The ID3 algorithm can be summarized as follows:
Take all unused attributes and count their entropy concerning test samples
Choose attribute for which entropy is minimum (or, equivalently, information gain is maximum) ...
splitting criterion in ID3 The point of the ID3 algorithm is to decide the best attribute, out of those not already used, on which to split the training instances that are classified to a particular branch node.
Chapter 8 begins with a discussion of the ID3 algorithm. This is used in many learning programs, including a world-beater -- better than the human expert who "taught" it -- at diagnosing soybean diseases (Michalski & Chilausky, 1980).
 See also: Decision Trees, Classification, Machine learning, Branch, Attribute
  
|
RSS
