Question: Suppose that a learning algorithm is trying to find a consistent hypothesis when the classifications of examples are actually random. There are n Boolean attributes,
Suppose that a learning algorithm is trying to find a consistent hypothesis when the classifications of examples are actually random. There are n Boolean attributes, and examples are drawn uniformly from the set of 2^n possible examples. Calculate the number of examples required before the probability of finding a contradiction in the data reaches 0.5.
Note:In this scenario, the goal is to find how many examples are required before the probability of finding a contradiction in the data reaches 0.5. As such, using an equation you must arrive at a numerical answer for this scenario.
Step by Step Solution
There are 3 Steps involved in it
Problem Understanding In this scenario we have n Boolean attributes which means there are 2n possible examples The classification of examples is random meaning the target function is inconsistent The ... View full answer
Get step-by-step solutions from verified subject matter experts
