I love this visualization of thompson sampling ("bayesian bandits") from @ted_dunning:http://www.youtube.com/watch?v=1nQBnyaI6s0&sns=em …
-
-
@avibryant super! tx. could you do the same with a stream of diffs? seems like sw design is also an explore/exploit balance. -
@KentBeck fascinating. One key difference: the algorithm can switch strategies at high frequency, context switching for humans is costly. -
@avibryant i think i do a relatively low-cost context switch: "let's prove in an hour that XXX refactoring is impossible"
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.