TensorFlow for AI,Ml&Dl Exercise & Quiz (Week 3)

1. What is a Convolution?

Ans: A technique to isolate features in images

2. What is a Pooling?

Ans: A technique to reduce the information in an image while maintaining features

3. How do Convolutions improve image recognition?

Ans: They isolate features in images

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

Ans: 26×26

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

Ans: 13×13

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

Ans: 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!