资源描述:
《不确定性推理部分参考答案》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库。
1、第6章不确定性推理部分参考答案6.8设有如下一组推理规则:r1:IFE1THENE2(0.6)r2:IFE2ANDE3THENE4(0.7)r3:IFE4THENH(0.8)r4:IFE5THENH(0.9)且已知CF(E1)=0.5,CF(E3)=0.6,CF(E5)=0.7。求CF(H)=?解:(1)先由r1求CF(E2)CF(E2)=0.6×max{0,CF(E1)}=0.6×max{0,0.5}=0.3(2)再由r2求CF(E4)CF(E4)=0.7×max{0,min{CF(E2),CF(E3)}}=0.7×
2、max{0,min{0.3,0.6}}=0.21(3)再由r3求CF1(H)CF1(H)=0.8×max{0,CF(E4)}=0.8×max{0,0.21)}=0.168(4)再由r4求CF2(H)CF2(H)=0.9×max{0,CF(E5)}=0.9×max{0,0.7)}=0.63(5)最后对CF1(H)和CF2(H)进行合成,求出CF(H)CF(H)=CF1(H)+CF2(H)+CF1(H)×CF2(H)=0.6926.10 设有如下推理规则r1:IFE1THEN(2,0.00001)H1r2:IFE2THEN
3、(100,0.0001)H1r3:IFE3THEN(200,0.001)H2r4:IFH1THEN(50,0.1)H2且已知P(E1)=P(E2)=P(H3)=0.6,P(H1)=0.091,P(H2)=0.01,又由用户告知:P(E1
4、S1)=0.84,P(E2
5、S2)=0.68,P(E3
6、S3)=0.36请用主观Bayes方法求P(H2
7、S1,S2,S3)=?解:(1)由r1计算O(H1
8、S1)先把H1的先验概率更新为在E1下的后验概率P(H1
9、E1)P(H1
10、E1)=(LS1×P(H1))/((LS1-1)×P(
11、H1)+1)=(2×0.091)/((2-1)×0.091+1)=0.16682由于P(E1
12、S1)=0.84>P(E1),使用P(H
13、S)公式的后半部分,得到在当前观察S1下的后验概率P(H1
14、S1)和后验几率O(H1
15、S1)6P(H1
16、S1)=P(H1)+((P(H1
17、E1)–P(H1))/(1-P(E1)))×(P(E1
18、S1)–P(E1))=0.091+(0.16682–0.091)/(1–0.6))×(0.84–0.6)=0.091+0.18955×0.24=0.136492O(H1
19、S1)=P(H1
20、S1)
21、/(1-P(H1
22、S1))=0.15807(2)由r2计算O(H1
23、S2)先把H1的先验概率更新为在E2下的后验概率P(H1
24、E2)P(H1
25、E2)=(LS2×P(H1))/((LS2-1)×P(H1)+1)=(100×0.091)/((100-1)×0.091+1)=0.90918由于P(E2
26、S2)=0.68>P(E2),使用P(H
27、S)公式的后半部分,得到在当前观察S2下的后验概率P(H1
28、S2)和后验几率O(H1
29、S2)P(H1
30、S2)=P(H1)+((P(H1
31、E2)–P(H1))/(1-P(E2)))×(P
32、(E2
33、S2)–P(E2))=0.091+(0.90918–0.091)/(1–0.6))×(0.68–0.6)=0.25464O(H1
34、S2)=P(H1
35、S2)/(1-P(H1
36、S2))=0.34163(3)计算O(H1
37、S1,S2)和P(H1
38、S1,S2)先将H1的先验概率转换为先验几率O(H1)=P(H1)/(1-P(H1))=0.091/(1-0.091)=0.10011再根据合成公式计算H1的后验几率O(H1
39、S1,S2)=(O(H1
40、S1)/O(H1))×(O(H1
41、S2)/O(H1))×O(H1)=(0.
42、15807/0.10011)×(0.34163)/0.10011)×0.10011=0.53942再将该后验几率转换为后验概率P(H1
43、S1,S2)=O(H1
44、S1,S2)/(1+O(H1
45、S1,S2))=0.35040(4)由r3计算O(H2
46、S3)先把H2的先验概率更新为在E3下的后验概率P(H2
47、E3)P(H2
48、E3)=(LS3×P(H2))/((LS3-1)×P(H2)+1)=(200×0.01)/((200-1)×0.01+1)=0.09569由于P(E3
49、S3)=0.36
50、S)公式的
51、前半部分,得到在当前观察S3下的后验概率P(H2
52、S3)和后验几率O(H2
53、S3)P(H2
54、S3)=P(H2
55、¬E3)+(P(H2)–P(H2
56、¬E3))/P(E3))×P(E3
57、S3)由当E3肯定不存在时有P(H2
58、¬E3)=LN3×P(H2)/((LN3-1)×P(H2)+1)=0.001×0.01/((0.001-1)×0.