Projects funded by the NCN

Information on the principal investigator and host institution

Information of the project and the call

Keywords

Equipment

Delete all

Głębokie nauczanie w reprezentacji długich danych sekwencyjnych

2018/28/T/ST6/00211

Keywords:

Descriptors:

  • ST6_11: Machine learning, statistical data processing and applications using signal processing (e.g. speech, image, video)
  • ST6_9: Human computer interaction, speech recognition and synthesis, natural language processing

Panel:

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

Host institution :

Uniwersytet Jagielloński, Wydział Matematyki i Informatyki

woj. małopolskie

Other projects carried out by the institution 

Principal investigator (from the host institution):

dr Konrad Żołna 

Number of co-investigators in the project: 2

Call: ETIUDA 6 - announced on 2017-12-15

Amount awarded: 93 104 PLN

Project start date (Y-m-d): 2018-10-01

Project end date (Y-m-d): 2019-09-30

Project duration:: 12 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.

Information in the final report

  • Publication in academic press/journals (1)
  • Articles in post-conference publications (5)
  1. Classifier-agnostic saliency map extraction
    Authors:
    Konrad Zolna, Krzysztof J Geras, Kyunghyun Cho
    Academic press:
    Computer Vision and Image Understanding (rok: 2020, tom: Volume 196, strony: 102969), Wydawca: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.cviu.2020.102969 - link to the publication
  1. Combating False Negatives in Adversarial Imitation Learning (Student Abstract)
    Authors:
    Konrad Zolna, Chitwan Saharia, Leonard Boussioux, David Yu-Tung Hui, Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Yoshua Bengio
    Conference:
    National Conference of the American Association for Artificial Intelligence (rok: 2020, ), Wydawca: Proceedings of the AAAI Conference on Artificial Intelligence
    Data:
    konferencja 07.02.20-12.02.20
    Status:
    Published
    DOI:
    link to the publication
  2. Leakage-Robust Classifier via Mask-Enhanced Training (Student Abstract)
    Authors:
    Damian Stachura, Christopher Galias, Konrad Zolna
    Conference:
    National Conference of the American Association for Artificial Intelligence (rok: 2020, ), Wydawca: Proceedings of the AAAI Conference on Artificial Intelligence
    Data:
    konferencja 07.02.20-12.02.20
    Status:
    Published
    DOI:
    link to the publication
  3. Combating False Negatives in Adversarial Imitation Learning
    Authors:
    Konrad Zolna, Chitwan Saharia, Leonard Boussioux, David Yu-Tung Hui, Maxime Chevalier-Boisvert, Dzmitry Bahdanau and Yoshua Bengio
    Conference:
    International Joint Conference on Neural Networks (rok: 2021, ), Wydawca: IEEE
    Data:
    konferencja 18.07.21-22.07.21
    Status:
    Published
  4. Robust Learning-Augmented Caching: An Experimental Study
    Authors:
    Jakub Chledowski, Adam Polak, Bartosz Szabucki, Konrad Zolna
    Conference:
    International Conference on Machine Learning (rok: 2021, ), Wydawca: Proceedings of Machine Learning Research
    Data:
    konferencja 18.07.21-24.07.21
    Status:
    Published
    DOI:
    link to the publication
  5. Task-Relevant Adversarial Imitation Learning
    Authors:
    Konrad Zolna, Scott Reed, Alexander Novikov, Sergio Gomez Colmenarejo, David Budden, Serkan Cabi, Misha Denil, Nando de Freitas, Ziyu Wang
    Conference:
    Annual Conference on Robot Learning (rok: 2020, ), Wydawca: Proceedings of Machine Learning Research
    Data:
    konferencja 16.11.20-18.11.20
    Status:
    Published
    DOI:
    link to the publication

O Narodowym Centrum Nauki

Finansowanie nauki

Współpraca zagraniczna

Centrum prasowe

Deklaracja dostępności
Przetwarzanie danych osobowych
Polityka cookies

Partnerzy