machine learning chapter 35
TRANSCRIPT
-
7/27/2019 machine learning chapter 35
1/6
Module
12Machine Learning
Version 2 CSE IIT, Kharagpur
-
7/27/2019 machine learning chapter 35
2/6
Lesson35
Rule Induction andDecision Tree - I
Version 2 CSE IIT, Kharagpur
-
7/27/2019 machine learning chapter 35
3/6
12.3 Decision Trees
Decision trees are a class of learning models that are more robust to noise as well as more
powerful as compared to concept learning. Consider the problem of classifying a star
based on some astronomical measurements. It can naturally be represented by the
following set of decisions on each measurement arranged in a tree like fashion.
LLuummiinnoossiittyy
MMaassss
TTyyppee AA TTyyppee BB
TTyyppee CC
>> TT11 TT22
-
7/27/2019 machine learning chapter 35
4/6
LLuummiinnoossiittyy
MMaassss
TTyyppee AA TTyyppee BB
TTyyppee CC
>> TT11 TT22
-
7/27/2019 machine learning chapter 35
5/6
2. Separate training set D into subsets {D1, D2, .., Dk} where each subset Di contains
3. Recursively apply the algorithm on each new subset until examples have the same
lustration:
ttributes: size and humidity.t1
3 and t
Class N: Non-
poisonous
tt11
tt22
tt33
SSuuppppoossee wwee cchhoooosseessiizzee aass tthhee bbeesstt
ssiizzee
PP
>> TT11
-
7/27/2019 machine learning chapter 35
6/6
tt11
tt22
tt33
SSuuppppoossee wwee cchhoooossee hhuummiiddiittyyaass tthhee nneexxtt bbeesstt
ssiizzee
PP
>> TT11tt22 tt33 &&