【吴恩达深度学习】01_week2_quiz Neural Netwoek Basics

(1)What does a neuron compute?
[A]A neuron computes an activation function followed by a linear function(z=Wx+b)
[B]A neuron computes the mean of all features before applying the output to an activation function.
[C]A neuron computes a linear function(z=Wx+b) followed by an activation function.
[D]A neuron computes a function g that scales the input x linearly(Wx+b)
答案：C
解析：如图所示

(2)Which of these is the “Logistic Loss”？
[A] $L^{(i)}({\hat{y}}^{(i)},y^{(i)})=|y^{(i)}-{\hat{y}}^{(i)}{|}^2$
[B] $L^{(i)}({\hat{y}}^{(i)},y^{(i)})=max(0,y^{(i)}-{\hat{y}}^{(i)})$
[C] $L^{(i)}({\hat{y}}^{(i)},y^{(i)})=|y^{(i)}-{\hat{y}}^{(i)}|$
[D] $L^{(i)}({\hat{y}}^{(i)},y^{(i)})=-y^{(i)}\log ({\hat{y}}^{(i)})+(1-y^{(i)})\log (1-{\hat{y}}^{(i)})$
答案：D

(3)Suppose img is a (32,32,3) array, representing a 32x32 image with 3 color channels red, green and blue. How do you reshape this into a column vector?
[A] x = img.reshape((32*32*3,1))
[B] x = img.reshape((1,32*32*3))
[C] x = img.reshape((3,32*32))
[C] x = img.reshape((32*32,3))
答案：A
解析：注意，题目要求列向量（column vector）

(4)Consider the two following random arrays “a” and “b”:

a = np.random.randn(2,3) # a.shape = (2,3)
b = np.random.randn(2,1) # a.shape = (2,1)
c = a+b

What will be the shape of “c”?
[A] c.shape = (2,1)
[B] c.shape = (3,2)
[C] c.shape = (2,3)
[D] The computation cannot happen because the size don’t match. It’s going to be “Error” !
答案：C
解析：Broadcasting

(5)Consider the two following random arrays “a” and “b”:

a = np.random.randn(4,3) # a.shape = (4,3)
b = np.random.randn(3,2) # a.shape = (3,2)
c = a*b

What will be the shape of “c”?
[A] c.shape = (3,3)
[B] c.shape = (4,2)
[C] c.shape = (4,3)
[D] The computation cannot happen because the size don’t match. It’s going to be “Error” !
答案：D
解析：对于ndarray，*运算符为元素乘法，matmul为矩阵乘法。

(6)Suppose you have $n_x$ input features per example. Recall that $X=[x^{(1)},x^{(2)}...x^{(m)}]$.What is the dimension of X?
[A] $(1,m)$
[B] $(m,1)$
[C] $(x_x,m)$
[D] $(m,n_x)$
答案：C

(7)Recall that “np.dot(a,b)” performs a matrix multiplication on a and b, whereas “a*b” performs an element-wise multiplication.
Consider the two following random arrays “a” and “b” .

a = np.random.randn(12288,150) # a.shape = (12288,150)
b = np.random.randn(150,45) # a.shape = (150,45)
c = np.dot(a,b)

What will be the shape of “c”?
[A] c.shape = (150,150)
[B] c.shape = (12288,150)
[C] c.shape = (12288,45)
[D] The computation cannot happen because the size don’t match. It’s going to be “Error” !
答案：C

(8)Consider the following code snippet:

# a.shape = (3,4)
# b.shape = (4,1)

for i in range(3):
    for j in range(4):
        c[i][j]=a[i][j]+b[j]

How do you vectorize this?
[A] c = a.T + b.T
[B] c = a.T + b
[C] c = a + b.T
[D] c = a + b
答案：C

(9)Consider the following code:

a = np.random.randn(3,3) 
b = np.random.randn(3,1) 
c = a*b

What will be c?(If you’re not sure, feel free to run this in python to find out).
[A]This will invoke broadcasting, so b is copied three times to become (3,3), and * is an element-wise product so c.shape will be (3,3)
[B]This will invoke broadcasting, so b is copied three times to become (3,3), and * invokes a matrix multiplication operation of two 3x3 matrices so c.shape will be (3,3)
[C]This will multiply a 3x3 matrix a with a 3x1 vector, thus resulting in a 3x1 vector. That is, c.shape = (3,1)
[D]It will lead to an error since you cannot use “*” to operate on these two matrices. You need to instead use np.dot(a,b)
答案：A

(10)Consider the following computation graph.

What is the output J?
[A] $J=(c-1)\ast (b+a)$
[B] $J=(a-1)\ast (b+c)$
[C] $J=a\ast b+b\ast c+a\ast c$
[D] $J=(b-1)\ast (c+a)$
答案：B
解析：
$$\begin{array}{rl}J& =u+v-w\\ & =a\ast b+a\ast c-(b+c)\\ & =a\ast (b+c)-(b+c)\\ & =(a-1)\ast (b+c)\end{array}$$