15.4 The ‘deep’ in deep learning (1)

  • Deep learning (DL) = mathematical framework = subfield of machine learning
    • New take on learning representations from data that puts an emphasis on learning successive layers of increasingly meaningful representations
  • “deep” stands for this idea of successive layers of representations
    • Depth of model = how many layers contribute to a model of the data
    • Modern deep learning often involves tens or even hundreds of successive layers of representations
  • Layered representations are (almost always) learned via models called neural networks (structured in literal layers stacked on top of each other)
  • “Neural network”
    • Reference to neurobiology as central DL concepts inspired from understanding brain
    • BUT no evidence that brain implements mechanisms used in DL!