Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Chęciński, Karol"'
Autor:
Chęciński, Karol, Wawrzyński, Paweł
Convolutional neural networks are based on a huge number of trained weights. Consequently, they are often data-greedy, sensitive to overtraining, and learn slowly. We follow the line of research in which filters of convolutional neural layers are det
Externí odkaz:
http://arxiv.org/abs/2001.08517
Autor:
Romaniuk, Ryszard S., Linczuk, Maciej, Radzikowski, Kacper, Chęciński, Karol, Forc, Mateusz, Lepak, Łukasz, Jabłoński, Michał, Kuśmirek, Wiktor, Twardowski, Bartłomiej, Wawrzyński, Paweł, Nowak, Robert M.
Publikováno v:
Proceedings of SPIE; November 2019, Vol. 11176 Issue: 1 p111761Q-111761Q-8, 1005858p
