Blog
About

212
views
0
recommends
+1 Recommend
0 collections
    8
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Unsupervised Learning on Neural Network Outputs

      Preprint

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          The outputs of a trained neural network contain much richer information than just an one-hot classifier. For example, a neural network might give an image of a dog the probability of one in a million of being a cat but it is still much larger than the probability of being a car. To reveal the hidden structure in them, we apply two unsupervised learning algorithms, PCA and ICA, to the outputs of a deep Convolutional Neural Network trained on the ImageNet of 1000 classes. The PCA/ICA embedding of the object classes reveals their visual similarity and the PCA/ICA components can be interpreted as common visual features shared by similar object classes. For an application, we proposed a new zero-shot learning method, in which the visual features learned by PCA/ICA are employed. Our zero-shot learning method achieves the state-of-the-art results on the ImageNet of over 20000 classes.

          Related collections

          Author and article information

          Journal
          2015-06-02
          2016-01-28
          Article
          1506.00990

          http://arxiv.org/licenses/nonexclusive-distrib/1.0/

          Custom metadata
          cs.LG

          Artificial intelligence

          Comments

          Comment on this article