Browsing by Subject "Artificial neural network"
Now showing items 8-8 of 8
(Springer https://doi.org/10.1007/978-3-319-46675-0_57, 2016-09-29)BARROW, E., EASTWOOD, M. and JAYNE, C. 2016. Selective dropout for deep neural networks. Lecture notes in computer science, 9949, Neural information processing: Proceedings of 23rd International conference on neural information processing (ICONIP 2016), 16-21 October 2016, Kyoto, Japan. Cham: Springer [online], pages 519-528. Available from: https://doi.org/10.1007/978-3-319-46675-0_57.Dropout has been proven to be an effective method for reducing overfitting in deep artificial neural networks. We present 3 new alternative methods for performing dropout on a deep neural network which improves the ...