11 Matching Annotations
  1. Feb 2021
    1. dream up music that echoes Bach or the Beatles

      Introducing the topic

      • The phrase "dream up music" makes the whole thing feel magical, yet the mentioning of "Bach" and "the Beatles" make it more realistic and down to earth
    2. human music is rooted in culture, history, and language. It has remarkable capacity to surprise, shock, and inspire

      Groups of 3

      • The author makes effective use of the lists of 3 elements to make a decisive point:
      • "culture, history and language" + "surprise, shock, and inspire"
    3. how does it compare to human musical creativity

      Transition

      • The author makes use of a question to segue into the next part of the article
      • This is a question that is likely to come up in any reader's mind. It is a great and captivating transition
    4. machine learning researcher at the University of Toronto who's interested in AI-generated music, was wowed

      Credibility

      • By mentioning the profession of Sageev, as well as his full name, along the word "wowed", the author is adding credibility to the argument, showing that he isn't the only one believing that these are important findings
    5. If you’ve ever wondered what it might sound like if the Beatles jammed with Lady Gaga

      Making it relatable

      • By drawing on well-known groups that are known by the majority of readers, the author helps people "buy into" their idea
    6. Who’d have thought that Richard Wagner and Britney Spears shared so much musical taste?

      Examples

      • Showing a surprising yet real example to invoke curiosity, expressing the odd nature of the findings
    7. interesting from a music-history perspective

      Transition

      • The author transitions from discussion of reactions to the AI model, to its relevance of music-theory
      • Showing that it's not just about the AI, but it's about a real science that doesn't seem connected to AI
    8. The researchers trained a very large neural network known as a transformer. This type of network learns to predict the next few notes in a piece of music. You can then give the network a few notes, and have it conjure up something new. It makes it possible to mix different genres and styles, and even to add and remove specific instruments.

      Simplifying for average reader

      • The author intentionally leaves out the AI-part of the discussion, providing only the crucial pieces of information needed to understand the meaning behind the technology
    9. If Mozart were alive today (and if he was feeling a bit uninspired)

      Setting the stage

      • Beginning the article by putting together "Mozart" and "uninspired" in the same sentence
      • Immediately draws attention to music, and the parallel between history and now