Bölüm "Işık University, Pattern Recognition and Machine Intelligence Laboratory" Mühendislik ve Doğa Bilimleri Fakültesi / Faculty Of Engineering And Natural Sciences için listeleme
Toplam kayıt 1, listelenen: 1-1
-
A novel similarity based unsupervised technique for training convolutional filters
(IEEE, 2023-05-17)Achieving satisfactory results with Convolutional Neural Networks (CNNs) depends on how effectively the filters are trained. Conventionally, an appropriate number of filters is carefully selected, the filters are initialized ...