Probabilistic Graphical Models 1: Representation-Week1-reasoning-patterns
课程链接:https://www.coursera.org/learn/probabilistic-graphical-models/lecture/KMjHs/reasoning-patterns
原CPD如下:
计算:
p(d1|g3) = p(d1, g3) / p(g3)
p(d1, g3) = p(g3, d1) = p(g3|d1, i0) * p(d1, i0) + p(g3|d1, i1) * p(d1, i1)
= 0.7*0.4*0.7 + 0.2*0.4*0.3 约等于0.22
p(g3) = p(g3|d1, i0) * p(d1, i0) + p(g3|d1, i1) * p(d1, i1) +
p(g3|d0, i0) * p(d0, i0) + p(g3|d0, i1) * p(d0, i1)
=0.7*0.4*0.7 + 0.2*0.4*0.3 +
0.3*0.6*0.7 + 0.02*0.68*0.3
约等于0.35
p(d1|g3) =0.22/0.35 约等于0.6286
p(i1|g3) = p(i1, g3) / p(g3)
p(i1, g3) = p(g3| i1, d0) * p(i1, d0) + p(g3| i1, d1) * p(i1, d1)
= 0.02 * 0.3 * 0.6 + 0.2 * 0.3 * 0.4
= 0.0276
p(i1|g3) = 0.0276/0.35 = 0.079
p(i1 | g3, d1) = p(i1, g3, d1) / p(g3, d1)
p(i1, g3, d1)= p(g3| i1, d1) * p(i1, d1) = 0.2 * 0.4 * 0.3
p(i1 | g3, d1) =0.2 * 0.4 * 0.3/0.22 = 0.1091