原书出处
Causal AI
get more blame for crashing the network if it was highly unusual for employees to access that server. We can quantify the abnormality of a causal event with probability; if event X=1 was abnormal, then it was unlikely to have occurred, so we assign a low value to P(X=1). One attribution measure, called actual causal strength (ACS), combines abnormality with probabilities of causation as follows:
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Causal AI/_epub-src/OEBPS/Text/chapter-8.xhtml
EPUB SHA-256:e55e7dc9d7966ea79311f2bc8d5bef7371a6dbb65240f11a2b3e44180b934e72