Please enable JavaScript.

Coggle requires JavaScript to display documents.

Chapter 6 Provost (Similarity and Distance (once the object can be…

- - - - many different ways to read the similarities or distance
        
        good spot to begin is with measurements from basic geometry
- - - - figuring out if something is discovered and if so what
- - - - " To use similarity for predictive modeling, the basic procedure is beautifully simple: given a new example and choose several that are the most similar to the new example
        
        then predict new examples target value
    - - shows whose label we want to predict indicated by a "?"
    - - Majority vote
        
        predicted class would be positive
  - - - come into play in real world applications
        
        Intelligibility
        
        complex issue,
        
        the justification of a specific decision and the intelligibility of an entire model
    - - thinking about clustering data is to focus on the clusters themselves
        
        most common use is called cluster center or centroid
- - - - this showing it was easy to calculate
- - - - look for useful sources of data to gain knowledge
        
        categories are not mutually exclusive
        
        this is an example of direct application to solve a problem
- - - - gives more than just yes or no