research

  • base on these hypothesis

    hypothesis

    1. real-life distributions are combinations of sub-distributions
    2. MLP can learn to fit sub-regions (sub-distributions) of the data
    Link to original
  • design a model that learn the sub-distributions in the data while also ensure those sub-distributions are separated
    • the distance between the distributions of latent vectors (at some middle layer or any part of network) and the distributions of the final output must be similar/proportional/equivalent
      • datasets can be artificially created to fit this description, i.e. the separation are known, and inductive bias can be used to design the algorithm
      • then try to make the algorithm learn to cluster the data without inductive bias