IV. Feasibility of Learning
IV. Feasibility of Learning
1. Learning is Impossible?
Lin provides two examples to show learning seems to be impossible.
2. Probability to the Rescue
Hoeffding’s Inequality:
is the actual frequency of event A and is my hypothetical frequency of event A. Hoeffding’s Inequality shows that the probability of the exitance of a huge gap() between and is tiny when I have a large N(big data)
the statement ‘’ is probably approximately correct(PAC)
3. Connection to Learning
The verification flow guarantee ‘historical records’(training set) are similar to the current conditon(test set).
Check ② of this quiz:
4. Connection to Real Learning
‘Bad Data’ could happens from time to time(let’s say if you filp a coin 5 times and get 5 heads). Accroding to Hoeffding’s inequality, the probability could be tiny when you have a large data.