Building high-level features using large scale unsupervised learning

Computer Science – Learning

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Scientific paper

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.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Building high-level features using large scale unsupervised learning does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Building high-level features using large scale unsupervised learning, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Building high-level features using large scale unsupervised learning will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-728248

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.