Question

Calculating probabiltiy from basian networks

Answer 1

“Faith, and it’s an uncertain world entirely.” --- Errol Flynn, “Captain Blood” (1935) = We need probability theory for our agents!! The world is chaos!! Could you design a logical agent that does the right thing below?? Extended example of 3-way Bayesian Networks A B C Conditionally independent effects: p(A,B,C) = p(B|A)p(C|A)p(A) B and C are conditionally independent Given A E.g., A is a disease, and we model B and C as conditionally independent symptoms given A E.g., A is Fire, B is Heat, C is Smoke. “Where there’s Smoke, there’s Fire.” If we see Smoke, we can infer Fire. If we see Smoke, observing Heat tells us very little additional information. Extended example of 3-way Bayesian Networks Suppose I build a fire in my fireplace about once every 10 days… A= Fire C= Heat B= Smoke Conditionally independent effects: P(A,B,C) = P(B|A)P(C|A)P(A) Smoke and Heat are conditionally independent given Fire. If we see B=Smoke, observing C=Heat tells us very little additional information