Hello,
I have been working on this problem for a couple of days and I am having some trouble figuring it out. This is a homework question for my AI masters class. Just wondering if I could get a little help either understanding the concept or how the algorithm would work. Thanks for your time.

Here is how it reads:
Suppose that a learning algorithm is trying to find a consistent hypothesis when the classification 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.

__________________
This message is a natural product made from recycled electrons. The slight
variations in spelling and grammar enhance its individual character and
beauty and in no way are to be considered flaws or defects.

I'm sorry that I didn't get to your question sooner. I have been trying to learn I little bit more to see if I would be able to help you out but have found that you must be smarter then I am. As this goes way over my head and gives me a headache when I start to think about it. I'm sorry that I'm unable to help you. I would like to know when you get the answer what it was, as I'm really interested in this type of thing. I would also like to know if you have any links you could post that I could take a look at. Thanks and I'm sorry that I can't be of more help.

__________________
If builders built buildings the way programmers wrote programs, then the first woodpecker that came along would destroy civilization.