• ferret
    link
    fedilink
    English
    112 years ago

    How can they be lossless? Isn’t a neural network inherently lossy?

    • @Bogasse@lemmy.ml
      link
      fedilink
      English
      6
      edit-2
      2 years ago

      I suppose the compression process looks like this :

      • call the model to predict the most probable next tokens (this is deterministic)
      • encode next tokens by with its ranking in model prediction

      If the model is good at predicting what the next token is, I suppose you need only 2bits to encode each token (for any of the top 4 predictions).

    • @9point6@lemmy.world
      link
      fedilink
      English
      62 years ago

      Lossless in terms of compression is being able to reconstruct the original bits of a piece of media exactly from its compressed bits.

      The thing that I’m wondering is how reliable this is