Practice Monitoring Models In Production (20.4) - Deployment and Monitoring of Machine Learning Models

Practice: Monitoring Models in Production

Lesson 20.4Deployment and Monitoring of Machine Learning Models

Practise this section

10 questions

Flashcard drill
4 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
4 questions · about 3 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What is data drift?
Show hintHide hint
Think about how the model's input data can change.
Question 2.
Name a tool used for monitoring machine learning models.
Show hintHide hint
Consider the tools we discussed for tracking performance.
3Question 3.
What is the main reason for monitoring machine learning models?
- To increase compute resources
- To maintain accuracy
- To enhance training speed
Show hintHide hint
Think about why we need to ensure consistent performance.
4Question 4.
True or False: Latency is the number of predictions a model can handle per second.
- True
- False
Show hintHide hint
Recall the definitions of latency and throughput.
Question 5.
Given a deployed a credit scoring model with noticeable accuracy drops, design a monitoring plan using tools to track and investigate issues.
Show hintHide hint
Focus on how to integrate these tools systematically in your monitoring strategy.
Question 6.
Explain how to determine when retraining of a machine learning model is necessary and the strategies involved in setting up a feedback loop.
Show hintHide hint
Consider both automatic and manual aspects of monitoring and model updating.

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