Projects funded by the NCN

Information on the principal investigator and host institution

Information of the project and the call

Keywords

Equipment

Delete all

Randomized learning methods for artificial neural networks

2017/27/B/ST6/01804

Keywords:

function approximation data classification feedforward neural networks neural networks with random hidden nodes randomized learning algorithms activation function

Descriptors:

  • ST6_7: Artificial intelligence, intelligent systems, multi-agent systems
  • ST6_11: Machine learning, statistical data processing and applications using signal processing (e.g. speech, image, video)

Panel:

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

Host institution :

Politechnika Częstochowska, Wydział Elektryczny

woj. śląskie

Other projects carried out by the institution 

Principal investigator (from the host institution):

dr hab. Grzegorz Dudek 

Number of co-investigators in the project: 1

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

Amount awarded: 152 400 PLN

Project start date (Y-m-d): 2018-06-29

Project end date (Y-m-d): 2021-06-28

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. Zestaw komputerowy (stacjonarny) (18 000 PLN)

Information in the final report

  • Publication in academic press/journals (2)
  • Articles in post-conference publications (10)
  1. Generating random weights and biases in feedforward neural networks with random hidden nodes
    Authors:
    Grzegorz Dudek
    Academic press:
    Information Sciences (rok: 2019, tom: 481, strony: 33-56), Wydawca: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.ins.2018.12.063 - link to the publication
  2. A Constructive Approach to Data-Driven Randomized Learning for Feedforward Neural Networks
    Authors:
    Grzegorz Dudek
    Academic press:
    Applied Soft Computing (rok: 2021, tom: 112, strony: 107797), Wydawca: Elsevier
    Status:
    Submitted
    DOI:
    10.1016/j.asoc.2021.107797 - link to the publication
  1. Are Direct Links Necessary in Random Vector Functional Link Networks for Regression
    Authors:
    Grzegorz Dudek
    Conference:
    19th International Conference on Artificial Intelligence and Soft Computing (rok: 2020, ), Wydawca: Springer
    Data:
    konferencja 21-25 czerwca 2020
    Status:
    Published
  2. Data-Driven Randomized Learning of Feedforward Neural Networks
    Authors:
    Grzegorz Dudek
    Conference:
    International Joint Conference on Neural Networks (rok: 2020, ), Wydawca: IEEE
    Data:
    konferencja 19-24 Lipca 2020
    Status:
    Published
  3. Data-Driven Learning of Feedforward Neural Networks with Different Activation Functions
    Authors:
    Grzegorz Dudek
    Conference:
    20th International Conference on Artificial Intelligence and Soft Computing (rok: 2021, ), Wydawca: Springer
    Data:
    konferencja 2021.06.20-24
    Status:
    Published
  4. Improving Randomized Learning of Feedforward Neural Networks by Appropriate Generation of Random Parameter
    Authors:
    Grzegorz Dudek
    Conference:
    15th International Work-Conference on Artificial Neural Networks (rok: 2019, ), Wydawca: Springer
    Data:
    konferencja 12-14 czerwca 2019
    Status:
    Published
    DOI:
    link to the publication
  5. Randomized Neural Networks for Forecasting Time Series with Multiple Seasonality
    Authors:
    Grzegorz Dudek
    Conference:
    16th International Work-Conference on Artificial Neural Networks (rok: 2021, ), Wydawca: Springer
    Data:
    konferencja 2021.06.16-18
    Status:
    Published
  6. Ensembles of Randomized Neural Networks for Pattern-based Time Series Forecasting
    Authors:
    Grzegorz Dudek, Paweł Pełka
    Conference:
    International Conference on Neural Information Processing, ICONIP 2021 (rok: 2021, ), Wydawca: Springer
    Data:
    konferencja 2021.12.8-12
    Status:
    Accepted for publication
  7. Autoencoder based Randomized Learning of Feedforward Neural Networks for Regression
    Authors:
    Grzegorz Dudek
    Conference:
    International Joint Conference on Neural Networks (rok: 2021, ), Wydawca: IEEEXplore
    Data:
    konferencja 2021.07.18-23
    Status:
    Published
  8. Generating Random Parameters in Feedforward Neural Networks with Random Hidden Nodes: Drawbacks of the Standard Method and How to Improve It
    Authors:
    Grzegorz Dudek
    Conference:
    International Conference on Neural Information Processing, ICONIP 2020 (rok: 2020, ), Wydawca: Springer
    Data:
    konferencja 18-22.11.2020
    Status:
    Published
  9. New Methods of Generating Random Parameters in Feedforward Neural Networks with Random Hidden Nodes
    Authors:
    Grzegorz Dudek
    Conference:
    Polskie Porozumienie na rzecz Rozwoju Sztucznej Inteligencji PP-RAI (rok: 2019, ), Wydawca: Department of Systems and Computer Networks, Faculty of Electronics Wroclaw University of Science and Technology
    Data:
    konferencja 16-18 października 2019
    Status:
    Published
    DOI:
    link to the publication
  10. Sensitivity Analysis of the Neural Networks Randomized Learning
    Authors:
    Grzegorz Dudek
    Conference:
    18th International Conference on Artificial Intelligence and Soft Computing (rok: 2019, ), Wydawca: Springer
    Data:
    konferencja 16-20 czerwca 2019
    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