Zmiana języka

Projects search

Efficient unsupervised learning with applications in deep learning

2017/25/B/ST6/01271

Keywords

Descriptors

  • ST6_11: Uczenie maszynowe, statystyczne przetwarzanie danych i zastosowanie w przetwarzaniu sygnałów

Panel

ST6 – Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems

Host institution

Uniwersytet Jagielloński, Wydział Matematyki i Informatyki

Voivodeship: małopolskie

Other projects carried out by the institution »

Principal investigator (from the host institution)

prof. Jacek Tabor

Number of co-investigators in the project: 8

Call

OPUS 13 – announced on 2017-03-15

Amount awarded
573 200 PLN
Project start date
2018-02-09
Project end date
2021-02-08
Project duration
36 months (the same as in the proposal)
Project status
Project settled

Project description

Download the project description in a pdf file

Note — project descriptions were prepared by the authors of the applications themselves and placed in the system in an unchanged form.

Equipment purchased [PL]

  1. Klaster komputerowy. Cost: 100 000 PLN
  2. serwer obliczeniowy.
  3. stacja robocza. Cost: 23 975 PLN
  4. tablet. Cost: 5 977 PLN

Information in the final report

Publication in academic press/journals (7)

  1. SeGMA: Semi-Supervised Gaussian Mixture Autoencoder

    Authors:
    Marek Śmieja, Maciej Wołczyk, Jacek Tabor, Bernhard C. Geiger
    Academic press:
    IEEE Transactions on Neural Networks and Learning Systems (year: 2020, volume: -, pages: 46034), Publisher: IEEE
    Status:
    Published
    DOI:
    10.1109/TNNLS.2020.3016221 – link to the publication

  2. Fast independent component analysis algorithm with a simple closed-form solution.

    Authors:
    Przemysław Spurek, Jacek Tabor, Łukasz Struski, Marek Śmieja
    Academic press:
    Knowledge-Based Systems 161 (2018): 26-34. (year: 2018, volume: 161, pages: 26-34), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.knosys.2018.07.027 – link to the publication

  3. Efficient mixture model for clustering of sparse high dimensional binary data

    Authors:
    Marek Śmieja, Krzysztof Hajto, Jacek Tabor
    Academic press:
    Data Mining and Knowledge Discovery (year: 2019, volume: 33, pages: 1583--1624), Publisher: Springer
    Status:
    Published
    DOI:
    10.1007/s10618-019-00635-1 – link to the publication

  4. Projected memory clustering

    Authors:
    Łukasz Struski, Przemysław Spurek, Jacek Tabor, Marek Śmieja
    Academic press:
    Pattern Recognition Letters (year: 2019, volume: 123, pages: 46280), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.patrec.2019.02.023 – link to the publication

  5. A classification-based approach to semi-supervised clustering with pairwise constraints

    Authors:
    Marek Śmieja, Łukasz Struski, Mario A. T. Figueiredo
    Academic press:
    Neural Networks (year: 2020, volume: 127, pages: 193-203), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.neunet.2020.04.017 – link to the publication

  6. Online updating of active function cross-entropy clustering

    Authors:
    Przemysław Spurek, Jacek Tabor, Krzysztof Byrski
    Academic press:
    Pattern Analysis and Applications (year: 2019, volume: 22, pages: 1409-1425), Publisher: Springer
    Status:
    Published
    DOI:
    10.1007/s10044-018-0701-8 – link to the publication

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

    Authors:
    Łukasz Maziarka; Marek Śmieja; Marcin Sendera; Łukasz Struski; Jacek Tabor; Przemysław Spurek
    Status:
    Accepted for publication

Articles in post-conference publications (12)

  1. Flow-based SVDD for anomaly detection

    Authors:
    Marcin Sendera, Marek Śmieja, Łukasz Maziarka, Łukasz Struski, Przemysław Spurek, Jacek Tabor
    Conference:
    Invertible Neural Networks, NormalizingFlows, and Explicit Likelihood Models(ICML 2020) (year: 2020, pages: 46026), Publisher: ICML
    Date:
    conference 44030
    Status:
    Published

  2. Non-linear ICA based on Cramer-Wold metric

    Authors:
    Przemysław Spurek, Aleksandra Nowak, Jacek Tabor, Łukasz Maziarka, Stanisław Jastrzębski
    Conference:
    Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science (year: 2020, pages: 294-305), Publisher: Springer, Cham
    Date:
    conference 44122
    Status:
    Published

  3. Processing of incomplete images by (graph) convolutional neural networks

    Authors:
    Tomasz Danel, Marek Śmieja, Łukasz Struski, Przemysław Spurek, Łukasz Maziarka
    Conference:
    Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science (year: 2020, pages: 512-523), Publisher: Springer, Cham
    Date:
    conference 44122
    Status:
    Published

  4. Iterative imputation of missing data using auto-encoder dynamics

    Authors:
    Marek Śmieja, Maciej Kołomycki, Łukasz Struski, Mateusz Juda, Mario A. T. Figueiredo
    Conference:
    Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science (year: 2020, pages: 258-269), Publisher: Springer, Cham
    Date:
    conference 44122
    Status:
    Published

  5. Estimating conditional density of missing values using deep gaussian mixture model

    Authors:
    Marcin Przewięźlikowski, Marek Śmieja, Łukasz Struski
    Conference:
    Neural Information Processing. ICONIP 2020. Lecture Notes in Computer Science (year: 2020, pages: 220-231), Publisher: Springer, Cham
    Date:
    conference 44122
    Status:
    Published

  6. Spatial graph convolutional networks

    Authors:
    Tomasz Danel, Przemysław Spurek, Jacek Tabor, Marek Śmieja, Łukasz Struski, Agnieszka Słowik, Łukasz Maziarka
    Conference:
    Neural Information Processing. ICONIP 2020. Communications in Computer and Information Science (year: 2020, pages: 668-675), Publisher: Springer, Cham.
    Date:
    conference 44122
    Status:
    Published

  7. Biologically-Inspired Spatial Neural Networks

    Authors:
    Maciej Wołczyk, Jacek Tabor, Marek Śmieja, Szymon Maszke
    Conference:
    NeurIPS workshop on Real Neurons & Hidden Units (NeuroAI 2019) (year: 2019, pages: 46027), Publisher: NeurIPS 2019
    Date:
    conference 2019
    Status:
    Published

  8. Set Aggregation Network as a Trainable Pooling Layer

    Authors:
    Łukasz Maziarka, Marek Śmieja, Aleksandra Nowak, Jacek Tabor, Łukasz Struski, Przemysław Spurek
    Conference:
    ICONIP (year: 2019, pages: 46038), Publisher: Springer International Publishing
    Date:
    conference 2019
    Status:
    Published

  9. Molecule-Augmented Attention Transformer

    Authors:
    Łukasz Maziarka, Tomasz Danel, Sławomir Mucha, Krzysztof Rataj, Jacek Tabor, Stanisław Jastrzębski
    Conference:
    Second Workshop on Machine Learning and the Physical Sciences (NeurIPS 2019), Vancouver, Canada (year: 2019, pages: 46027), Publisher: NeurIPS 2019
    Date:
    conference 2019
    Status:
    Published

  10. Fast and Stable Interval Bounds Propagation for Training Verifiably Robust Models

    Authors:
    Paweł Morawiecki, Przemysław Spurek, Marek Śmieja, Jacek Tabor
    Conference:
    European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN 2020) (year: 2020, pages: 55-60), Publisher: Louvain-la-Neuve : i6doc
    Date:
    conference 44106
    Status:
    Published

  11. Can autoencoders help with filling missing data?

    Authors:
    Marek Śmieja, Maciej Kołomycki, Łukasz Struski, Mateusz Juda, Mário A. T. Figueiredo
    Conference:
    ICLR 2020 Workshop on Integration of Deep Neural Models and Differential Equations (year: 2020, pages: 46028), Publisher: ICLR
    Date:
    conference 43947
    Status:
    Published

  12. Finding the Optimal Network Depth in Classification Tasks

    Authors:
    Bartosz Wójcik, Maciej Wołczyk, Klaudia Bałazy, Jacek Tabor
    Conference:
    Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2020 (year: 2020, pages: 263-278), Publisher: Springer, Cham
    Date:
    conference 44088
    Status:
    Published

« New search

Graphic design and implementation: Jakub Piotrowski