Year  Title  Author 
2017

Controlled dropout: A different approach to using dropout on deep neural network 
BS Ko, HG Kim, KJ Oh, HJ Choi

2017

An improved dropout method and its application into DBNbased handwriting recognition 
G Hu, H Li, L Luo, Y Xia

2016

Dropout Versus Weight Decay for Deep Networks 
DP Helmbold, PM Long

2016

A Dropout Distribution Model on Deep Transfer Learning Networks 
F Li, H Yang, J Wang

2016

Improved Dropout for Shallow and Deep Learning 
Z Li, B Gong, T Yang

2016

A New Design BasedSVM of the CNN Classifier Architecture with Dropout for Offline Arabic Handwritten Recognition 
M Elleuch, R Maalej, M Kherallah

2016

Selective Dropout for Deep Neural Networks 
E Barrow, M Eastwood, C Jayne

2016

Group Dropout Inspired by Ensemble Learning 
K Hara, D Saitoh, T Kondou, S Suzuki, H Shouno

2016

Improving quantitative structureâ€“activity relationship models using Artificial Neural Networks trained with dropout 
J Mendenhall, J Meiler

2016

Structured Dropout for Weak Label and MultiInstance Learning and Its Application to ScoreInformed Source Separation 
S Ewert, MB Sandler

2016

NFLB dropout: Improve generalization ability by dropping out the bestA biologically inspired adaptive dropout method for unsupervised learning 
P Yin, L Qi, X Xi, B Zhang, H Qiao

2016

Analysis of Dropout Learning Regarded as Ensemble Learning 
K Hara, D Saitoh, H Shouno

2016

Learning deep feature representations with domain guided dropout for person reidentification 
T Xiao, H Li, W Ouyang, X Wang

2016

Fundamental differences between Dropout and Weight Decay in Deep Networks 
DP Helmbold, PM Long

2015

DropELM: Fast Neural Network Regularization with Dropout and DropConnect 
A Iosifidis, A Tefas, I Pitas

2015

Efficient batchwise dropout training using submatrices 
B Graham, J Reizenstein, L Robinson

2015

Dropout as a Bayesian Approximation: Appendix 
Y Gal, Z Ghahramani

2015

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning 
Y Gal, Z Ghahramani

2015

Parallel Dither and Dropout for Regularising Deep Neural Networks 
AJR Simpson

2015

Partitioning Large Scale Deep Belief Networks Using Dropout 
Y Huang, S Zhang

2015

FlipRotatePooling Convolution and Split Dropout on Convolution Neural Networks for Image Classification 
F Wu, P Hu, D Kong

2015

A Theoretically Grounded Application of Dropout in Recurrent Neural Networks 
Y Gal

2015

Dropout as a Bayesian approximation: Insights and applications 
Y Gal, Z Ghahramani

2015

QBDC: Query by dropout committee for training deep supervised architecture 
M Ducoffe, F Precioso

2015

Stochastically Reducing Overfitting In Deep Neural Network Using Dropout 
N Tripathi, A Jadeja

2015

Dither is Better than Dropout for Regularising Deep Neural Networks 
AJR Simpson

2015

Deep Dropout Artificial Neural Networks for Recognising Digits and Characters in Natural Images 
E Barrow, C Jayne, M Eastwood

2015

Hierarchical Feature Learning With Dropout KMeans for Hyperspectral Image Classification 
F Zhang, B Du, L Zhang, L Zhang

2014

Learning Compact Convolutional Neural Networks with Nested Dropout 
C Finn, LA Hendricks, T Darrell

2014

Temporal Dropout of Changes Approach to Convolutional Learning of SpatioTemporal Features 
D Culibrk, N Sebe

2014

On the Inductive Bias of Dropout 
DP Helmbold, PM Long

2014

A Comparison of Random Forests and Dropout Nets for Sign Language Recognition with the Kinect 
N Jaques, J Nutini
