Authors
Quoc V Le, Marc A. Ranzato, Rajat Monga, Matthieu Devin, Kai Chen, Greg S. Corrado, J Dean, Andrew Y Ng
Publication date
2012/7/12
Conference
International Conference on Machine Learning
Description
ABSTRACT We consider the problem of building high-level, class-specific feature detectors
from only unlabeled data. For example, is it possible to learn a face detector using only
unlabeled images? To answer this, we train a deep sparse autoencoder on a large dataset
of images (the model has 1 billion connections, the dataset has 10 million 200x200 pixel
images downloaded from the Internet). We train this network using model parallelism and
asynchronous SGD on a cluster with 1,000 machines (16,000 cores) for three days. ...
Total citations
2012201320142015201635163257277166
Scholar articles