Homework_Week4_Coursera【Machine Learning】AndrewNg、Neural Networks: Representation

Neural Networks: Representation

1.Which of the following statements are true? Check all that apply.

解析：
A 说两层神经网络，一层输入，一层输出、就可以实现异或功能、无法实现。课上案例必须要有隐藏层
B 逻辑函数完全可以神经网络表达，所以正确
C 有多类别分类任务，用3层网络分三类、设a(3)1是第一个输出、类似的，第二个第三个输出都加起来为1错误、这是最好情况，非一定
D 确实sigmoid函数输出都是在0，1故正确
答案：BD

2. 【wrong】Consider the following neural network which takes two binary-valued inputsXX Which of the following logical functions does it (approximately) compute?

解析：
计算一下即可

30+x1*-20 +x2*-20	x1	x2	result
30	0	0	1
10	1	0	1
10	0	1	1
-10	1	1	0

很明显是或

答案：C

纠错：或的话0或上0应该是0、1或1还是1、而与的话只有1与1是1、前三项情况都为0、取反后，非与就对了所以题选Not And

最终答案：A

3.Consider the neural network given below. Which of the following equations correctly computes the activation XXX Note: g(z)g(z) is the sigmoid activation function.

解析：第三层的输入一定来自第二层，所以选A选项
答案：A

4.You have the following neural network:XXX

解析：theta1是33矩阵、x是31、B里面无法相乘、错误，先求Z后整体放入sigmoid自变量中，所以选A
答案：A

5.You are using the neural network pictured below and have learned the parametersXXX

解析：两边都交换了、等于没换答案：
答案：A

最终得分：80