Http://arxiv.org/pdf /1112.6209.pdf

1112.6209.pdf
Preview of http://arxiv.org/pdf /1112.6209.pdf
🔗 Source: arxiv.org
📊 Size: 2.92 MB
👤 Author: Quoc V. Le, Marc'Aurelio Ranzato, Rajat Monga, Matthieu Devin, Kai Chen, Greg S. Corrado, Jeff Dean,
⬇️ Downloads: 53

Summary

Researchers trained a 9-layered locally connected sparse autoencoder on a large dataset of 10 million 200x200 pixel images to build high-level, class-specific feature detectors from only unlabeled data, achieving a face detector without labeling images and obtaining 15.8% accuracy in recognizing 22,000 object categories from ImageNet, a 70% relative improvement over the previous state-of-the-art.

Description

Researchers trained a 9-layered locally connected sparse autoencoder on a large dataset of 10 million 200x200 pixel images to build high-level, class-specific...

Technical Information

  • File Format: PDF
  • File Size: 2.92 MB
  • Pages: 11
  • Language: EN
  • Author: Quoc V. Le, Marc'Aurelio Ranzato, Rajat Monga, Matthieu Devin, Kai Chen, Greg S. Corrado, Jeff Dean,
  • Total Downloads: 53
  • Last Updated: 7 days ago

Document Overview

This PDF document about http://arxiv.org/pdf /1112.6209.pdf provides comprehensive information and guidance. Whether you're a beginner or advanced user, this resource offers valuable insights into http://arxiv.org/pdf /1112.6209.pdf.

Related Topics

If you're interested in http://arxiv.org/pdf /1112.6209.pdf, you might also want to explore:

Download http://arxiv.org/pdf /1112.6209.pdf eBooks for free and learn more about http://arxiv.org/pdf /1112.6209.pdf. These books contain exercises and tutorials to improve your practical skills, at all levels!

Not satisfied with this document? We have related documents to http://arxiv.org/pdf /1112.6209.pdf, try searching with similar keywords: http://arxiv.org/pdf /1112.6209.pdf, http://arxiv.org/ftp /arxiv/papers/1106/1 106.6178.pdf, https://arxiv.org/ft p/arxiv/papers/1807/ 1807.03976.pdf, http://arxiv.org/pdf /1108.6077.pdf, http://arxiv.org/pdf /1404.7828v4.pdf, http://arxiv.org/pdf /1302.1933v1.pdf, http://arxiv.org/pdf /0803.0982.pdf, http://arxiv.org/pdf /1502.05698v7.pdf

You can download PDF versions of the user's guide, manuals and ebooks about http://arxiv.org/pdf /1112.6209.pdf, you can also find and download for free A free online manual (notices) with beginner and intermediate, Downloads Documentation, You can download PDF files (or DOC and PPT) about http://arxiv.org/pdf /1112.6209.pdf for free, but please respect copyrighted ebooks.