TensorFlow for AI,ML&DL (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?
5. After max pooling a 26×26 image with a 2×2 filter, how big will the output be?
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!
TensorFlow for AI,ML&DL EXERCISE (WEEK 3)
For reference .ipynb file is attached below.
* The material and content uploaded on this website are for general information and reference purposes only. Please do it by your own first. COPYING MATERIALS IS STRICTLY PROHIBITED.