Link Search Menu Expand Document

Mitchell, Ch. 3

  1. Give a non-empty set that has entropy 0.
  2. Give a non-empty set that has entropy 1.
  3. Compute: Entropy[17+,5-] (complete expression only, no need for calculator).
  4. Give the formula for the information gain, Gain(S,A),  resulting from decomposing set, S,  on a given attribute, A.
  5. Given the entropy of set  S, calculate the Gain(S,A),  resulting from decomposing, S  on a given attribute, A
  6. For the data on text page 59 use variables, function log2 and the fact that Sunny has entropy, .970, to compute a precise exspression that evaluates to Gain(Sunny,Wind).
    Wind when Sunny:
    • Weak: 2N, 1 Y,proportion= 3/5

      entropyWeak = -(2/3)log2(2/3) -(1/3)log2(1/3) = .9183

    • Strong: 1N 1Y ,proportion= 2/5

      entropyStrong = -(1/2)log2(1/2) -(1/2)log2(1/2) = 1

    • Gain(Sunny,Wind) =

      =.97 - (3/5)(entropyWeak) - (2/5) entropyStrong = 97- (3/5)(.9183) - (2/5)(1) = .97 - .55098 - .4 = .01902

  7. Describe the inductive bias of ID3. good trees have low depth and nodes near the root corresponding to high entropy variables
  8. Calculate the entropy for a given variable that has more than two values (like V = {1,2,3,2,1,1}).
  9. Describe approaches to avoiding overtraining of decision trees (p68).
  10. What is pruning of a decision tree node?
  11. How does a trainer determine that it is desirable to prune a node?
  12. Give an example of a decision-tree rule.
  13. Give rules for the four leaves in the decision tree on p53.
  14. Describe the components of a decision-tree rule, defining the terms If portion , antecedentthen portion, post condition.
  15. List the steps of Rule Post-Pruning (p71).
  16. Explain why rule post-pruning is more powerful than node post pruning (p72). (Can remove paths through nodes instead of entire nodes, can remove entire node without need to restructure a tree, easier to read.)