
Bayesian Thinking
Programming Throwdown
00:00
The Upper Confidence Bound of Something Kan Can Give You This Nice of Learning
Having the uncertainty lhat you do some reallyrell cool things, like imagine against problems dependent. Four square is actually a good example. Let's say we're recommending restaurants to somebody and don't know whether they like typhood or not. What maybe we should do? What's called the upper confidence bounds - which is just a fancy of saying, if the distribution is really wide, we want to be more likely to choose this item.
Transcript
Play full episode