convolutional neural networks coursera week 4 quiz answers
Quiz - Special Applications: Face Recognition & Neural Style Transfer
1. Which of the following do you agree with?
- Face recognition requires comparing pictures against one person’s face.
- Face recognition requires K comparisons of a person’s face.
- Face verification requires K comparisons of a person’s face.
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.
- 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).
- This allows us to learn to recognize a new person given just a single image of that person.
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.
- False
- True
4. Which of the following is a correct definition of the triplet loss? Consider that a > O. (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 networks share parameters to have a consistent encoding for both images. True/False?
- True
- False
6. Our intuition about the layers of a neural network tells us that units that respond more to complex features are more likely to be in deeper layers. True/False?
- False
- True
7. In neural style transfer, we train the pixels of an image, and not the parameters of a network.
- True
- False
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
9. In neural style transfer, which of the following better express the gradients used?
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 3x3x3x16 (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
- 30×30×30×32
- 30x30x30x16