Projects funded by the NCN

Information on the principal investigator and host institution

Information of the project and the call

Keywords

Equipment

Delete all

DALEX: Desciptive and model Agnostic Local EXplanations of machine learning models

2017/27/B/ST6/01307

Keywords:

machine learning local explanations white-box approximations

Descriptors:

  • ST6_11: Machine learning, statistical data processing and applications using signal processing (e.g. speech, image, video)
  • ST6_12: Scientific computing, simulation and modelling tools

Panel:

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

Host institution :

Politechnika Warszawska, Wydział Matematyki i Nauk Informacyjnych

woj. mazowieckie

Other projects carried out by the institution 

Principal investigator (from the host institution):

dr hab. Przemysław Biecek 

Number of co-investigators in the project: 4

Call: OPUS 14 - announced on 2017-09-15

Amount awarded: 542 660 PLN

Project start date (Y-m-d): 2018-08-08

Project end date (Y-m-d): 2023-01-07

Project duration:: 53 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. Laptop (6 000 PLN)
  2. Serwer 30TB HDD; 128 GB RAM; 24 cores (46 000 PLN)
  3. 2 x Notebook DELL Vostro 7500.
  4. Monitor 65'' (5 000 PLN)
  5. Tablet Apple iPad.

Information in the final report

  • Publication in academic press/journals (9)
  • Articles in post-conference publications (2)
  1. Simpler is better: Lifting interpretability-performance trade-off via automated feature engineering
    Authors:
    Alicja Gosiewska, Anna Kozak, Przemysław Biecek
    Academic press:
    Decision Support Systems (rok: 2021, tom: 150, strony: 113556), Wydawca: Decision Support Systems
    Status:
    Published
    DOI:
    10.1016/j.dss.2021.113556 - link to the publication
  2. The grammar of interactive explanatory model analysis
    Authors:
    Hubert Baniecki, Dariusz Parzych, Przemyslaw Biecek
    Academic press:
    Data Mining and Knowledge Discovery (rok: 2023, tom: 1, strony: 13516), Wydawca: Springer
    Status:
    Published
    DOI:
    10.1007/s10618-023-00924-w - link to the publication
  3. dalex: Responsible Machine Learning with Interactive Explainability and Fairness in Python
    Authors:
    Hubert Baniecki, Wojciech Kretowicz, Piotr Piatyszek, Jakub Wisniewski, Przemyslaw Biecek
    Academic press:
    Journal of Machine Learning Research (rok: 2021, tom: 22, strony: 45298), Wydawca: Journal of Machine Learning Research
    Status:
    Published
    DOI:
    brak - link to the publication
  4. Clinical Significance of Nucleoli Cytomorphology Assessment in Patients With Uveal Melanoma
    Authors:
    TOMASZ BERUS, ANNA MARKIEWICZ, PRZEMYSŁAW BIECEK, JOLANTA ORŁOWSKA-HEITZMAN, AGNIESZKA HAŁOŃ, BOŻENA ROMANOWSKA-DIXON, PIOTR DONIZY
    Academic press:
    ANTICANCER RESEARCH (rok: 2020, tom: 40, strony: 505-3512), Wydawca: International Institute of Anticancer Research
    Status:
    Published
    DOI:
    10.21873/anticanres.14338 - link to the publication
  5. Interpretable meta-score for model performance
    Authors:
    Alicja Gosiewska, Katarzyna Woźnica, Przemysław Biecek
    Academic press:
    Nature Machine Intelligence (rok: 2022, tom: 4, strony: 792–800), Wydawca: Nature
    Status:
    Published
    DOI:
    10.1038/s42256-022-00531-2 - link to the publication
  6. Interpretable segmentation of medical free-text records based on word embeddings
    Authors:
    Adam Dobrakowski, Agnieszka Mykowiecka, Małgorzata Marciniak, Wojciech Jaworski, Przemysław Biecek
    Academic press:
    Journal of Intelligent Information Systems (rok: 2021, tom: 57, strony: 447-465), Wydawca: Journal of Intelligent Information Systems
    Status:
    Published
    DOI:
    10.1007/s10844-021-00659-4 - link to the publication
  7. modelDown: automated website generator with interpretable documentation for predictive machine learning models
    Authors:
    Kamil Romaszko, Magda Tatarynowicz, Mateusz Urbański, and Przemysław Biecek
    Academic press:
    The Journal of Open Software (rok: 2019, tom: 4 (38), strony: 5), Wydawca: nie dotyczy
    Status:
    Published
    DOI:
    10.21105/joss.01444 - link to the publication
  8. Responsible Prediction Making of COVID-19 Mortality (Student Abstract)
    Authors:
    Hubert Baniecki, Przemyslaw Biecek
    Academic press:
    The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI-21) Student Papers and Demonstrations (rok: 2021, tom: 35 (18), strony: 15755-15756), Wydawca: Association for the Advancement of Artificial Intelligence
    Status:
    Published
    DOI:
    brak - link to the publication
  9. pyCeterisParibus: explaining Machine Learning models with Ceteris Paribus Profiles in Python
    Authors:
    Michał Kuźba, Ewa Baranowska, Przemysław Biecek
    Academic press:
    The Journal of Open Software (rok: 2019, tom: 4 (37), strony: 7), Wydawca: nie dotyczy
    Status:
    Published
    DOI:
    10.21105/joss.01389 - link to the publication
  1. Towards Explainable Meta-learning
    Authors:
    Katarzyna Woźnica, Przemysław Biecek
    Conference:
    ECML PKDD 2021: Warsztat Machine Learning and Principles and Practice of Knowledge Discovery in Databases (rok: 2021, ), Wydawca: Springer
    Data:
    konferencja 44452
    Status:
    Published
  2. Fooling Partial Dependence via Data Poisoning
    Authors:
    Hubert Baniecki , Wojciech Kretowicz, Przemyslaw Biecek
    Conference:
    ECML PKDD: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (rok: 2022, ), Wydawca: Springer
    Data:
    konferencja 44823
    Status:
    Published

O Narodowym Centrum Nauki

Finansowanie nauki

Współpraca zagraniczna

Centrum prasowe

Deklaracja dostępności
Przetwarzanie danych osobowych
Polityka cookies

Partnerzy