1. Do STT systems have "intriguing properties"?

    Do STT systems have "intriguing properties"?

    « previous post | In "Intriguing properties of neural networks" (2013), Christian Szegedy et al. point out that … deep neural networks learn input-output mappings that are fairly discontinuous to a significant extent. We can cause the network to misclassify an image by applying a certain imperceptible perturbation… For example: There has been quite a bit of discussion of the topic since then.

    Read Full Article

    Login to comment.

  1. Categories

    1. Default:

      Discourse, Entailment, Machine Translation, NER, Parsing, Segmentation, Semantic, Sentiment, Summarization, WSD
  2. Authors