Here's the question you clicked on:

55 members online
  • 0 replying
  • 0 viewing


  • 3 years ago

I am doing problem set 10. How do you compute the distance between a point in the holdout set to its nearest cluster? I was using points in the clusters (the points in the training set), but that means the holdout error wont change if k changes. Should I use distance between holdout point and nearest centroid?

  • This Question is Open

    Not the answer you are looking for?
    Search for more explanations.

    • Attachments:

Ask your own question

Sign Up
Find more explanations on OpenStudy
Privacy Policy