Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Checiński, 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:
Radzikowski, Kacper, Checiński, Karol, Forc, Mateusz, Lepak, Łukasz, Jabłonski, Michał, Kusmirek, Wiktor, Twardowski, Bartłomiej, Wawrzynski, Paweł, Nowak, Robert M.
Publikováno v:
Proceedings of SPIE; 8/27/2019, Vol. 11176, p111761Q-1-111761Q-8, 8p
