Szczegóły publikacji
Opis bibliograficzny
Combining Probabilistic Neural Networks with a Convolution Neural Network as a feature transformer / Szymon KUCHARCZYK, Piotr A. KOWALSKI // W: Progress in Polish artificial intelligence research 6 [Dokument elektroniczny] : 6th Polish Conference on Artifical Intelligence (PP-RAI'2025) : 07–09.04.2025, Katowice, Poland / ed. by Rafał Doroz, Beata Zielosko. — Wersja do Windows. — Dane tekstowe. — Katowice : Wydawnictwo Uniwersytetu Śląskiego, 2025. — e-ISBN: 978-83-226-4405-8. — S. 58–64. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 63–64, Abstr. — P. A. Kowalski - dod. afiliacja: Systems Research Institute, Polish Academy of Sciencesul, Warsaw, Poland
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 165794 |
|---|---|
| Data dodania do BaDAP | 2026-02-03 |
| Tekst źródłowy | URL |
| Rok publikacji | 2025 |
| Typ publikacji | fragment monografii pokonferencyjnej |
| Otwarty dostęp |  |
| Creative Commons | |
| Wydawca | Uniwersytet Śląski w Katowicach |
Abstract
Probabilistic Neural Networks (PNNs) are memory-based Artifi-cial Networks that have been successfully used for classification and regression problems for tabular data. PNNs differ significantly from deep neuralnetworks (CNN or RNN) in terms of both architecture and network training. In addition, because of their architecture, they have been used mainly tosolve problems with tabular data. Here, we propose an evaluation of the ideaof joining convolution neural networks with PNNs to solve well-defined image classification problems (MNIST, CIFAR10). The results show that PNNsare capable of correctly classifying images after extracting the features usingconvolution layers.
