Practice Limitations Of Cnn (23.7) - Convolutional Neural Network (CNN)

Practice: Limitations of CNN

Lesson 23.7Convolutional Neural Network (CNN)

Practise this section

9 questions

Flashcard drill
2 cards from this section. Quick, good the night before a test.
Exercise
6 questions · about 4 min · pass mark 70%. Hints available.
Sign up to start the exercise
Quiz
3 questions · about 2 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What does it mean when we say CNNs need a large dataset?
Show hintHide hint
Think about why more examples could help a model learn.
Question 2.
What is overfitting in a CNN?
Show hintHide hint
Consider what would happen if a model only memorizes its training images.
3Question 3.
What is the major data requirement for CNNs?
- Small datasets
- Moderate datasets
- Large datasets
Show hintHide hint
Think about why having more examples helps CNNs.
4Question 4.
True or False: Overfitting is beneficial for a CNN's performance.
- True
- False
Show hintHide hint
Consider what happens when a model learns too much detail about training data.
Question 5.
In a scenario where a CNN has been trained on images of only sunny days, describe how and why its performance would decline on cloudy day images.
Show hintHide hint
Think about how changing conditions can affect visibility and contrast in images.
Question 6.
Suppose a CNN exhibits signs of overfitting. Discuss at least two strategies that could be implemented to mitigate this issue.
Show hintHide hint
Consider how each method alters the training data or the model itself.

5 more questions in this section. Enroll free to practise them all.