Practice Infrastructure And Tools For Deployment (20.2) - Deployment and Monitoring of Machine Learning Models

Practice: Infrastructure and Tools for Deployment

Lesson 20.2Deployment 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 the purpose of model serialization?
Show hintHide hint
Think about storing and retrieving models.
Question 2.
Name one framework used for serving TensorFlow models.
Show hintHide hint
Consider popular frameworks for serving models.
3Question 3.
What format is not secure for untrusted input?
- Pickle
- ONNX
- Joblib
Show hintHide hint
Think about what serialization tool might have security risks.
4Question 4.
True or False: Docker allows for consistent deployment of applications across different environments.
- True
- False
Show hintHide hint
Consider the main purpose of containerization.
Question 5.
You have a machine learning model that you wish to deploy in a production environment. Describe the steps you would take using Docker and Kubernetes.
Show hintHide hint
Think about the entire flow from creation to deployment using containers.
Question 6.
Consider a scenario where you have deployed multiple models using various serving frameworks. Explain how you would handle updates or version changes to these models.
Show hintHide hint
Focus on how to automate the deployment and monitoring of updates.

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