Youssef Mroueh, Etienne Marcheret, et al.
AISTATS 2017
Conference paper
Noisy objective functions based on the f-divergence
Abstract
Dropout, the random dropping out of activations according to a specified rate, is a very simple but effective method to avoid over-fitting of deep neural networks to the training data.
Related
Xiaodong Cui, Vaibhava Goel, et al.
ICASSP 2015
Jing Huang, Peder A. Olsen, et al.
ICASSP 2013
Conference paper
Detecting audio-visual synchrony using deep neural networks
Etienne Marcheret, Gerasimos Potamianos, et al.
INTERSPEECH 2015