P Floding;180545 Wrote: > In fact, you have no safe way of estimating plausability when you have > incomplete knowledge. And if you have complete knowledge you know if it > is POSSIBLE or not. So much for that distinction.
That isn't entirely true, actually. Substitute probability of being true for plausibility, and you've got something to work with. It's a pretty hot research topic these days. That's what Bayesian statistics is all about, and what other "machine learning" stuff is generally about (this is what I do for a living, so I feel on pretty solid ground on this one), and is also, AFAIK, the main thrust of "decision theory". If you're interested, here are some classic references: Judea Pearl: Probabilistic Reasoning in Intelligent Systems http://www.amazon.com/Probabilistic-Reasoning-Intelligent-Systems-Plausible/dp/1558604790/sr=8-1/qid=1171477877/ref=sr_1_1/104-5904837-3949567?ie=UTF8&s=books Pearl's new book on causation http://bayes.cs.ucla.edu/BOOK-2K/why.html Hastie and Tibshirani: Elements of Statistical Learning http://www.amazon.com/Elements-Statistical-Learning-T-Hastie/dp/0387952845/sr=1-1/qid=1171477972/ref=pd_bbs_sr_1/104-5904837-3949567?ie=UTF8&s=books Haven't read the new one on causality, but the other two are great: you basically need undergrad level engineering math to get through them. -- totoro squeezebox 3 -> mccormack dna .5 -> audio physic tempo 4 ------------------------------------------------------------------------ totoro's Profile: http://forums.slimdevices.com/member.php?userid=5935 View this thread: http://forums.slimdevices.com/showthread.php?t=32352 _______________________________________________ audiophiles mailing list audiophiles@lists.slimdevices.com http://lists.slimdevices.com/lists/listinfo/audiophiles
