吴恩达 Convolutional Neural Networks 第一周quizzes详解

1.What do you think applying this filter to a grayscale image will do?

Detect horizontal edges
Detect vertical edges
Detect 45 degree edges
Detect image contras
这个滤波器左右对称，所以检测的是竖的线

2.Suppose your input is a 300 by 300 color (RGB) image, and you are not using a convolutional network. If the first hidden layer has 100 neurons, each one fully connected to the input, how many parameters does this hidden layer have (including the bias parameters)?
9,000,001
9,000,100
27,000,001
27,000,100
（300×300×3+1）×100=27000100

3.Suppose your input is a 300 by 300 color (RGB) image, and you use a convolutional layer with 100 filters that are each 5x5. How many parameters does this hidden layer have (including the bias parameters)?
2501
2600
7500
7600
（5×5×3+1 ）×100==7600

4.You have an input volume that is 63x63x16, and convolve it with 32 filters that are each 7x7, using a stride of 2 and no padding. What is the output volume?
29x29x32
16x16x32
16x16x16
29x29x16
（63-7）/2 +1=29 有32个通道，所以×32

5.You have an input volume that is 15x15x8, and pad it using “pad=2.” What is the dimension of the resulting volume (after padding)?
19x19x8
17x17x8
19x19x12
17x17x10
f+2P = 15+4=19

6.You have an input volume that is 63x63x16, and convolve it with 32 filters that are each 7x7, and stride of 1. You want to use a “same” convolution. What is the padding?
1
2
3
7
(63+2p-7)/1+1=63 所以p=3

7.You have an input volume that is 32x32x16, and apply max pooling with a stride of 2 and a filter size of 2. What is the output volume?
15x15x16
16x16x8
16x16x16
32x32x8
(32-2)/2=16 通道数不变还是16

8.Because pooling layers do not have parameters, they do not affect the backpropagation (derivatives) calculation.
True
False
avg-pooling 把梯度分成N份（n为filtersize），max-pooling 记录下最大元素的位置，只传给这个，其他位置为0.

9.In lecture we talked about “parameter sharing” as a benefit of using convolutional networks. Which of the following statements about parameter sharing in ConvNets are true? (Check all that apply.)
It allows gradient descent to set many of the parameters to zero, thus making the connections sparse.（max-pooling）
It allows a feature detector to be used in multiple locations throughout the whole input image/input volume.
It allows parameters learned for one task to be shared even for a different task (transfer learning).
It reduces the total number of parameters, thus reducing overfitting.

10.In lecture we talked about “sparsity of connections” as a benefit of using convolutional layers. What does this mean?
Regularization causes gradient descent to set many of the parameters to zero.
Each filter is connected to every channel in the previous layer.（FC）
Each layer in a convolutional network is connected only to two other layers
Each activation in the next layer depends on only a small number of activations from the previous layer.