Design an ML production system end-to-end: project scoping, data needs, modeling strategies, and deployment requirements.
CourseIntermediate
Machine Learning in Production
Instructor: Andrew Ng
DeepLearning.AI
Enroll Now
Also available on Coursera
- Intermediate
- Instructor: Andrew Ng
What you'll learn
Establish a model baseline, address concept drift, and prototype how to develop, deploy, and continuously improve a productionized ML application.
Skills you will gain
- Data Pipelines
- Model Pipelines
- Deployment Pipelines
- Managing Machine Learning Production systems
- ML Deployment Challenges
- Project Scoping and Design
- Concept Drift
- Model Baseline
- Human-level Performance (HLP)
- Data transformation
- Data augmentation
- Data validation
- Model Performance Analysis
- Model Monitoring
- MLOps
- Machine Learning Engineering for Production
Machine learning engineering for production refers to the tools, techniques, and practical experiences that transform theoretical ML knowledge into a production-ready skillset.
The Machine Learning in Production course covers how to conceptualize integrated systems that continuously operate in production as well as solve common challenges unique to the production environment. In striking contrast with standard machine learning modeling, production systems need to handle relentlessly evolving data. Moreover, the production system must run non-stop at the minimum cost while producing the maximum performance.
In this Machine Learning in Production course, you will build intuition about designing a production ML system end-to-end: project scoping, data needs, modeling strategies, and deployment patterns and technologies. You will learn strategies for addressing common challenges in production like establishing a model baseline, addressing concept drift, and performing error analysis. You’ll follow a framework for developing, deploying, and continuously improving a productionized ML application.
Understanding machine learning and deep learning concepts is essential, but if you’re looking to build an effective AI career, you need experience preparing your projects for deployment as well. Machine learning engineering for production combines the foundational concepts of machine learning with the skills and best practices of modern software development necessary to successfully deploy and maintain ML systems in real-world environments.
By the end of this program, you will be ready to:
- Design an ML production system end-to-end: project scoping, data needs, modeling strategies, and deployment requirements.
- Establish a model baseline, address concept drift, and prototype how to develop, deploy, and continuously improve a productionized ML application.
Course Outline
Machine Learning in Production
Week 1: Overview of the ML Lifecycle and Deployment
The Machine Learning Project Lifecycle
Deployment
Lecture Notes (Optional)
Week 2: Modeling Challenges and Strategies
Select and train a model
Error analysis and performance auditing
Data iteration
Graded assessment
Lecture Notes (Optional)
Ungraded Lab
Week 3: Data Definition and Baseline
Define Data and Establish Baseline
Label and Organize Data
Scoping (optional)
Lecture Notes (Optional)
Ungraded Lab
Final Project
Course Resources
Acknowledgements
Instructor
Frequently Asked Questions
What is machine learning engineering for production? Why is it relevant?
Machine learning engineering for production refers to the tools, techniques, and practical experiences that transform theoretical ML knowledge into a production-ready skillset.
Effectively deploying machine learning models requires competencies more commonly found in technical fields such as software engineering and DevOps. Machine learning engineering for production combines the foundational concepts of machine learning with the functional expertise of modern software development and engineering roles.
Understanding machine learning and deep learning concepts is essential, but if you’re looking to build an effective AI career, you need production engineering capabilities as well. With machine learning engineering for production, you can turn your knowledge of machine learning into production-ready skills.
What is the Machine Learning in Production Course about?
The Machine Learning in Production course covers how to conceptualize integrated systems that continuously operate in production as well as solve common challenges unique to the production environment. In striking contrast with standard machine learning modeling, production systems need to handle relentlessly evolving data. Moreover, the production system must run non-stop at the minimum cost while producing the maximum performance.
In this Machine Learning in Production course, you will build intuition about designing a production ML system end-to-end: project scoping, data needs, modeling strategies, and deployment patterns and technologies. You will learn strategies for addressing common challenges in production like establishing a model baseline, addressing concept drift, and performing error analysis. You’ll follow a framework for developing, deploying, and continuously improving a productionized ML application.
What will I be able to do after completing the Machine Learning in Production Course?
By the end, you will be ready to:
- Design an ML production system end-to-end: project scoping, data needs, modeling strategies, and deployment requirements.
- Establish a model baseline, address concept drift, and prototype how to develop, deploy, and continuously improve a productionized ML application.
What background knowledge is necessary for the Machine Learning in Production Course?
- Learners should have a working knowledge of AI and deep learning.
- Learners should have intermediate Python skills and experience with any deep learning framework (TensorFlow, Keras, or PyTorch).
- We highly recommend that you complete the updated Deep Learning Specialization before starting this course.
Who is the Machine Learning in Production Course for?
The Machine Learning in Production Course is for early-career machine learning practitioners or software engineers looking to gain practical knowledge of how to formulate a reproducible, traceable, and verifiable machine learning project for production.
How long does it take to complete the Machine Learning in Production Course?
At the rate of 5 hours a week, it typically takes 3 weeks to complete this course.
At the rate of 5 hours a week, it typically takes 3 weeks to complete this course.
Who is the Machine Learning in Production Course by?
The Machine Learning Engineering for Production course has been created by Andrew Ng
Andrew Ng is Founder of DeepLearning.AI, General Partner at AI Fund, Chairman and Co-Founder of Coursera, and an Adjunct Professor at Stanford University. As a pioneer in machine learning and online education, Dr. Ng has changed countless lives through his work in AI, authoring or co-authoring over 100 research papers in machine learning, robotics, and related fields. Previously, he was chief scientist at Baidu, the founding lead of the Google Brain team, and the co-founder of Coursera – the world’s largest MOOC platform.
Is this a standalone course or a Specialization?
This is a standalone course.
The course is a standalone course.
Will I receive a certificate at the end of the course?
Yes. You will receive a certificate at the end of the course if you are subscribed to the DeepLearning.AI Pro subscription, or a Coursera subscription and complete the assignments.
Sign Up
Be notified of new courses