Special applications: Face recognition & Neural style transfer

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
verification 是验证是不是这个人 1对1 recognition是识别，这个人是谁 1对N

2.Why do we learn a function d(img1,img2) for face verification? (Select all that apply.)
Given how few images we have per person, we need to apply transfer learning.
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).不用softmax,不是当作多分类问题做的
We need to solve a one-shot learning problem.
This allows us to learn to recognize a new person given just a single image of that person.
这题重在审题要清楚，这里问的是为什么要用图像相似度来做人脸的验证？所以，从这个角度选，而不是其他的。
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
每个人要几张图片，一张不够。
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.)

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
   确实是对的，自己手抖写错了，siamese network 参数当然是一毛一样的

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
越往后走，提取的特征越抽象

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
这题错了，是false，不是supervised learning ，是unsupervised learning ，风格迁移是没有标签的，没有labeled data，所以是非监督

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
风格迁移的代价函数包含两个部分，内容代价函数与风格代价函数，风格的话是对通道之间相关性的度量。

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 generated image G
The pixel values of the content image C
错了，更新的不是网络的参数，是生成的图片的像素值，估计和她不是监督学习有关系，他最小化的是代价函数。论坛里有个人说的很对，The goal is not to train the network but use the network to generate a new image until which satisfies the cost function。确实，风格迁移的目标不在训练网络怎样，而是生成图像怎样。see 2:50 to 3:00 in the Cost Function video for the explanation。字幕copy过来如下 What you can do is use gradient descent to minimize this so you can update G as G minus the derivative respect to the cost function of J of G. In this process, you're actually updating the pixel values of this image G which is a 100 by 100 by 3 maybe rgb channel image. Here's an example, let's say you start with this content image and this style image. This is a another probably Picasso image. Then when you initialize G randomly, you're initial randomly generated image is just this white noise image with each pixel value chosen at random. As you run gradient descent, you minimize the cost function J of G slowly through the pixel value so then you get slowly an image that looks more and more like your content image rendered in the style of your style image.

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?
Undefined: This convolution step is impossible and cannot be performed because the dimensions specified don’t match up.
30x30x30x16
30x30x30x32
三维其实和二维一样，直接算就好了。
错题：5.7.9