Question: Suppose that a learning algorithm is trying to find a consistent hypothesis when the classifications of examples are actually random. There are u Boolean attributes,
Suppose that a learning algorithm is trying to find a consistent hypothesis when the classifications of examples are actually random. There are u Boolean attributes, and examples are drawn uniformly from the set of 2n possible examples. Calculate the number of examples required before the probability of finding a contradiction in the data reaches 0.5.
Step by Step Solution
3.42 Rating (171 Votes )
There are 3 Steps involved in it
To solve this problem well need to calculate the expected number of examples required before a contradiction arises when classifications are random Step 1 Understand the problem setup Definitions and ... View full answer
Get step-by-step solutions from verified subject matter experts
Document Format (1 attachment)
21-C-S-A-I (267).docx
120 KBs Word File
