Skip to main content

Challenges in Machine Generation of Analytic Products from Multi-Source Data Proceedings of a Workshop (2017) / Chapter Skim
Currently Skimming:

7 Session 6: Learning from Social Media
Pages 26-27

The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.


From page 26...
... A complete graph would have 1010 edges1 per day, so this method scales to very large data streams. Fergus noted that when analyzing these large, noisy data streams, ambiguity creates challenges that can be addressed with these methods -- for example, exploring the embedding space can reveal whether a post about "football" is discussing soccer or the National Football League.
Read the entire page →
From page 27...
... In distributed training, as the batch size increases, optimization issues arise, so the learning rate must be scaled linearly to ensure accuracy. Increasing the number of graphical processing units also allows a linear speed-up in the training time.
Read the entire page →

Key Terms

  • neural networks
  • convolutional neural
  • project fergus
  • training convolutional
  • processing unit

  • issues arise
  • fergus introduced
  • explicit human
  • introduced described
  • national football

  • scaled linearly
  • deep models
  • creates challenges
  • training time
  • processing units

  • fergus noted
  • data streams
  • program addressed
  • images found
  • predict words

  • embedding space
  • using deep
  • described strategies
  • previously discussed
  • studied training

  • train deep
  • discussed program
  • ambiguity creates
  • noisy data
  • metadata associated


    • This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
    More information on Chapter Skim is available.