Coursera《Introduction to TensorFlow》第三周测验(Enhancing Vision with Convolutional Neural Networks)

Coursera《Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning》(Quiz of Week3)

Enhancing Vision with Convolutional Neural Networks

本博客为Coursera上的课程《Introduction to TensorFlow for Artificial Intelligence, Machine Learning, and Deep Learning》第三周的测验。

详细内容可参考原网站(https://wangpei.ink/)

目录

1. 第一题
2. 第二题
3. 第三题
4. 第四题
5. 第五题
6. 第六题

Coursera课程地址

---

第一题

1. What is a Convolution?

   A. A technique to isolate features in images
   B. A technique to make images bigger
   C. A technique to make images smaller
   D. A technique to filter out unwanted images

   答案：A

第二题

2. What is a Pooling?

   A. A technique to isolate features in images
   B. A technique to combine pictures
   C. A technique to reduce the information in an image while maintaining features
   D. A technique to make images sharper

   答案：C

第三题

3. How do Convolutions improve image recognition?

   A. They make the image clearer
   B. They make processing of images faster
   C. They isolate features in images
   D. They make the image smaller
   答案：C

第四题

4. After passing a 3x3 filter over a 28x28 image, how big will the output be?

   A. 25x25
   B. 31x31
   C. 28x28
   D. 26x26
   答案：D

第五题

5. After max pooling a 26x26 image with a 2x2 filter, how big will the output be?

   A. 13x13
   B. 56x56
   C. 26x26
   D. 28x28
   答案：A

第六题

6. Applying Convolutions on top of our Deep neural network will make training:

   A. It depends on many factors. It might make your training faster or slower, and a poorly designed Convolutional layer may even be less efficient than a plain DNN!
   B. Faster
   C. Stay the same
   D. Slower
   答案：A