research
∙
05/18/2017
Building effective deep neural network architectures one feature at a time
Successful training of convolutional neural networks is often associated...
share
research
∙
11/09/2015
How far can we go without convolution: Improving fully-connected networks
We propose ways to improve the performance of fully connected networks. ...
research
∙
06/29/2015
Dropout as data augmentation
Dropout is typically interpreted as bagging a large number of models sha...
research
∙
03/05/2015
EmoNets: Multimodal deep learning approaches for emotion recognition in video
The task of the emotion recognition in the wild (EmotiW) Challenge is to...
research
∙
02/13/2014
Zero-bias autoencoders and the benefits of co-adapting features
Regularized training of an autoencoder typically results in hidden unit ...
research
∙
02/10/2014
Modeling sequential data using higher-order relational features and predictive training
Bi-linear feature learning models, like the gated autoencoder, were prop...
research
∙
12/12/2013