Ad

Saturday, March 25, 2017

K Means Clustering Unsupervised Learning - Udacity Machine Learning Nanodegree Flash Card


  • Draw a line connecting two centroids and use the half way line as a division line for two hyperplanes (if two clusters). Results vary greatly.
  • Initial positions of centroid can strongly influence result. Different initial positions give completely different results.
  • Analogy "Rubber Band"
  • Center of the cluster is called a centroid
  • Number of centroids at initiation can heavily influence the result. 
  • Great for ... PROS:
  • Bad for ... CONS ... limitations:
    • Hill climbing algorithm.
    • Result depends on initiation
    • If initiation is close to local optima, may be sticky. Never move away. Ignore global optima. Bad initial centroids exist
    • If there are more potential clusters, there are more local optima. Run iterate the algorithm many times to avoid being stuck. 

No comments:

Post a Comment

Machine Learning with Emoji for Fun?

Here's an interesting idea. Explain Machine Learning with Emojis! It's not trivial to convey complex ideas with symbols but it is a ...