Once upon a time a young shepherd boy started tending the flock on his own. In the first week, he watched as twice another shepherd cried "wolf!" and the villagers raced to their aid, scaring off the wolf, and hailing the shepherd a hero. The next day, feeling bored and lonely, the boy cried "wolf!" and the villagers rushed to him, only to find there was no wolf. The next day, he cried "wolf!" again, and the villagers rushed up the hill, though they went away grumbling when no wolf was found. On the tenth day, he saw a real live wolf making for his sheep, but when he shouted "wolf!" no one came. And he and his entire flock were eaten.
The moral of this story is that the strength of beliefs can be updated based on new evidence, and that is the foundation of how Machine Learning works. Can you get it to calculate the conditional probability that there is a wolf using Bayes' Theorem? P(A|B) = (P(B|A)*P(A))/P(B)
