Alle Publikationen

  • Erweiterte Suche öffnen

Treffer: 1
  • <<
  • 1

  • 2012

  • Le, Quoc V.; Ranzato, Marc'Aurelio; Monga, Rajat; Devin, Matthieu; Chen, Kai; Corrado, Greg S.; Dean, Jeff; Ng, Andrew Y. (2012) : Building high-level features using large scale unsupervised learning In: Langford, John; Pineau, Joelle (Hg.): Proceedings of the 29th International Conference on Machine Learning: Edinburgh, Scotland, UK: Anderson, USA: Omnipress, S. 507-514. Online verfügbar unter http://arxiv.org/pdf/1112.6209v5

     

    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 9-layered locally connected sparse autoencoder with pooling and local contrast normalization 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. Contrary to what appears to be a widely-held intuition, our experimental results reveal that it is possible to train a face detector without having to label images as containing a face or not. Control experiments show that this feature detector is robust not only to translation but also to scaling and out-of-plane rotation. We also find that the same network is sensitive to other high-level concepts such as cat faces and human bodies. Starting with these learned features, we trained our network to obtain 15.8% accuracy in recognizing 20,000 object categories from ImageNet, a leap of 70% relative improvement over the previous state-of-the-art.

    Keywords: Bilderkennung, Computer Science - Learning, Gestalt, Katze, schema, Schematheorie, Youtube
  • <<
  • 1