Week Two: Programming Fundamentals of Neural Networks-----------10 quiz questions (neural network Basics)

--------------------------------------------------Chinese Translation------------------------------------------------------------------- ----------------------

1. What is the calculation of neurons? (B)

A. The neuron calculates the average of all features before applying the output to the activation function

B. The neuron calculates a linear function (Z = Wx + b), then an activation function

C. Neuron calculates an activation function followed by a linear function (Z = Wx + b)

D. A neuron calculates a function g, which scales the input x linearly (Wx + b)

2. Which of the following is a loss function? B

See the corresponding English question 2

3. Assume that img is an array (32,32,3) that represents a 32x32 image with a 3-color channel red, green, and blue. How do I reshape it as a column vector? (B)

A. x = img Reshaping (32 * 32,3))

B. x = img Reshaping (32 * 32 * 3,1))

C. x = img Remodeling (1,32 * +, * 3))D. x = img Remodeling (3,32 * +))4. Consider the following two random arrays "a" and "B", what is the shape of "C"? B

# A.shape = (2, 3) # B.shape = (2, 1)C = A + b

A. C.shape = (2, 1)

B. C.shape = (2, 3)

C. C.shape = (3, 2)

D. Cannot be calculated due to size mismatch. This will be "wrong"!

5. Consider the following two random arrays "a" and "B", what is the shape of "C"? D

# A.shape = (4, 3) # B.shape = (3, 2)C = a*b

A. cannot be calculated due to size mismatch. This will be "wrong"!

A. C.shape = (3, 3)

B. C.shape = (4, 2)

C. C.shape = (4, 3)

6. Assume that each sample is characterized by an NX dimension,X=[X(1)x(2): . What is the dimension of X (m)],x? (A)

A. (nx,m)

B. (1,m)

C. (m,1)

D. (M,NX)

7, Remember "NP." Dot (A, b) "performs matrix multiplication on A and B, while" A * b "performs element multiplication. Consider the following two random arrays of "a" and "B":

# A.shape = (12288, max) # B.shape = (a) c = Np.dot (A, B)

what is the shape of C? (D)

A. c. Shape = (12288, max.)

B. cannot be calculated due to size mismatch. This will be "wrong"!

C. c. Shape = (150150)

D. c. Shape = (12288, $)

8, please consider the following code snippet, how do you quantify? B

# A.shape = (3,4) # B.shape = (4,1)  for  in range (3):  as in range (4):    = a[i][j] + b[j]

A. C = a + b

B. C = A + b.t

C. C = a.t + b

D. C = a.t + b.t

9. Please consider the following code: C results? (If you are unsure, run this lookup in Python at any time). A

A = Np.random.randn (3, 3= NP.RANDOM.RANDN (3, 1= a*b

A. This will trigger the broadcast mechanism, so B is copied three times, becomes (3,3), * represents the matrix corresponding element multiplied, so the size of C will be (3, 3)B. This will trigger the broadcast mechanism, so B is duplicated three times, becomes (3, 3), * represents matrix multiplication, operations two 3x3 matrices, so the size of C will be (3, 3)C. This multiplies a 3x3 matrix A with a 3x1 vector B, resulting in a 3x1 vector. That is, the size of C (3,1). D. This will result in an error because you cannot use "*" to manipulate the two matrices. You need to switch to Np.dot (A, b)10.consider the following calculation diagram. What is output J? (Note: The answer to this question is uncertain because the website cannot display the picture.) The knowledge point of the study is the calculation chart)

A. J = (c-1) * (b + a)

B. J = (A-1) * (b + c)

C. J = a*b + b*c + a*c

D. J = (b-1) * (C + a)

Week Two: Programming Fundamentals of Neural Networks-----------10 quiz questions (neural network Basics)