Practice Pruning (3.2) - AI for Edge Devices and Internet of Things

Practise this section

9 questions

Flashcard drill
3 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 is pruning in AI?
Show hintHide hint
Think about simplifying a complex structure.
Question 2.
Name the two types of pruning discussed.
Show hintHide hint
One focuses on connections, the other on entire neurons.
3Question 3.
What is the main purpose of pruning in AI?
- To increase model size
- To remove unnecessary weights
- To add more nodes
Show hintHide hint
Think about what pruning does to complexity.
4Question 4.
True or False: Pruning may reduce the model's accuracy.
- True
- False
Show hintHide hint
What happens if essential components are removed?
Question 5.
Consider a neural network composed of 10,000 weights. If 30% of its weights are pruned, what will be the new total number of weights? Discuss the potential implications of this pruning on computation.
Show hintHide hint
Think percentages here!
Question 6.
Design an experiment to compare the effectiveness of weight pruning versus node pruning on a specific AI model. What metrics will you measure?
Show hintHide hint
What do you want to find out about each pruning effect?

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