Authors
George E Dahl, Tara N Sainath, Geoffrey E Hinton
Publication date
2013/5/26
Conference
2013 IEEE International Conference on Acoustics, Speech and Signal Processing
Pages
8609-8613
Publisher
IEEE
Description
ABSTRACT Recently, pre-trained deep neural networks (DNNs) have outperformed
traditional acoustic models based on Gaussian mixture models (GMMs) on a variety of large
vocabulary speech recognition benchmarks. Deep neural nets have also achieved excellent
results on various computer vision tasks using a random “dropout” procedure that drastically
improves generalization error by randomly omitting a fraction of the hidden units in all layers.
Since dropout helps avoid overfitting, it has also been successful on a small-scale phone ...
Total citations
2013201420152016157311971
Scholar articles
GE Dahl, TN Sainath, GE Hinton - 2013 IEEE International Conference on Acoustics, …, 2013