Please enable JavaScript.

Coggle requires JavaScript to display documents.

Machine Learning (Types of learning (Semi-Supervised Learning (● A lot of…

- - - - ● Clustering: find groups observation that are similar
      - ● Does not require labeled observations
- - - - REGRESSION FUNCTION
        
        Response
    - - Qualitative Output
      - Previous input-output observations
  - - - Similar within cluster
      - Dissimilar between clusters
    - - Grouping similar animal photos
        
        No labels
        
        No right or wrong
        
        Plenty possible clusterings
    - - Cluster data in k clusters!
  - - - Earlier Observations
        
        Estimate
        
        CLASSIFIER
      - Unseen Data
        
        CLASSIFIER
        
        Class
    - - Qualitative Output
      - Predefined Classes
- - - - Accuracy
        
        correctly classified instances / total amount of classified instances
      - Error
        
        1 - Accuracy
    - - RMSE - Root Mean Squared Error
    - - ● No label information
      - ● Need distance metric between points
  - - - Precision
        
        TP/(TP+FP)
      - Recall
        
        TP/(TP+FN)
      - Accuracy
        
        (TN + TP) / (TP+TN+FN+FP)