Life Science (MLLS 2015),

    published by Wroclaw University of Technology, pp. 16-27, 2015

    (preprint) (published)