# Get Yourself Some Bayes!

I read about Bayesian probability first on Paul Graham’ milestone article on spam two years ago. Amazingly, his Bayesian based algorithm did the same thing that a sophisticated AI algorithm will do, i.e. to precisely identify spam emails (success rate: 995 out of 1000) just like humans do it with their image recognition, natural language processing capabilities and yet unparalleled intelligence. That got me interested and Bayesian probabilities got added in my things to learn. I just recently finished my that goal and I can’t over emphasize, its an serious weapon in your. The coolest way to understand Bayes is this article on web. Unlike most others, this article states real equation at the end rather then at the start or middle of the article and author writes “By this point, Bayes’ Theorem may seem blatantly obvious or even tautological, rather than exciting and new. If so, this introduction has entirely succeeded in its purpose.” Yes, indeed he is! One of the points that isn’t crystal clear in this article is the difference between P(A&B) and P(A|B). I wouldn’t go on explaining that but you can see on left the small diagram that I created which will aid in understanding with above article. These two terms are actually the key in understanding why traditional probability analysis (which is about time independent calculations i.e. about probabilities that exist after all events have been finished occurring) is different then Bayesian analysis (which is about probabilities when we are still waiting for some events still to occur but we don’t know which one will really occur).