COMPSCI 171 Quiz: 2013-fq-cs-171-quiz-4-key
Document Summary
Quiz#4 fall quarter, 2013 20 minutes. P(h | d) = p(d | h) p(h) / p(d) P(h | d) = p(h d) / p(d) A decision tree can learn and represent any boolean function. The information gain from an attribute a is how much classifier accuracy improves. From right: (5 pts) definition of conditional probability. Write down the definition of p(h | d) in terms of p(h), p(d), p(h d), and p(h d): (5 pts) bayes" rule. Write down the result of applying bayes" rule to p(h | d): 15 pts total, 3 pts each) machine learning. Label the following statements t (true) or f (false). 3b. when attribute a is added to the example feature vectors in the training set. 3e. observations about the world: (30 pts total, 2 pts each) machine learning concepts. For each of the following items on the left, write in the letter corresponding to the best answer or the correct definition on the right.
