Repozytorium Uniwersytetu Zielonogórskiego udostępnia 9 387 obiektów cyfrowych
Obiekt
Tytuł: Choice of the p-norm for high level classification features pruning in modern convolutional neural networks with local sensitivity analysis
Contributor:
Korbicz, Józef (1951- ) - red. ; Uciński, Dariusz - red.
Group publication title:
Abstract:
Transfer learning has surfaced as a compelling technique in machine learning, enabling the transfer of knowledge across networks. This study evaluates the efficacy of ImageNet pretrained state-of-the-art networks, including DenseNet, ResNet, and VGG, in implementing transfer learning for prepruned models on compact datasets, such as FashionMNIST, CIFAR10, and CIFAR100. The primary objective is to reduce the number of neurons while preserving high-level features. To this end, local sensitivity analysis is employed alongside p-norms and various reduction levels. ; This investigation discovers that VGG16, a network rich in parameters, displays resilience to high-level feature pruning. Conversely, the ResNet architectures reveal an interesting pattern of increased volatility. These observations assist in identifying an optimal combination of the norm and the reduction level for each network architecture, thus offering valuable directions for model-specific optimization. This study marks a significant advance in understanding and implementing effective pruning strategies across diverse network architectures, paving the way for future research and applications.
Publisher:
Zielona Góra: Uniwersytet Zielonogórski
Resource Identifier:
DOI:
Pages:
Source:
AMCS, volume 33, number 4 (2023) ; kliknij tutaj, żeby przejść
Language:
License CC BY 4.0:
Rights:
Biblioteka Uniwersytetu Zielonogórskiego
Kolekcje, do których przypisany jest obiekt:
- Repository > Faculties > Faculty of Computer, Electrical and Control Engineering
- Repository > Types of work > Articles
- Repository > Scientific journals and UZ publishing series > International Journal of Applied Mathematics and Computer Science (AMCS) > International Journal of Applied Mathematics and Computer Science (AMCS) (2023)
Data ostatniej modyfikacji:
28 lip 2025
Data dodania obiektu:
28 lip 2025
Liczba wyświetleń treści obiektu:
33
Wszystkie dostępne wersje tego obiektu:
https://zbc.uz.zgora.pl/repozytorium/publication/101628
Wyświetl opis w formacie RDF:
Wyświetl opis w formacie OAI-PMH:
-
-
-
-
-
International Journal of Applied Mathematics and Computer Science (AMCS), volume 33, number 1 (2023)
-
International Journal of Applied Mathematics and Computer Science (AMCS), volume 33, number 2 (2023)
-
International Journal of Applied Mathematics and Computer Science (AMCS), volume 33, number 3 (2023)
-
International Journal of Applied Mathematics and Computer Science (AMCS), volume 33, number 4 (2023)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Obiekty Podobne
Wang, Tianming Wang, Kaige Li, Qing Korbicz, Józef (1951- ) - red. Uciński, Dariusz - red.
Patro, Kiran Kumar Prakash, Allam Jaya Samantray, Saunak Pławiak, Joanna Tadeusiewicz, Ryszard (1947- ) Pławiak, Paweł Wiśniewski, Remigiusz - ed. Gomes, Luis - ed. Wan, Shaohua - ed.
Karlupia, Namrata Mahajan, Palak Abrol, Pawanesh Lehana, Parveen K. Niemiec, Marcin - ed. Dziech, Andrzej - ed. Wassermann, Jakob - ed.
Korvel, Gražina Treigys, Povilas Kąkol, Krzysztof Kostek, Bożena Foryś, Urszula - ed. Rejniak, Katarzyna - ed. Pękala, Barbara - ed. Bartłomiejczyk, Agnieszka - ed.
Kandukuri, Usha Rani Prakash, Allam Jaya Patro, Kiran Kumar Neelapu, Bala Chakravarthy Tadeusiewicz, Ryszard (1947- ) Pławiak, Paweł Foryś, Urszula - ed. Rejniak, Katarzyna - ed. Pękala, Barbara - ed. Bartłomiejczyk, Agnieszka - ed.
Yasui, Syozo Rutkowska, Danuta - ed. Zadeh, Lotfi A. - ed.
Eny, Gérémino Ella Eya, Honorine Angue Mintsa Nzue, Rolland Michel Assoumou Senouveau, Nzamba Jurczak, Paweł - red.
Gao, Depeng Liu, Jiafeng Wu, Rui Cheng, Dansong Fan, Xiaopeng Tang, Xianglong Kulczycki, Piotr - ed. Kacprzyk, Janusz - ed. Kóczy, László T. - ed. Mesiar, Radko - ed.
