【吴恩达深度学习】01_week4_quiz Key concepts on Deep Neural Networks

(1)What is the “cache” used for in our implementation of forward propagation and backward propagation?
[A]It is used to keep track of the hyperparameters that we are searching over, to speed up computation.
[B]We use it to pass variables computed during forward propagation to the corresponding backward propagation step. It contains useful values for backward propagation to compute derivatives.
[C]We use it to pass variables computed during backward propagation to the corresponding forward propagation step. It contains useful values for forward propagation to compute activation.
[D]It is used to cache the intermediate values of the cost function during training.
答案：B

(2)Among the following, which ones are “hyperparameters”?(Check all that apply.)
[A]learning rate $\alpha$
[B]number of iterations
[C]size of the hidden layers $n^{[l]}$
[D]bias vectors $b^{[l]}$
[E]number of layers L in the neural network
[F]weight matrices $W^{[l]}$
[G]activation values $a^{[l]}$
答案：A,B,C,E
解析：模型参数通常是有数据来驱动调整，超参数则不需要数据来驱动，而是在训练前或者训练中人为的进行调整的参数。

(3)Which of the following statements is true?
[A]The deeper layers of a neural network are typically computing more complex features of the input than the earlier layers.
[B]The earlier layer of a neural network are typically computing more complex features of the input than the deeper layers.
答案：A

(4)Vectorization allows you to compute forward propagation in an L-layer neural network without an explicit for-loop(or any other explicit iterative loop) over the layers $I=1,2,...L$.True/False?
答案：False

(5)Assume we store the values for $n^{[l]}$ in an array called layers, as follows: layer_dims=[nx,4,3,2,1]. So layer 1 has four hidden units, layer 2 has 3 hidden units and so on. Which of the following for-loops will allow you to initialize the parameters for the model?
[A]
[B]
[C]
[D]
答案：D

(6)Consider the following neural network.

How many layers does this network have?
[A]The number of layer L is 4. The number of hidden layers is 3.
[B]The number of layer L is 3. The number of hidden layers is 3.
[C]The number of layer L is 4. The number of hidden layers is 4.
[D]The number of layer L is 5. The number of hidden layers is 4.
答案：A
解析：输出层不算隐藏层

(7)During forward propagation, in the forward function for a layer l you need to know that is the activation function in a layer(Sigmoid, tanh,ReLu,etc.). During back propagation, the corresponding backward function also needs to know what is the activation function for layer l, since the gradient depends on it. True/False?
答案：True
解析：不同的激活函数导数不同

(8)There are certain functions with the following properties:
To compute the function using a shallow network circuit, you will need a large network(where we measure size by the number of logic gates in the network), but to compute it using a deep network circuit, you need only an exponentially smaller network. True/False?
答案：True
解析：见视频：Why deep representations

(9)Consider the following 2 hidden layer neural network:

Which of the following statements are True?(Check all that apply)
[A] $W^{[1]}$ will have shape (4,4)
[B] $b^{[1]}$ will have shape (4,1)
[C] $W^{[1]}$ will have shape (3,4)
[D] $b^{[1]}$ will have shape (3,1)
[E] $W^{[2]}$ will have shape (3,4)
[F] $b^{[2]}$ will have shape (1,1)
[G] $W^{[2]}$ will have shape (3,1)
[H] $b^{[2]}$ will have shape (3,1)
[I] $W^{[3]}$ will have shape (3,1)
[J] $b^{[3]}$ will have shape (1,1)
[K] $W^{[3]}$ will have shape (1,3)
[L] $b^{[3]}$ will have shape (3,1)
答案：A,B,E,H,J,K

(10)Whereas the previous question used a specific network, in the general case what is the dimension of $W^{[l]}$, the weight matrix associated with layer I ?
[A] $W^{[l]}$ has shape $(n^{[l-1]},n^{[l]})$
[B] $W^{[l]}$ has shape $(n^{[l+1]},n^{[l]})$
[C] $W^{[l]}$ has shape $(n^{[l]},n^{[l-1]})$
[D] $W^{[l]}$ has shape $(n^{[l]},n^{[l+1]})$
答案：C