Autor: Siwocha, A. - Katalog OPAC zbiorów

Skocz do pozycji: 1.

Tytuł:: Ways of Selecting Internal Patterns in Multilayer Perceptron Network
Autorzy:: Kolibabka, M.
Cader, A.
Siwocha, A.
Krupski, M.
Powiązania:: https://bibliotekanauki.pl/articles/108637.pdf
Data publikacji:: 2012
Wydawca:: Społeczna Akademia Nauk w Łodzi
Tematy:: neural networks
artificial intelligence
back propagation
Opis:: Creating and later learning one-way neural networks depends on many factors. Selecting many of them has estimated and experimental character. The suggested method is the Allows weakness of the influence of the not optimal choice of the net structure, also speed and momentum values are less influential in classic Back then Propagation Method. There are few modes of choosing elements to use in Followed algorithm.
Źródło:: Journal of Applied Computer Science Methods; 2012, 4 No. 1; 63-73
1689-9636
Pojawia się w:: Journal of Applied Computer Science Methods
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 2.

Tytuł:: Fractal Format for Bitmap Images
Autorzy:: Siwocha, A.
Cader, A.
Kolibabka, M.
Krupski, M.
Powiązania:: https://bibliotekanauki.pl/articles/108680.pdf
Data publikacji:: 2012
Wydawca:: Społeczna Akademia Nauk w Łodzi
Tematy:: fractal interpolation method
image recording formats
fractal dimension
multifractal analysis
non-local characteristics
Opis:: The conception of proposed recording format is the example of the theoretical and practical application of the FBS method, which was precisely described in thesis [18,19,20]. The foundation of the presented recording format is the use of a new method of fractal basis splines (FB-splines), which allows the reconstruction of complex geometric structures with the properties of fractals. Fractral basis splines method is based on the use of non-local characteristics to describe the interpolation nodes. With that the one-parameter family of fractal curves is used as the basic approximating elements.
Źródło:: Journal of Applied Computer Science Methods; 2012, 4 No. 2; 41-54
1689-9636
Pojawia się w:: Journal of Applied Computer Science Methods
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 3.

Tytuł:: Efficient image retrieval by fuzzy rules from boosting and metaheuristic
Autorzy:: Korytkowski, Marcin
Senkerik, Roman
Scherer, Magdalena M.
Angryk, Rafal A.
Kordos, Miroslaw
Siwocha, Agnieszka
Powiązania:: https://bibliotekanauki.pl/articles/91856.pdf
Data publikacji:: 2020
Wydawca:: Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:: image retrieval
fuzzy rules
local image features
pobieranie obrazu
lokalne funkcje obrazu
Opis:: Fast content-based image retrieval is still a challenge for computer systems. We present a novel method aimed at classifying images by fuzzy rules and local image features. The fuzzy rule base is generated in the first stage by a boosting procedure. Boosting meta-learning is used to find the most representative local features. We briefly explore the utilization of metaheuristic algorithms for the various tasks of fuzzy systems optimization. We also provide a comprehensive description of the current best-performing DISH algorithm, which represents a powerful version of the differential evolution algorithm with effective embedded mechanisms for stronger exploration and preservation of the population diversity, designed for higher dimensional and complex optimization tasks. The algorithm is used to fine-tune the fuzzy rule base. The fuzzy rules can also be used to create a database index to retrieve images similar to the query image fast. The proposed approach is tested on a state-of-the-art image dataset and compared with the bag-of-features image representation model combined with the Support Vector Machine classification. The novel method gives a better classification accuracy, and the time of the training and testing process is significantly shorter.
Źródło:: Journal of Artificial Intelligence and Soft Computing Research; 2020, 10, 1; 57-69
2083-2567
2449-6499
Pojawia się w:: Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Informacja

Wyszukujesz frazę "Siwocha, A." wg kryterium: Autor

Źródło danych

Dostawca treści

Kolekcja

Rok wydania

Wydawca

Temat

Autor

Typ dokumentu

Język