卷積神經網絡Quiz4

Question 1
Face verification requires comparing a new picture against one person’s face, whereas face recognition requires comparing a new picture against K person’s faces.

True

False

解析：
人臉驗證（Verification）：

• Input：圖片、名字/ID；
• Output：輸入的圖片是否是對應的人。
• 1 to 1 問題。

人臉識別（Recognition）：

• 擁有一個具有K個人的數據庫；
• 輸入一副人臉圖片；
• 如果圖片是任意這K個人中的一位，則輸出對應人的ID。

---

Question 2
Why do we learn a function d(img1,img2) for face verification? (Select all that apply.)

We need to solve a one-shot learning problem.

This allows us to learn to predict a person’s identity using a softmax output unit, where the number of classes equals the number of persons in the database plus 1 (for the final “not in database” class).

Given how few images we have per person, we need to apply transfer learning.

This allows us to learn to recognize a new person given just a single image of that person.

解析：對於一個人臉識別系統，我們需要僅僅通過先前的一張人臉的圖片或者說一個人臉的樣例，就能夠實現該人的識別，那麼這樣的問題就是one shot 問題；其實在最後一層把Softmax函數去掉了；不需要遷移學習；人臉識別中，當需要對一個新的面孔進行識別時，只需要添加幾張該面孔進數據庫即可

---

Question 3
In order to train the parameters of a face recognition system, it would be reasonable to use a training set comprising 100,000 pictures of 100,000 different persons.

True

False

解析：不需要全不相同，每個人需要有幾張不同的照片。

---

4。Question 4
Which of the following is a correct definition of the triplet loss? Consider that α>0. (We encourage you to figure out the answer from first principles, rather than just refer to the lecture.)

max(||f(A)−f(P)||²−||f(A)−f(N)||²+α,0)

max(||f(A)−f(N)||²−||f(A)−f(P)||²+α,0)

max(||f(A)−f(N)||²−||f(A)−f(P)||²−α,0)

max(||f(A)−f(P)||²−||f(A)−f(N)||²−α,0)

---

Question 5
Consider the following Siamese network architecture:

The upper and lower neural networks have different input images, but have exactly the same parameters.

True

False
解析：網絡的參數是相同的

---

Question 6
You train a ConvNet on a dataset with 100 different classes. You wonder if you can find a hidden unit which responds strongly to pictures of cats. (I.e., a neuron so that, of all the input/training images that strongly activate that neuron, the majority are cat pictures.) You are more likely to find this unit in layer 4 of the network than in layer 1.

True

False

解析：對於卷積網絡的各層單元，隨着網絡深度的增加，隱藏層計算單元隨着層數的增加，從簡單的事物逐漸到更加複雜的事物。

---

Question 7
Neural style transfer is trained as a supervised learning task in which the goal is to input two images (x), and train a network to output a new, synthesized image (y).

True

False
解析：圖像並沒有相應的label

---

Question 8
In the deeper layers of a ConvNet, each channel corresponds to a different feature detector. The style matrix G^[l] measures the degree to which the activations of different feature detectors in layer l vary (or correlate) together with each other.

True

False

解析：定義“Style”表示 l 層的各個通道激活項之間的相關性。

---

Question 9
In neural style transfer, what is updated in each iteration of the optimization algorithm?

The regularization parameters

The neural network parameters

The pixel values of the content image C

The pixel values of the generated image G

解析：
神經風格遷移執行過程：

• 隨機初始化生成圖片G，如大小爲100×100×3；
• 使用梯度下降算法最小化上面定義的代價函數 J(G)， G：=G−∂J(G)/∂G；
  

---

10。Question 10
You are working with 3D data. You are building a network layer whose input volume has size 32x32x32x16 (this volume has 16 channels), and applies convolutions with 32 filters of dimension 3x3x3 (no padding, stride 1). What is the resulting output volume?

30x30x30x16

Undefined: This convolution step is impossible and cannot be performed because the dimensions specified don’t match up.

30x30x30x32
解析：

3D卷積：14×14×14×1∗5×5×5×1——>10×10×10×nc

---

參考：http://blog.csdn.net/koala_tree/article/details/78647528