Artificial Intelligence

Building High-Level Features Using Large Scale Unsupervised Learning

Authors: Quoc V. Le, Rajat Monga, Matthieu Devin, Greg Corrado, Kai Chen, Marc'Aurelio Ranzato, Jeff Dean, Andrew Y. Ng
Comments: 10 Pages.

We consider the problem of building detectors for high-level concepts using only unsupervised feature learning. For example, we would like to understand if it is possible to learn a face detector using only unlabeled images downloaded from the internet. To answer this question, we trained a simple feature learning algorithm on a large dataset of images (10 million images, each image is 200x200). The simulation is performed on a cluster of 1000 machines with fast network hardware for one week. Extensive experimental results reveal surprising evidence that such high-level concepts can indeed be learned using only unlabeled data and a simple learning algorithm.
Category: Artificial Intelligence