Which is more important: the depth of the data or the width of the loop?

· Bits and Bobs 9/21/26
  • Which is more important: the depth of the data or the width of the loop?
    • Whose learning loop will be better?
    • The former is only possible with your data.
      • Inside the Coasian veil.
    • The latter requires buying someone else's data.
    • A friend did a simulation and concluded that the learning loop aggregator (the wide one) does better no matter how good the data.
    • Transfer learning is just too powerful.